Code examples
Computer Vision Image classification from scratch Simple MNIST convnet Image classification via fine-tuning with EfficientNet Image classification with Vision Transformer Classification using Attention-based Deep Multiple Instance Learning Image classification with modern MLP models A mobile-friendly Transformer-based model for image classification Pneumonia Classification on TPU Compact Convolutional Transformers Image classification with ConvMixer Image classification with EANet (External Attention Transformer) Involutional neural networks Image classification with Perceiver Few-Shot learning with Reptile Semi-supervised image classification using contrastive pretraining with SimCLR Image classification with Swin Transformers Train a Vision Transformer on small datasets A Vision Transformer without Attention Image Classification using Global Context Vision Transformer When Recurrence meets Transformers Image segmentation with a U-Net-like architecture Multiclass semantic segmentation using DeepLabV3+ Highly accurate boundaries segmentation using BASNet Image Segmentation using Composable Fully-Convolutional Networks Object Detection with RetinaNet Keypoint Detection with Transfer Learning Object detection with Vision Transformers 3D image classification from CT scans Monocular depth estimation 3D volumetric rendering with NeRF Point cloud segmentation with PointNet Point cloud classification OCR model for reading Captchas Handwriting recognition Convolutional autoencoder for image denoising Low-light image enhancement using MIRNet Image Super-Resolution using an Efficient Sub-Pixel CNN Enhanced Deep Residual Networks for single-image super-resolution Zero-DCE for low-light image enhancement CutMix data augmentation for image classification MixUp augmentation for image classification RandAugment for Image Classification for Improved Robustness Image captioning Natural language image search with a Dual Encoder Visualizing what convnets learn Model interpretability with Integrated Gradients Investigating Vision Transformer representations Grad-CAM class activation visualization Near-duplicate image search Semantic Image Clustering Image similarity estimation using a Siamese Network with a contrastive loss Image similarity estimation using a Siamese Network with a triplet loss Metric learning for image similarity search Metric learning for image similarity search using TensorFlow Similarity Self-supervised contrastive learning with NNCLR Video Classification with a CNN-RNN Architecture Next-Frame Video Prediction with Convolutional LSTMs Video Classification with Transformers Video Vision Transformer Image Classification using BigTransfer (BiT) Gradient Centralization for Better Training Performance Learning to tokenize in Vision Transformers Knowledge Distillation FixRes: Fixing train-test resolution discrepancy Class Attention Image Transformers with LayerScale Augmenting convnets with aggregated attention Learning to Resize Semi-supervision and domain adaptation with AdaMatch Barlow Twins for Contrastive SSL Consistency training with supervision Distilling Vision Transformers Focal Modulation: A replacement for Self-Attention Using the Forward-Forward Algorithm for Image Classification Masked image modeling with Autoencoders Segment Anything Model with 🤗Transformers Semantic segmentation with SegFormer and Hugging Face Transformers Self-supervised contrastive learning with SimSiam Supervised Contrastive Learning Efficient Object Detection with YOLOV8 and KerasCV Natural Language Processing Structured Data Timeseries Generative Deep Learning Audio Data Reinforcement Learning Graph Data Quick Keras Recipes
► Code examples / Computer Vision / Point cloud classification with PointNet

Point cloud classification with PointNet

Author: David Griffiths
Date created: 2020/05/25
Last modified: 2024/01/09
Description: Implementation of PointNet for ModelNet10 classification.

ⓘ This example uses Keras 3

View in Colab • GitHub source

Point cloud classification

Introduction

Classification, detection and segmentation of unordered 3D point sets i.e. point clouds is a core problem in computer vision. This example implements the seminal point cloud deep learning paper PointNet (Qi et al., 2017). For a detailed intoduction on PointNet see this blog post.

Setup

If using colab first install trimesh with !pip install trimesh.

import os
import glob
import trimesh
import numpy as np
from tensorflow import data as tf_data
from keras import ops
import keras
from keras import layers
from matplotlib import pyplot as plt

keras.utils.set_random_seed(seed=42)

Load dataset

We use the ModelNet10 model dataset, the smaller 10 class version of the ModelNet40 dataset. First download the data:

DATA_DIR = keras.utils.get_file(
    "modelnet.zip",
    "http://3dvision.princeton.edu/projects/2014/3DShapeNets/ModelNet10.zip",
    extract=True,
)
DATA_DIR = os.path.join(os.path.dirname(DATA_DIR), "ModelNet10")

Downloading data from http://3dvision.princeton.edu/projects/2014/3DShapeNets/ModelNet10.zip

     0/473402300 ━━━━━━━━━━━━━━━━━━━━  0s 0s/step



  8192/473402300 ━━━━━━━━━━━━━━━━━━━━  1:06:44 8us/step



 40960/473402300 ━━━━━━━━━━━━━━━━━━━━  26:17 3us/step



 90112/473402300 ━━━━━━━━━━━━━━━━━━━━  17:49 2us/step



188416/473402300 ━━━━━━━━━━━━━━━━━━━━  11:20 1us/step



385024/473402300 ━━━━━━━━━━━━━━━━━━━━  6:55 1us/step



786432/473402300 ━━━━━━━━━━━━━━━━━━━━  4:03 1us/step



1581056/473402300 ━━━━━━━━━━━━━━━━━━━━ 2:21 0us/step



3170304/473402300 ━━━━━━━━━━━━━━━━━━━━ 1:20 0us/step



6004736/473402300 ━━━━━━━━━━━━━━━━━━━━ 47s 0us/step 



8880128/473402300 ━━━━━━━━━━━━━━━━━━━━ 35s 0us/step



11902976/473402300 ━━━━━━━━━━━━━━━━━━━━ 28s 0us/step



14925824/473402300 ━━━━━━━━━━━━━━━━━━━━ 24s 0us/step



17915904/473402300 ━━━━━━━━━━━━━━━━━━━━ 22s 0us/step



21020672/473402300 ━━━━━━━━━━━━━━━━━━━━ 20s 0us/step



23977984/473402300 ━━━━━━━━━━━━━━━━━━━━ 18s 0us/step



26861568/473402300 ━━━━━━━━━━━━━━━━━━━━ 17s 0us/step



29958144/473402300 ━━━━━━━━━━━━━━━━━━━━ 16s 0us/step



33071104/473402300 ━━━━━━━━━━━━━━━━━━━━ 16s 0us/step



36175872/473402300 ━━━━━━━━━━━━━━━━━━━━ 15s 0us/step



39206912/473402300 ━━━━━━━━━━━━━━━━━━━━ 14s 0us/step



41902080/473402300 ━━━━━━━━━━━━━━━━━━━━ 14s 0us/step



45015040/473402300 ━━━━━━━━━━━━━━━━━━━━ 14s 0us/step



48021504/473402300 ━━━━━━━━━━━━━━━━━━━━ 13s 0us/step



51003392/473402300 ━━━━━━━━━━━━━━━━━━━━ 13s 0us/step



53960704/473402300 ━━━━━━━━━━━━━━━━━━━━ 13s 0us/step



56803328/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step



59834368/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step



62750720/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step



65839104/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step



68698112/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step



71385088/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step



74432512/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step



77365248/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step



80363520/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step



83156992/473402300 ━━━━━━━━━━━━━━━━━━━━ 11s 0us/step



86179840/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



89300992/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



92282880/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



95371264/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



98410496/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



101130240/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



104169472/473402300 ━━━━━━━━━━━━━━━━━━━━ 10s 0us/step



107192320/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step 



110297088/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



113344512/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



116391936/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



119513088/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



122626048/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



125313024/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



128368640/473402300 ━━━━━━━━━━━━━━━━━━━━ 9s 0us/step



131432448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



134520832/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



137560064/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



140648448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



143720448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



146808832/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



149864448/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



152592384/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



155623424/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



158728192/473402300 ━━━━━━━━━━━━━━━━━━━━ 8s 0us/step



161783808/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



164806656/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



167895040/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



170975232/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



174071808/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



177119232/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



180166656/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



182976512/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



185884672/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



188932096/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



192028672/473402300 ━━━━━━━━━━━━━━━━━━━━ 7s 0us/step



195117056/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



198189056/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



201302016/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



204406784/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



207470592/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



210575360/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



213581824/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



216268800/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



218374144/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



220569600/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



222363648/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



225345536/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



228425728/473402300 ━━━━━━━━━━━━━━━━━━━━ 6s 0us/step



231473152/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



234577920/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



237690880/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



240746496/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



243834880/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



246898688/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



249954304/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



252936192/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



255672320/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



258695168/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



261734400/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



264847360/473402300 ━━━━━━━━━━━━━━━━━━━━ 5s 0us/step



267919360/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



271015936/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



273768448/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



276840448/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



279625728/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



282525696/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



285581312/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



288645120/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



291733504/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



294682624/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



297795584/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



300851200/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



303955968/473402300 ━━━━━━━━━━━━━━━━━━━━ 4s 0us/step



306798592/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



309846016/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



312926208/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



315990016/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



319053824/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



322134016/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



325099520/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



328187904/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



331251712/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



334364672/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



337477632/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



340598784/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



343130112/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



345554944/473402300 ━━━━━━━━━━━━━━━━━━━━ 3s 0us/step



347570176/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



350224384/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



352436224/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



355393536/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



357179392/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



359858176/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



362045440/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364281856/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364298240/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364306432/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364314624/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364322816/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364331008/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364339200/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364347392/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364355584/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364363776/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364371968/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364380160/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364396544/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364445696/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



364601344/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



365084672/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



366510080/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



369491968/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



372400128/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



375521280/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



378535936/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



381558784/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



384475136/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



387571712/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



390463488/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



393551872/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



396632064/473402300 ━━━━━━━━━━━━━━━━━━━━ 2s 0us/step



399704064/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



402767872/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



405790720/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



408854528/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



411975680/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



414982144/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



418045952/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



421167104/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



423878656/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



426999808/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



430112768/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



433053696/473402300 ━━━━━━━━━━━━━━━━━━━━ 1s 0us/step



436125696/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



439189504/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



442286080/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



445063168/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



448118784/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



451166208/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



454262784/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



457293824/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



460275712/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



463011840/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



466018304/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



469057536/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



472145920/473402300 ━━━━━━━━━━━━━━━━━━━━ 0s 0us/step



473402300/473402300 ━━━━━━━━━━━━━━━━━━━━ 12s 0us/step

We can use the trimesh package to read and visualize the .off mesh files.

mesh = trimesh.load(os.path.join(DATA_DIR, "chair/train/chair_0001.off"))
mesh.show()

To convert a mesh file to a point cloud we first need to sample points on the mesh surface. .sample() performs a uniform random sampling. Here we sample at 2048 locations and visualize in matplotlib.

points = mesh.sample(2048)

fig = plt.figure(figsize=(5, 5))
ax = fig.add_subplot(111, projection="3d")
ax.scatter(points[:, 0], points[:, 1], points[:, 2])
ax.set_axis_off()
plt.show()

png

To generate a tf.data.Dataset() we need to first parse through the ModelNet data folders. Each mesh is loaded and sampled into a point cloud before being added to a standard python list and converted to a numpy array. We also store the current enumerate index value as the object label and use a dictionary to recall this later.

def parse_dataset(num_points=2048):
    train_points = []
    train_labels = []
    test_points = []
    test_labels = []
    class_map = {}
    folders = glob.glob(os.path.join(DATA_DIR, "[!README]*"))

    for i, folder in enumerate(folders):
        print("processing class: {}".format(os.path.basename(folder)))
        # store folder name with ID so we can retrieve later
        class_map[i] = folder.split("/")[-1]
        # gather all files
        train_files = glob.glob(os.path.join(folder, "train/*"))
        test_files = glob.glob(os.path.join(folder, "test/*"))

        for f in train_files:
            train_points.append(trimesh.load(f).sample(num_points))
            train_labels.append(i)

        for f in test_files:
            test_points.append(trimesh.load(f).sample(num_points))
            test_labels.append(i)

    return (
        np.array(train_points),
        np.array(test_points),
        np.array(train_labels),
        np.array(test_labels),
        class_map,
    )

Set the number of points to sample and batch size and parse the dataset. This can take ~5minutes to complete.

NUM_POINTS = 2048
NUM_CLASSES = 10
BATCH_SIZE = 32

train_points, test_points, train_labels, test_labels, CLASS_MAP = parse_dataset(
    NUM_POINTS
)

processing class: bathtub

processing class: monitor

processing class: desk

processing class: dresser

processing class: toilet

processing class: bed

processing class: sofa

processing class: chair

processing class: night_stand

processing class: table

Our data can now be read into a tf.data.Dataset() object. We set the shuffle buffer size to the entire size of the dataset as prior to this the data is ordered by class. Data augmentation is important when working with point cloud data. We create a augmentation function to jitter and shuffle the train dataset.

def augment(points, label):
    # jitter points
    points += keras.random.uniform(points.shape, -0.005, 0.005, dtype="float64")
    # shuffle points
    points = keras.random.shuffle(points)
    return points, label


train_size = 0.8
dataset = tf_data.Dataset.from_tensor_slices((train_points, train_labels))
test_dataset = tf_data.Dataset.from_tensor_slices((test_points, test_labels))
train_dataset_size = int(len(dataset) * train_size)

dataset = dataset.shuffle(len(train_points)).map(augment)
test_dataset = test_dataset.shuffle(len(test_points)).batch(BATCH_SIZE)

train_dataset = dataset.take(train_dataset_size).batch(BATCH_SIZE)
validation_dataset = dataset.skip(train_dataset_size).batch(BATCH_SIZE)

Build a model

Each convolution and fully-connected layer (with exception for end layers) consists of Convolution / Dense -> Batch Normalization -> ReLU Activation.

def conv_bn(x, filters):
    x = layers.Conv1D(filters, kernel_size=1, padding="valid")(x)
    x = layers.BatchNormalization(momentum=0.0)(x)
    return layers.Activation("relu")(x)


def dense_bn(x, filters):
    x = layers.Dense(filters)(x)
    x = layers.BatchNormalization(momentum=0.0)(x)
    return layers.Activation("relu")(x)

PointNet consists of two core components. The primary MLP network, and the transformer net (T-net). The T-net aims to learn an affine transformation matrix by its own mini network. The T-net is used twice. The first time to transform the input features (n, 3) into a canonical representation. The second is an affine transformation for alignment in feature space (n, 3). As per the original paper we constrain the transformation to be close to an orthogonal matrix (i.e. ||X*X^T - I|| = 0).

class OrthogonalRegularizer(keras.regularizers.Regularizer):
    def __init__(self, num_features, l2reg=0.001):
        self.num_features = num_features
        self.l2reg = l2reg
        self.eye = ops.eye(num_features)

    def __call__(self, x):
        x = ops.reshape(x, (-1, self.num_features, self.num_features))
        xxt = ops.tensordot(x, x, axes=(2, 2))
        xxt = ops.reshape(xxt, (-1, self.num_features, self.num_features))
        return ops.sum(self.l2reg * ops.square(xxt - self.eye))

We can then define a general function to build T-net layers.

def tnet(inputs, num_features):
    # Initialise bias as the identity matrix
    bias = keras.initializers.Constant(np.eye(num_features).flatten())
    reg = OrthogonalRegularizer(num_features)

    x = conv_bn(inputs, 32)
    x = conv_bn(x, 64)
    x = conv_bn(x, 512)
    x = layers.GlobalMaxPooling1D()(x)
    x = dense_bn(x, 256)
    x = dense_bn(x, 128)
    x = layers.Dense(
        num_features * num_features,
        kernel_initializer="zeros",
        bias_initializer=bias,
        activity_regularizer=reg,
    )(x)
    feat_T = layers.Reshape((num_features, num_features))(x)
    # Apply affine transformation to input features
    return layers.Dot(axes=(2, 1))([inputs, feat_T])

The main network can be then implemented in the same manner where the t-net mini models can be dropped in a layers in the graph. Here we replicate the network architecture published in the original paper but with half the number of weights at each layer as we are using the smaller 10 class ModelNet dataset.

inputs = keras.Input(shape=(NUM_POINTS, 3))

x = tnet(inputs, 3)
x = conv_bn(x, 32)
x = conv_bn(x, 32)
x = tnet(x, 32)
x = conv_bn(x, 32)
x = conv_bn(x, 64)
x = conv_bn(x, 512)
x = layers.GlobalMaxPooling1D()(x)
x = dense_bn(x, 256)
x = layers.Dropout(0.3)(x)
x = dense_bn(x, 128)
x = layers.Dropout(0.3)(x)

outputs = layers.Dense(NUM_CLASSES, activation="softmax")(x)

model = keras.Model(inputs=inputs, outputs=outputs, name="pointnet")
model.summary()

Model: "pointnet"

┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━┓
┃ Layer (type)        ┃ Output Shape      ┃ Param # ┃ Connected to         ┃
┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━┩
│ input_layer         │ (None, 2048, 3)   │       0 │ -                    │
│ (InputLayer)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d (Conv1D)     │ (None, 2048, 32)  │     128 │ input_layer[0][0]    │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalization │ (None, 2048, 32)  │     128 │ conv1d[0][0]         │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation          │ (None, 2048, 32)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_1 (Conv1D)   │ (None, 2048, 64)  │   2,112 │ activation[0][0]     │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 64)  │     256 │ conv1d_1[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_1        │ (None, 2048, 64)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_2 (Conv1D)   │ (None, 2048, 512) │  33,280 │ activation_1[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 512) │   2,048 │ conv1d_2[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_2        │ (None, 2048, 512) │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ global_max_pooling… │ (None, 512)       │       0 │ activation_2[0][0]   │
│ (GlobalMaxPooling1… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense (Dense)       │ (None, 256)       │ 131,328 │ global_max_pooling1… │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 256)       │   1,024 │ dense[0][0]          │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_3        │ (None, 256)       │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_1 (Dense)     │ (None, 128)       │  32,896 │ activation_3[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 128)       │     512 │ dense_1[0][0]        │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_4        │ (None, 128)       │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_2 (Dense)     │ (None, 9)         │   1,161 │ activation_4[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ reshape (Reshape)   │ (None, 3, 3)      │       0 │ dense_2[0][0]        │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dot (Dot)           │ (None, 2048, 3)   │       0 │ input_layer[0][0],   │
│                     │                   │         │ reshape[0][0]        │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_3 (Conv1D)   │ (None, 2048, 32)  │     128 │ dot[0][0]            │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 32)  │     128 │ conv1d_3[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_5        │ (None, 2048, 32)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_4 (Conv1D)   │ (None, 2048, 32)  │   1,056 │ activation_5[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 32)  │     128 │ conv1d_4[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_6        │ (None, 2048, 32)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_5 (Conv1D)   │ (None, 2048, 32)  │   1,056 │ activation_6[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 32)  │     128 │ conv1d_5[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_7        │ (None, 2048, 32)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_6 (Conv1D)   │ (None, 2048, 64)  │   2,112 │ activation_7[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 64)  │     256 │ conv1d_6[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_8        │ (None, 2048, 64)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_7 (Conv1D)   │ (None, 2048, 512) │  33,280 │ activation_8[0][0]   │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 512) │   2,048 │ conv1d_7[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_9        │ (None, 2048, 512) │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ global_max_pooling… │ (None, 512)       │       0 │ activation_9[0][0]   │
│ (GlobalMaxPooling1… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_3 (Dense)     │ (None, 256)       │ 131,328 │ global_max_pooling1… │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 256)       │   1,024 │ dense_3[0][0]        │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_10       │ (None, 256)       │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_4 (Dense)     │ (None, 128)       │  32,896 │ activation_10[0][0]  │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 128)       │     512 │ dense_4[0][0]        │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_11       │ (None, 128)       │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_5 (Dense)     │ (None, 1024)      │ 132,096 │ activation_11[0][0]  │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ reshape_1 (Reshape) │ (None, 32, 32)    │       0 │ dense_5[0][0]        │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dot_1 (Dot)         │ (None, 2048, 32)  │       0 │ activation_6[0][0],  │
│                     │                   │         │ reshape_1[0][0]      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_8 (Conv1D)   │ (None, 2048, 32)  │   1,056 │ dot_1[0][0]          │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 32)  │     128 │ conv1d_8[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_12       │ (None, 2048, 32)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_9 (Conv1D)   │ (None, 2048, 64)  │   2,112 │ activation_12[0][0]  │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 64)  │     256 │ conv1d_9[0][0]       │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_13       │ (None, 2048, 64)  │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ conv1d_10 (Conv1D)  │ (None, 2048, 512) │  33,280 │ activation_13[0][0]  │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 2048, 512) │   2,048 │ conv1d_10[0][0]      │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_14       │ (None, 2048, 512) │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ global_max_pooling… │ (None, 512)       │       0 │ activation_14[0][0]  │
│ (GlobalMaxPooling1… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_6 (Dense)     │ (None, 256)       │ 131,328 │ global_max_pooling1… │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 256)       │   1,024 │ dense_6[0][0]        │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_15       │ (None, 256)       │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dropout (Dropout)   │ (None, 256)       │       0 │ activation_15[0][0]  │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_7 (Dense)     │ (None, 128)       │  32,896 │ dropout[0][0]        │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ batch_normalizatio… │ (None, 128)       │     512 │ dense_7[0][0]        │
│ (BatchNormalizatio… │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ activation_16       │ (None, 128)       │       0 │ batch_normalization… │
│ (Activation)        │                   │         │                      │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dropout_1 (Dropout) │ (None, 128)       │       0 │ activation_16[0][0]  │
├─────────────────────┼───────────────────┼─────────┼──────────────────────┤
│ dense_8 (Dense)     │ (None, 10)        │   1,290 │ dropout_1[0][0]      │
└─────────────────────┴───────────────────┴─────────┴──────────────────────┘

 Total params: 748,979 (2.86 MB)

 Trainable params: 742,899 (2.83 MB)

 Non-trainable params: 6,080 (23.75 KB)

Train model

Once the model is defined it can be trained like any other standard classification model using .compile() and .fit().

model.compile(
    loss="sparse_categorical_crossentropy",
    optimizer=keras.optimizers.Adam(learning_rate=0.001),
    metrics=["sparse_categorical_accuracy"],
)

model.fit(train_dataset, epochs=20, validation_data=validation_dataset)

Epoch 1/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 16:59 10s/step - loss: 70.7465 - sparse_categorical_accuracy: 0.2188



2/100 ━━━━━━━━━━━━━━━━━━━━ 2:06 1s/step - loss: 69.8872 - sparse_categorical_accuracy: 0.1953 



3/100 ━━━━━━━━━━━━━━━━━━━━ 2:00 1s/step - loss: 69.4798 - sparse_categorical_accuracy: 0.1823



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:57 1s/step - loss: 68.7454 - sparse_categorical_accuracy: 0.1719



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:53 1s/step - loss: 67.8508 - sparse_categorical_accuracy: 0.1700



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:50 1s/step - loss: 67.0352 - sparse_categorical_accuracy: 0.1703



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:47 1s/step - loss: 66.3409 - sparse_categorical_accuracy: 0.1702



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:45 1s/step - loss: 65.5973 - sparse_categorical_accuracy: 0.1734



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 64.8169 - sparse_categorical_accuracy: 0.1761



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 64.0699 - sparse_categorical_accuracy: 0.1769



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 63.3220 - sparse_categorical_accuracy: 0.1779



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 62.6677 - sparse_categorical_accuracy: 0.1776



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 62.0234 - sparse_categorical_accuracy: 0.1778



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 61.4256 - sparse_categorical_accuracy: 0.1774



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 60.8435 - sparse_categorical_accuracy: 0.1772



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 60.2982 - sparse_categorical_accuracy: 0.1771



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 59.7788 - sparse_categorical_accuracy: 0.1773



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 59.2792 - sparse_categorical_accuracy: 0.1777



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 58.7959 - sparse_categorical_accuracy: 0.1782



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 58.3345 - sparse_categorical_accuracy: 0.1787



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 57.8916 - sparse_categorical_accuracy: 0.1794



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 57.4650 - sparse_categorical_accuracy: 0.1803



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 57.0690 - sparse_categorical_accuracy: 0.1811



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 56.6876 - sparse_categorical_accuracy: 0.1819



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 56.3285 - sparse_categorical_accuracy: 0.1827



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 55.9864 - sparse_categorical_accuracy: 0.1834



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 55.6550 - sparse_categorical_accuracy: 0.1843



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 55.3351 - sparse_categorical_accuracy: 0.1852



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 55.0261 - sparse_categorical_accuracy: 0.1863



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 54.7329 - sparse_categorical_accuracy: 0.1872



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 54.4503 - sparse_categorical_accuracy: 0.1882



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 54.1778 - sparse_categorical_accuracy: 0.1891



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 53.9170 - sparse_categorical_accuracy: 0.1900



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 53.6651 - sparse_categorical_accuracy: 0.1909



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 53.4239 - sparse_categorical_accuracy: 0.1916



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 53.1926 - sparse_categorical_accuracy: 0.1922



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 52.9695 - sparse_categorical_accuracy: 0.1929



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 52.7542 - sparse_categorical_accuracy: 0.1935



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 52.5469 - sparse_categorical_accuracy: 0.1940



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 52.3461 - sparse_categorical_accuracy: 0.1946



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 52.1509 - sparse_categorical_accuracy: 0.1950



42/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 51.9608 - sparse_categorical_accuracy: 0.1955



43/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 51.7759 - sparse_categorical_accuracy: 0.1960



44/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 51.5960 - sparse_categorical_accuracy: 0.1966 



45/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 51.4224 - sparse_categorical_accuracy: 0.1971



46/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 51.2539 - sparse_categorical_accuracy: 0.1976



47/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 51.0897 - sparse_categorical_accuracy: 0.1982



48/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 50.9300 - sparse_categorical_accuracy: 0.1987



49/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 50.7742 - sparse_categorical_accuracy: 0.1992



50/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 50.6223 - sparse_categorical_accuracy: 0.1997



51/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 50.4747 - sparse_categorical_accuracy: 0.2001



52/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 50.3312 - sparse_categorical_accuracy: 0.2006



53/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 50.1910 - sparse_categorical_accuracy: 0.2011



54/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 50.0539 - sparse_categorical_accuracy: 0.2017



55/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 49.9200 - sparse_categorical_accuracy: 0.2022



56/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 49.7896 - sparse_categorical_accuracy: 0.2027



57/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 49.6620 - sparse_categorical_accuracy: 0.2032



58/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 49.5372 - sparse_categorical_accuracy: 0.2037



59/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 49.4152 - sparse_categorical_accuracy: 0.2041



60/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 49.2957 - sparse_categorical_accuracy: 0.2046



61/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 49.1790 - sparse_categorical_accuracy: 0.2050



62/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 49.0646 - sparse_categorical_accuracy: 0.2054



63/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 48.9525 - sparse_categorical_accuracy: 0.2058



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 48.8427 - sparse_categorical_accuracy: 0.2062



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 48.7353 - sparse_categorical_accuracy: 0.2065



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 48.6299 - sparse_categorical_accuracy: 0.2069



67/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 48.5266 - sparse_categorical_accuracy: 0.2072



68/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 48.4277 - sparse_categorical_accuracy: 0.2075



69/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 48.3308 - sparse_categorical_accuracy: 0.2078



70/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 48.2357 - sparse_categorical_accuracy: 0.2081



71/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 48.1423 - sparse_categorical_accuracy: 0.2084



72/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 48.0505 - sparse_categorical_accuracy: 0.2087



73/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 47.9604 - sparse_categorical_accuracy: 0.2090



74/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 47.8719 - sparse_categorical_accuracy: 0.2093



75/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 47.7852 - sparse_categorical_accuracy: 0.2096



76/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 47.7000 - sparse_categorical_accuracy: 0.2098



77/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 47.6164 - sparse_categorical_accuracy: 0.2101



78/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 47.5342 - sparse_categorical_accuracy: 0.2104



79/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 47.4536 - sparse_categorical_accuracy: 0.2106



80/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 47.3744 - sparse_categorical_accuracy: 0.2109



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 47.2967 - sparse_categorical_accuracy: 0.2112



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 47.2202 - sparse_categorical_accuracy: 0.2114



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 47.1450 - sparse_categorical_accuracy: 0.2117



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 47.0711 - sparse_categorical_accuracy: 0.2119



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 46.9984 - sparse_categorical_accuracy: 0.2122



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 46.9270 - sparse_categorical_accuracy: 0.2124



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 46.8568 - sparse_categorical_accuracy: 0.2126



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 46.7877 - sparse_categorical_accuracy: 0.2129



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 46.7196 - sparse_categorical_accuracy: 0.2131



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 46.6525 - sparse_categorical_accuracy: 0.2133



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 46.5865 - sparse_categorical_accuracy: 0.2135 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 46.5215 - sparse_categorical_accuracy: 0.2137



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 46.4574 - sparse_categorical_accuracy: 0.2139



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 46.3946 - sparse_categorical_accuracy: 0.2141



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 46.3327 - sparse_categorical_accuracy: 0.2143



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 46.2717 - sparse_categorical_accuracy: 0.2145



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 46.2115 - sparse_categorical_accuracy: 0.2147



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 46.1522 - sparse_categorical_accuracy: 0.2149



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 46.0937 - sparse_categorical_accuracy: 0.2151



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 46.0345 - sparse_categorical_accuracy: 0.2154



100/100 ━━━━━━━━━━━━━━━━━━━━ 119s 1s/step - loss: 45.9764 - sparse_categorical_accuracy: 0.2156 - val_loss: 4122951.0000 - val_sparse_categorical_accuracy: 0.3154

Epoch 2/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 36.7920 - sparse_categorical_accuracy: 0.2500



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.8501 - sparse_categorical_accuracy: 0.2188



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.8194 - sparse_categorical_accuracy: 0.2049



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.7948 - sparse_categorical_accuracy: 0.1947



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.7802 - sparse_categorical_accuracy: 0.1907



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.7761 - sparse_categorical_accuracy: 0.1911



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.7720 - sparse_categorical_accuracy: 0.1937



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.7660 - sparse_categorical_accuracy: 0.1964



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.7617 - sparse_categorical_accuracy: 0.1977



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7567 - sparse_categorical_accuracy: 0.1992



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7558 - sparse_categorical_accuracy: 0.2007



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.7534 - sparse_categorical_accuracy: 0.2022



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.7539 - sparse_categorical_accuracy: 0.2033



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.7521 - sparse_categorical_accuracy: 0.2049



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.7500 - sparse_categorical_accuracy: 0.2064



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.7464 - sparse_categorical_accuracy: 0.2087



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.7410 - sparse_categorical_accuracy: 0.2116



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.7356 - sparse_categorical_accuracy: 0.2138



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.7314 - sparse_categorical_accuracy: 0.2157



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.7275 - sparse_categorical_accuracy: 0.2178



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.7235 - sparse_categorical_accuracy: 0.2196



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.7189 - sparse_categorical_accuracy: 0.2218



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.7141 - sparse_categorical_accuracy: 0.2241



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.7087 - sparse_categorical_accuracy: 0.2262



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.7027 - sparse_categorical_accuracy: 0.2283



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.6970 - sparse_categorical_accuracy: 0.2303



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.6911 - sparse_categorical_accuracy: 0.2325



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.6862 - sparse_categorical_accuracy: 0.2342



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.6818 - sparse_categorical_accuracy: 0.2357



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.6766 - sparse_categorical_accuracy: 0.2372



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.6717 - sparse_categorical_accuracy: 0.2387



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.6670 - sparse_categorical_accuracy: 0.2403



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.6629 - sparse_categorical_accuracy: 0.2418



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.6591 - sparse_categorical_accuracy: 0.2431



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.6551 - sparse_categorical_accuracy: 0.2444



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.6513 - sparse_categorical_accuracy: 0.2456



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.6478 - sparse_categorical_accuracy: 0.2467



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.6441 - sparse_categorical_accuracy: 0.2477



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.6405 - sparse_categorical_accuracy: 0.2487



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.6368 - sparse_categorical_accuracy: 0.2497



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2507



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2515 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2523



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2531



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2538



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2546



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2554



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2561



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2568



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2575



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2582



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2588



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2594



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2600



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.6329 - sparse_categorical_accuracy: 0.2606



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2612



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2618



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2624



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2630



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.6331 - sparse_categorical_accuracy: 0.2636



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2641



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2646



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.6329 - sparse_categorical_accuracy: 0.2652



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.6329 - sparse_categorical_accuracy: 0.2657



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.6330 - sparse_categorical_accuracy: 0.2662



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.6332 - sparse_categorical_accuracy: 0.2667



67/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.6336 - sparse_categorical_accuracy: 0.2671



68/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.6340 - sparse_categorical_accuracy: 0.2674



69/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.6346 - sparse_categorical_accuracy: 0.2678



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.6352 - sparse_categorical_accuracy: 0.2682



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.6359 - sparse_categorical_accuracy: 0.2685



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.6365 - sparse_categorical_accuracy: 0.2688



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.6371 - sparse_categorical_accuracy: 0.2690



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.6377 - sparse_categorical_accuracy: 0.2693



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.6384 - sparse_categorical_accuracy: 0.2696



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.6389 - sparse_categorical_accuracy: 0.2698



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.6394 - sparse_categorical_accuracy: 0.2700



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.6398 - sparse_categorical_accuracy: 0.2703



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.6401 - sparse_categorical_accuracy: 0.2706



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.6406 - sparse_categorical_accuracy: 0.2708



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.6411 - sparse_categorical_accuracy: 0.2710



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.6415 - sparse_categorical_accuracy: 0.2712



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.6419 - sparse_categorical_accuracy: 0.2714



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.6423 - sparse_categorical_accuracy: 0.2716



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.6426 - sparse_categorical_accuracy: 0.2718



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.6429 - sparse_categorical_accuracy: 0.2720



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.6431 - sparse_categorical_accuracy: 0.2723



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.6432 - sparse_categorical_accuracy: 0.2725



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.6433 - sparse_categorical_accuracy: 0.2727



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.6434 - sparse_categorical_accuracy: 0.2730



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.6435 - sparse_categorical_accuracy: 0.2732 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.6435 - sparse_categorical_accuracy: 0.2734



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.6434 - sparse_categorical_accuracy: 0.2736



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.6432 - sparse_categorical_accuracy: 0.2738



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.6430 - sparse_categorical_accuracy: 0.2740



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.6427 - sparse_categorical_accuracy: 0.2742



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.6424 - sparse_categorical_accuracy: 0.2744



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.6421 - sparse_categorical_accuracy: 0.2746



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.6418 - sparse_categorical_accuracy: 0.2748



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.6402 - sparse_categorical_accuracy: 0.2749



100/100 ━━━━━━━━━━━━━━━━━━━━ 108s 1s/step - loss: 36.6386 - sparse_categorical_accuracy: 0.2751 - val_loss: 20961250112658389073920.0000 - val_sparse_categorical_accuracy: 0.3191

Epoch 3/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 57:33 35s/step - loss: 35.9745 - sparse_categorical_accuracy: 0.3438



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.1432 - sparse_categorical_accuracy: 0.3359 



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.1628 - sparse_categorical_accuracy: 0.3420



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.1912 - sparse_categorical_accuracy: 0.3424



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.2222 - sparse_categorical_accuracy: 0.3390



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.2318 - sparse_categorical_accuracy: 0.3345



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.2484 - sparse_categorical_accuracy: 0.3301



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.2639 - sparse_categorical_accuracy: 0.3284



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3282



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3304



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3316



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.2714 - sparse_categorical_accuracy: 0.3319



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.2731 - sparse_categorical_accuracy: 0.3319



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.2716 - sparse_categorical_accuracy: 0.3325



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.2714 - sparse_categorical_accuracy: 0.3327



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.2703 - sparse_categorical_accuracy: 0.3325



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.2685 - sparse_categorical_accuracy: 0.3322



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.2665 - sparse_categorical_accuracy: 0.3322



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.2672 - sparse_categorical_accuracy: 0.3320



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.2689 - sparse_categorical_accuracy: 0.3316



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.2700 - sparse_categorical_accuracy: 0.3311



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.2712 - sparse_categorical_accuracy: 0.3307



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.2732 - sparse_categorical_accuracy: 0.3301



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.2753 - sparse_categorical_accuracy: 0.3293



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.2772 - sparse_categorical_accuracy: 0.3284



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.2789 - sparse_categorical_accuracy: 0.3275



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.2803 - sparse_categorical_accuracy: 0.3266



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.2832 - sparse_categorical_accuracy: 0.3258



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.2886 - sparse_categorical_accuracy: 0.3251



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.2944 - sparse_categorical_accuracy: 0.3245



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.3001 - sparse_categorical_accuracy: 0.3237



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.3053 - sparse_categorical_accuracy: 0.3231



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.3102 - sparse_categorical_accuracy: 0.3226



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.3150 - sparse_categorical_accuracy: 0.3221



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.3196 - sparse_categorical_accuracy: 0.3216



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.3239 - sparse_categorical_accuracy: 0.3212



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.3281 - sparse_categorical_accuracy: 0.3209



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.3322 - sparse_categorical_accuracy: 0.3204



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.3358 - sparse_categorical_accuracy: 0.3201



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.3392 - sparse_categorical_accuracy: 0.3199



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.3423 - sparse_categorical_accuracy: 0.3196



42/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.3453 - sparse_categorical_accuracy: 0.3195



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.3482 - sparse_categorical_accuracy: 0.3193 



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.3509 - sparse_categorical_accuracy: 0.3193



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.3534 - sparse_categorical_accuracy: 0.3192



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.3557 - sparse_categorical_accuracy: 0.3191



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.3577 - sparse_categorical_accuracy: 0.3191



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.3597 - sparse_categorical_accuracy: 0.3190



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.3617 - sparse_categorical_accuracy: 0.3188



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.3636 - sparse_categorical_accuracy: 0.3186



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.3654 - sparse_categorical_accuracy: 0.3183



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.3671 - sparse_categorical_accuracy: 0.3181



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.3687 - sparse_categorical_accuracy: 0.3179



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.3705 - sparse_categorical_accuracy: 0.3177



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.3723 - sparse_categorical_accuracy: 0.3175



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.3744 - sparse_categorical_accuracy: 0.3173



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.3764 - sparse_categorical_accuracy: 0.3171



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.3784 - sparse_categorical_accuracy: 0.3170



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.3805 - sparse_categorical_accuracy: 0.3168



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.3824 - sparse_categorical_accuracy: 0.3167



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.3843 - sparse_categorical_accuracy: 0.3166



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.3862 - sparse_categorical_accuracy: 0.3165



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.3879 - sparse_categorical_accuracy: 0.3164



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.3893 - sparse_categorical_accuracy: 0.3163



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.3907 - sparse_categorical_accuracy: 0.3163



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.3921 - sparse_categorical_accuracy: 0.3162



67/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.3933 - sparse_categorical_accuracy: 0.3162



68/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.3944 - sparse_categorical_accuracy: 0.3161



69/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.3953 - sparse_categorical_accuracy: 0.3161



70/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.3962 - sparse_categorical_accuracy: 0.3160



71/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.3971 - sparse_categorical_accuracy: 0.3160



72/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.3978 - sparse_categorical_accuracy: 0.3159



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.3986 - sparse_categorical_accuracy: 0.3159



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.3994 - sparse_categorical_accuracy: 0.3158



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.4003 - sparse_categorical_accuracy: 0.3157



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.4011 - sparse_categorical_accuracy: 0.3157



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.4019 - sparse_categorical_accuracy: 0.3156



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.4026 - sparse_categorical_accuracy: 0.3156



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.4032 - sparse_categorical_accuracy: 0.3155



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.4038 - sparse_categorical_accuracy: 0.3155



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.4045 - sparse_categorical_accuracy: 0.3155



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.4051 - sparse_categorical_accuracy: 0.3154



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.4058 - sparse_categorical_accuracy: 0.3154



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.4066 - sparse_categorical_accuracy: 0.3154



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.4072 - sparse_categorical_accuracy: 0.3154



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.4079 - sparse_categorical_accuracy: 0.3154



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.4085 - sparse_categorical_accuracy: 0.3154



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.4091 - sparse_categorical_accuracy: 0.3154



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.4097 - sparse_categorical_accuracy: 0.3154



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.4104 - sparse_categorical_accuracy: 0.3154



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.4110 - sparse_categorical_accuracy: 0.3154 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.4117 - sparse_categorical_accuracy: 0.3153



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.4123 - sparse_categorical_accuracy: 0.3153



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.4129 - sparse_categorical_accuracy: 0.3152



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.4135 - sparse_categorical_accuracy: 0.3152



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.4142 - sparse_categorical_accuracy: 0.3152



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.4150 - sparse_categorical_accuracy: 0.3151



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.4157 - sparse_categorical_accuracy: 0.3151



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.4164 - sparse_categorical_accuracy: 0.3151



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.4156 - sparse_categorical_accuracy: 0.3150



100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 36.4148 - sparse_categorical_accuracy: 0.3150 - val_loss: 14661139300352.0000 - val_sparse_categorical_accuracy: 0.2240

Epoch 4/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.7380 - sparse_categorical_accuracy: 0.5312



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.7969 - sparse_categorical_accuracy: 0.4844



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.7860 - sparse_categorical_accuracy: 0.4653



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.7852 - sparse_categorical_accuracy: 0.4447



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.7560 - sparse_categorical_accuracy: 0.4370



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.7412 - sparse_categorical_accuracy: 0.4293



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.7300 - sparse_categorical_accuracy: 0.4221



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.7233 - sparse_categorical_accuracy: 0.4148



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.7190 - sparse_categorical_accuracy: 0.4073



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.7201 - sparse_categorical_accuracy: 0.3990



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7176 - sparse_categorical_accuracy: 0.3925



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.7097 - sparse_categorical_accuracy: 0.3882



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.7017 - sparse_categorical_accuracy: 0.3850



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.6936 - sparse_categorical_accuracy: 0.3819



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.6858 - sparse_categorical_accuracy: 0.3786



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.6785 - sparse_categorical_accuracy: 0.3752



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.6711 - sparse_categorical_accuracy: 0.3723



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.6637 - sparse_categorical_accuracy: 0.3695



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.6692 - sparse_categorical_accuracy: 0.3668



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.6728 - sparse_categorical_accuracy: 0.3647



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.6748 - sparse_categorical_accuracy: 0.3631



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.6766 - sparse_categorical_accuracy: 0.3616



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.6783 - sparse_categorical_accuracy: 0.3601



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.6799 - sparse_categorical_accuracy: 0.3588



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.6818 - sparse_categorical_accuracy: 0.3576



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.6836 - sparse_categorical_accuracy: 0.3565



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.6852 - sparse_categorical_accuracy: 0.3555



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.6879 - sparse_categorical_accuracy: 0.3545



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.6908 - sparse_categorical_accuracy: 0.3535



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.6939 - sparse_categorical_accuracy: 0.3525



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.6971 - sparse_categorical_accuracy: 0.3515



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.7002 - sparse_categorical_accuracy: 0.3506



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.7032 - sparse_categorical_accuracy: 0.3498



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.7059 - sparse_categorical_accuracy: 0.3492



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.7085 - sparse_categorical_accuracy: 0.3487



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.7110 - sparse_categorical_accuracy: 0.3481



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.7138 - sparse_categorical_accuracy: 0.3476



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.7167 - sparse_categorical_accuracy: 0.3472



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.7196 - sparse_categorical_accuracy: 0.3468



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.7225 - sparse_categorical_accuracy: 0.3463



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.7254 - sparse_categorical_accuracy: 0.3459



42/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.7283 - sparse_categorical_accuracy: 0.3455



43/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.7311 - sparse_categorical_accuracy: 0.3450 



44/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.7339 - sparse_categorical_accuracy: 0.3446



45/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.7364 - sparse_categorical_accuracy: 0.3441



46/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.7387 - sparse_categorical_accuracy: 0.3437



47/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.7410 - sparse_categorical_accuracy: 0.3432



48/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.7433 - sparse_categorical_accuracy: 0.3428



49/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.7454 - sparse_categorical_accuracy: 0.3424



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.7475 - sparse_categorical_accuracy: 0.3420



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.7496 - sparse_categorical_accuracy: 0.3416



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.7515 - sparse_categorical_accuracy: 0.3413



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.7532 - sparse_categorical_accuracy: 0.3410



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.7547 - sparse_categorical_accuracy: 0.3407



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.7561 - sparse_categorical_accuracy: 0.3404



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.7575 - sparse_categorical_accuracy: 0.3401



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.7590 - sparse_categorical_accuracy: 0.3398



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.7603 - sparse_categorical_accuracy: 0.3396



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.7617 - sparse_categorical_accuracy: 0.3393



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.7629 - sparse_categorical_accuracy: 0.3390



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.7641 - sparse_categorical_accuracy: 0.3387



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.7653 - sparse_categorical_accuracy: 0.3383



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.7665 - sparse_categorical_accuracy: 0.3380



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.7676 - sparse_categorical_accuracy: 0.3376



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.7687 - sparse_categorical_accuracy: 0.3373



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.7696 - sparse_categorical_accuracy: 0.3369



67/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.7705 - sparse_categorical_accuracy: 0.3366



68/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.7713 - sparse_categorical_accuracy: 0.3363



69/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.7720 - sparse_categorical_accuracy: 0.3360



70/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.7725 - sparse_categorical_accuracy: 0.3357



71/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.7730 - sparse_categorical_accuracy: 0.3354



72/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.7734 - sparse_categorical_accuracy: 0.3352



73/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.7736 - sparse_categorical_accuracy: 0.3350



74/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.7739 - sparse_categorical_accuracy: 0.3348



75/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.7742 - sparse_categorical_accuracy: 0.3345



76/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.7744 - sparse_categorical_accuracy: 0.3343



77/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.7746 - sparse_categorical_accuracy: 0.3340



78/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.7747 - sparse_categorical_accuracy: 0.3338



79/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.7747 - sparse_categorical_accuracy: 0.3335



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.7747 - sparse_categorical_accuracy: 0.3333



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.7746 - sparse_categorical_accuracy: 0.3330



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.7745 - sparse_categorical_accuracy: 0.3328



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.7743 - sparse_categorical_accuracy: 0.3325



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.7741 - sparse_categorical_accuracy: 0.3322



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.7739 - sparse_categorical_accuracy: 0.3320



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.7737 - sparse_categorical_accuracy: 0.3317



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.7735 - sparse_categorical_accuracy: 0.3315



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.7732 - sparse_categorical_accuracy: 0.3312



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.7729 - sparse_categorical_accuracy: 0.3310



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.7727 - sparse_categorical_accuracy: 0.3307



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.7724 - sparse_categorical_accuracy: 0.3305 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.7721 - sparse_categorical_accuracy: 0.3303



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.7718 - sparse_categorical_accuracy: 0.3300



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.7714 - sparse_categorical_accuracy: 0.3298



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.7711 - sparse_categorical_accuracy: 0.3296



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.7707 - sparse_categorical_accuracy: 0.3294



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.7704 - sparse_categorical_accuracy: 0.3293



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.7701 - sparse_categorical_accuracy: 0.3291



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.7697 - sparse_categorical_accuracy: 0.3289



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.7677 - sparse_categorical_accuracy: 0.3288



100/100 ━━━━━━━━━━━━━━━━━━━━ 110s 1s/step - loss: 36.7658 - sparse_categorical_accuracy: 0.3286 - val_loss: 2640681721921536.0000 - val_sparse_categorical_accuracy: 0.3542

Epoch 5/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 36.6004 - sparse_categorical_accuracy: 0.2188



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.5184 - sparse_categorical_accuracy: 0.2734



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 36.4827 - sparse_categorical_accuracy: 0.2969



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.4396 - sparse_categorical_accuracy: 0.3086



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.4243 - sparse_categorical_accuracy: 0.3131



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.4060 - sparse_categorical_accuracy: 0.3165



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.4471 - sparse_categorical_accuracy: 0.3178



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.4807 - sparse_categorical_accuracy: 0.3177



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.5028 - sparse_categorical_accuracy: 0.3163



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.5155 - sparse_categorical_accuracy: 0.3162



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.5232 - sparse_categorical_accuracy: 0.3151



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.5263 - sparse_categorical_accuracy: 0.3147



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.5277 - sparse_categorical_accuracy: 0.3145



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.5289 - sparse_categorical_accuracy: 0.3139



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.5328 - sparse_categorical_accuracy: 0.3130



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.5365 - sparse_categorical_accuracy: 0.3120



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.5411 - sparse_categorical_accuracy: 0.3116



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.5457 - sparse_categorical_accuracy: 0.3119



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.5504 - sparse_categorical_accuracy: 0.3127



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.5570 - sparse_categorical_accuracy: 0.3130



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.5644 - sparse_categorical_accuracy: 0.3134



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.5724 - sparse_categorical_accuracy: 0.3134



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.5828 - sparse_categorical_accuracy: 0.3136



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.6011 - sparse_categorical_accuracy: 0.3138



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.6181 - sparse_categorical_accuracy: 0.3137



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.6334 - sparse_categorical_accuracy: 0.3140



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.6477 - sparse_categorical_accuracy: 0.3142



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.6605 - sparse_categorical_accuracy: 0.3147



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.6723 - sparse_categorical_accuracy: 0.3149



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.6831 - sparse_categorical_accuracy: 0.3153



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.6929 - sparse_categorical_accuracy: 0.3157



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.7023 - sparse_categorical_accuracy: 0.3160



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.7110 - sparse_categorical_accuracy: 0.3161



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.7188 - sparse_categorical_accuracy: 0.3161



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.7264 - sparse_categorical_accuracy: 0.3161



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.7333 - sparse_categorical_accuracy: 0.3160



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.7404 - sparse_categorical_accuracy: 0.3160



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.7483 - sparse_categorical_accuracy: 0.3158



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.7558 - sparse_categorical_accuracy: 0.3156



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.7629 - sparse_categorical_accuracy: 0.3155



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.7698 - sparse_categorical_accuracy: 0.3153



42/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.7760 - sparse_categorical_accuracy: 0.3151



43/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.7818 - sparse_categorical_accuracy: 0.3150



44/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.7870 - sparse_categorical_accuracy: 0.3149



45/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.7922 - sparse_categorical_accuracy: 0.3147 



46/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.7971 - sparse_categorical_accuracy: 0.3145



47/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.8016 - sparse_categorical_accuracy: 0.3144



48/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.8057 - sparse_categorical_accuracy: 0.3143



49/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.8098 - sparse_categorical_accuracy: 0.3142



50/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.8136 - sparse_categorical_accuracy: 0.3141



51/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.8172 - sparse_categorical_accuracy: 0.3141



52/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.8203 - sparse_categorical_accuracy: 0.3141



53/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.8234 - sparse_categorical_accuracy: 0.3141



54/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.8262 - sparse_categorical_accuracy: 0.3141



55/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.8288 - sparse_categorical_accuracy: 0.3140



56/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.8313 - sparse_categorical_accuracy: 0.3140



57/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.8338 - sparse_categorical_accuracy: 0.3139



58/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.8362 - sparse_categorical_accuracy: 0.3139



59/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.8383 - sparse_categorical_accuracy: 0.3139



60/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.8402 - sparse_categorical_accuracy: 0.3138



61/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.8420 - sparse_categorical_accuracy: 0.3137



62/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.8436 - sparse_categorical_accuracy: 0.3137



63/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.8450 - sparse_categorical_accuracy: 0.3136



64/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.8501 - sparse_categorical_accuracy: 0.3135



65/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.8548 - sparse_categorical_accuracy: 0.3134



66/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.8594 - sparse_categorical_accuracy: 0.3133



67/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.8637 - sparse_categorical_accuracy: 0.3132



68/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.8679 - sparse_categorical_accuracy: 0.3132



69/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.8722 - sparse_categorical_accuracy: 0.3131



70/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.8765 - sparse_categorical_accuracy: 0.3130



71/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.8808 - sparse_categorical_accuracy: 0.3129



72/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.8851 - sparse_categorical_accuracy: 0.3128



73/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.8893 - sparse_categorical_accuracy: 0.3127



74/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.8934 - sparse_categorical_accuracy: 0.3126



75/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.8974 - sparse_categorical_accuracy: 0.3125



76/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.9016 - sparse_categorical_accuracy: 0.3124



77/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.9056 - sparse_categorical_accuracy: 0.3123



78/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.9097 - sparse_categorical_accuracy: 0.3122



79/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.9137 - sparse_categorical_accuracy: 0.3121



80/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.9180 - sparse_categorical_accuracy: 0.3120



81/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.9223 - sparse_categorical_accuracy: 0.3119



82/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.9265 - sparse_categorical_accuracy: 0.3118



83/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.9306 - sparse_categorical_accuracy: 0.3117



84/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.9348 - sparse_categorical_accuracy: 0.3116



85/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.9389 - sparse_categorical_accuracy: 0.3115



86/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.9430 - sparse_categorical_accuracy: 0.3114



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.9471 - sparse_categorical_accuracy: 0.3113



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.9511 - sparse_categorical_accuracy: 0.3112



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.9550 - sparse_categorical_accuracy: 0.3112



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.9589 - sparse_categorical_accuracy: 0.3111



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.9626 - sparse_categorical_accuracy: 0.3110 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.9663 - sparse_categorical_accuracy: 0.3109



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.9700 - sparse_categorical_accuracy: 0.3108



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.9734 - sparse_categorical_accuracy: 0.3107



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.9768 - sparse_categorical_accuracy: 0.3106



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.9801 - sparse_categorical_accuracy: 0.3105



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.9834 - sparse_categorical_accuracy: 0.3104



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.9866 - sparse_categorical_accuracy: 0.3103



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.9898 - sparse_categorical_accuracy: 0.3102



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.9913 - sparse_categorical_accuracy: 0.3101



100/100 ━━━━━━━━━━━━━━━━━━━━ 112s 1s/step - loss: 36.9928 - sparse_categorical_accuracy: 0.3100 - val_loss: 2087371157504536015273984.0000 - val_sparse_categorical_accuracy: 0.3004

Epoch 6/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 37.1168 - sparse_categorical_accuracy: 0.1875



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:48 1s/step - loss: 37.1688 - sparse_categorical_accuracy: 0.1719



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:46 1s/step - loss: 37.1452 - sparse_categorical_accuracy: 0.1944



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 37.0992 - sparse_categorical_accuracy: 0.2220



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 37.0764 - sparse_categorical_accuracy: 0.2376



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 37.0523 - sparse_categorical_accuracy: 0.2492



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 37.0250 - sparse_categorical_accuracy: 0.2602



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.9997 - sparse_categorical_accuracy: 0.2692



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.9775 - sparse_categorical_accuracy: 0.2755



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.9576 - sparse_categorical_accuracy: 0.2805



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.9399 - sparse_categorical_accuracy: 0.2849



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.9274 - sparse_categorical_accuracy: 0.2881



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.9169 - sparse_categorical_accuracy: 0.2911



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.9084 - sparse_categorical_accuracy: 0.2931



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.8988 - sparse_categorical_accuracy: 0.2952



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.8877 - sparse_categorical_accuracy: 0.2976



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.8768 - sparse_categorical_accuracy: 0.3001



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.8669 - sparse_categorical_accuracy: 0.3020



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.8565 - sparse_categorical_accuracy: 0.3036



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.8455 - sparse_categorical_accuracy: 0.3054



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.8350 - sparse_categorical_accuracy: 0.3068



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.8242 - sparse_categorical_accuracy: 0.3080



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.8151 - sparse_categorical_accuracy: 0.3088



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.8065 - sparse_categorical_accuracy: 0.3096



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.7989 - sparse_categorical_accuracy: 0.3102



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.7921 - sparse_categorical_accuracy: 0.3105



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.7860 - sparse_categorical_accuracy: 0.3107



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.7804 - sparse_categorical_accuracy: 0.3107



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.7753 - sparse_categorical_accuracy: 0.3109



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.7707 - sparse_categorical_accuracy: 0.3113



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.7666 - sparse_categorical_accuracy: 0.3118



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.7625 - sparse_categorical_accuracy: 0.3123



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.7581 - sparse_categorical_accuracy: 0.3129



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.7541 - sparse_categorical_accuracy: 0.3132



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.7502 - sparse_categorical_accuracy: 0.3134



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.7466 - sparse_categorical_accuracy: 0.3136



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.7429 - sparse_categorical_accuracy: 0.3138



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.7391 - sparse_categorical_accuracy: 0.3140



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.7354 - sparse_categorical_accuracy: 0.3141



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.7317 - sparse_categorical_accuracy: 0.3141



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.7280 - sparse_categorical_accuracy: 0.3141



42/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.7242 - sparse_categorical_accuracy: 0.3142



43/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.7205 - sparse_categorical_accuracy: 0.3142



44/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.7167 - sparse_categorical_accuracy: 0.3143 



45/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.7129 - sparse_categorical_accuracy: 0.3144



46/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.7114 - sparse_categorical_accuracy: 0.3145



47/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.7097 - sparse_categorical_accuracy: 0.3146



48/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.7081 - sparse_categorical_accuracy: 0.3147



49/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.7067 - sparse_categorical_accuracy: 0.3148



50/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.7053 - sparse_categorical_accuracy: 0.3149



51/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.7043 - sparse_categorical_accuracy: 0.3150



52/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.7035 - sparse_categorical_accuracy: 0.3151



53/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.7027 - sparse_categorical_accuracy: 0.3152



54/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.7020 - sparse_categorical_accuracy: 0.3153



55/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.7013 - sparse_categorical_accuracy: 0.3153



56/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.7005 - sparse_categorical_accuracy: 0.3154



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.6997 - sparse_categorical_accuracy: 0.3155



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.6991 - sparse_categorical_accuracy: 0.3155



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.6983 - sparse_categorical_accuracy: 0.3156



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.6977 - sparse_categorical_accuracy: 0.3156



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.6974 - sparse_categorical_accuracy: 0.3156



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.6971 - sparse_categorical_accuracy: 0.3156



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.6968 - sparse_categorical_accuracy: 0.3156



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.6963 - sparse_categorical_accuracy: 0.3157



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.6959 - sparse_categorical_accuracy: 0.3157



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.6954 - sparse_categorical_accuracy: 0.3158



67/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.6949 - sparse_categorical_accuracy: 0.3159



68/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.6944 - sparse_categorical_accuracy: 0.3160



69/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.6939 - sparse_categorical_accuracy: 0.3161



70/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.6933 - sparse_categorical_accuracy: 0.3162



71/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.6927 - sparse_categorical_accuracy: 0.3163



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.6921 - sparse_categorical_accuracy: 0.3164



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.6914 - sparse_categorical_accuracy: 0.3165



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.6907 - sparse_categorical_accuracy: 0.3166



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.6901 - sparse_categorical_accuracy: 0.3166



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.6897 - sparse_categorical_accuracy: 0.3167



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.6892 - sparse_categorical_accuracy: 0.3167



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.6887 - sparse_categorical_accuracy: 0.3168



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.6882 - sparse_categorical_accuracy: 0.3169



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.6878 - sparse_categorical_accuracy: 0.3170



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.6872 - sparse_categorical_accuracy: 0.3171



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.6867 - sparse_categorical_accuracy: 0.3172



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.6862 - sparse_categorical_accuracy: 0.3173



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.6858 - sparse_categorical_accuracy: 0.3173



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.6853 - sparse_categorical_accuracy: 0.3174



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.6847 - sparse_categorical_accuracy: 0.3175



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.6842 - sparse_categorical_accuracy: 0.3175



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.6835 - sparse_categorical_accuracy: 0.3176



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.6829 - sparse_categorical_accuracy: 0.3176



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.6823 - sparse_categorical_accuracy: 0.3177



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.6817 - sparse_categorical_accuracy: 0.3177 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.6810 - sparse_categorical_accuracy: 0.3177



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.6804 - sparse_categorical_accuracy: 0.3177



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.6802 - sparse_categorical_accuracy: 0.3178



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.6800 - sparse_categorical_accuracy: 0.3178



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.6798 - sparse_categorical_accuracy: 0.3179



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.6797 - sparse_categorical_accuracy: 0.3179



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.6795 - sparse_categorical_accuracy: 0.3180



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.6792 - sparse_categorical_accuracy: 0.3180



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.6775 - sparse_categorical_accuracy: 0.3181



100/100 ━━━━━━━━━━━━━━━━━━━━ 108s 1s/step - loss: 36.6758 - sparse_categorical_accuracy: 0.3182 - val_loss: 598952362161209344.0000 - val_sparse_categorical_accuracy: 0.4180

Epoch 7/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:46 1s/step - loss: 36.5799 - sparse_categorical_accuracy: 0.2188



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:45 1s/step - loss: 39.4707 - sparse_categorical_accuracy: 0.2422



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 39.7202 - sparse_categorical_accuracy: 0.2622



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 39.6028 - sparse_categorical_accuracy: 0.2826



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 39.4266 - sparse_categorical_accuracy: 0.2923



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.2664 - sparse_categorical_accuracy: 0.3000



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 39.1370 - sparse_categorical_accuracy: 0.3050



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 39.0332 - sparse_categorical_accuracy: 0.3064



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 38.9412 - sparse_categorical_accuracy: 0.3090



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 38.8614 - sparse_categorical_accuracy: 0.3115



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 38.7961 - sparse_categorical_accuracy: 0.3127



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 38.7323 - sparse_categorical_accuracy: 0.3144



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 38.6772 - sparse_categorical_accuracy: 0.3161



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 38.6311 - sparse_categorical_accuracy: 0.3166



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 38.5887 - sparse_categorical_accuracy: 0.3172



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 38.5600 - sparse_categorical_accuracy: 0.3173



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 38.5358 - sparse_categorical_accuracy: 0.3172



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 38.5143 - sparse_categorical_accuracy: 0.3170



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 38.4937 - sparse_categorical_accuracy: 0.3166



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 38.4737 - sparse_categorical_accuracy: 0.3164



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.4543 - sparse_categorical_accuracy: 0.3164



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 38.4364 - sparse_categorical_accuracy: 0.3163



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 38.4201 - sparse_categorical_accuracy: 0.3161



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 38.4052 - sparse_categorical_accuracy: 0.3162



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 38.3898 - sparse_categorical_accuracy: 0.3165



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 38.3748 - sparse_categorical_accuracy: 0.3167



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 38.3601 - sparse_categorical_accuracy: 0.3167



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 38.3457 - sparse_categorical_accuracy: 0.3167



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 38.3315 - sparse_categorical_accuracy: 0.3168



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 38.3167 - sparse_categorical_accuracy: 0.3172



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 38.3021 - sparse_categorical_accuracy: 0.3175



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 38.2873 - sparse_categorical_accuracy: 0.3179



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 38.2722 - sparse_categorical_accuracy: 0.3184



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 38.2571 - sparse_categorical_accuracy: 0.3189



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 38.2425 - sparse_categorical_accuracy: 0.3193



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 38.2277 - sparse_categorical_accuracy: 0.3197



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 38.2132 - sparse_categorical_accuracy: 0.3199



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 38.1989 - sparse_categorical_accuracy: 0.3201



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 38.1846 - sparse_categorical_accuracy: 0.3204



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 38.1707 - sparse_categorical_accuracy: 0.3206



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 38.1595 - sparse_categorical_accuracy: 0.3209



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 38.1484 - sparse_categorical_accuracy: 0.3211 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 38.1373 - sparse_categorical_accuracy: 0.3213



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 38.1262 - sparse_categorical_accuracy: 0.3214



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 38.1152 - sparse_categorical_accuracy: 0.3215



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 38.1040 - sparse_categorical_accuracy: 0.3216



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 38.0932 - sparse_categorical_accuracy: 0.3216



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 38.0824 - sparse_categorical_accuracy: 0.3216



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 38.0716 - sparse_categorical_accuracy: 0.3216



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 38.0609 - sparse_categorical_accuracy: 0.3216



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 38.0535 - sparse_categorical_accuracy: 0.3216



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 38.0460 - sparse_categorical_accuracy: 0.3217



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 38.0384 - sparse_categorical_accuracy: 0.3217



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 38.0309 - sparse_categorical_accuracy: 0.3217



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 38.0235 - sparse_categorical_accuracy: 0.3218



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 38.0162 - sparse_categorical_accuracy: 0.3218



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 38.0092 - sparse_categorical_accuracy: 0.3217



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 38.0029 - sparse_categorical_accuracy: 0.3217



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 37.9967 - sparse_categorical_accuracy: 0.3216



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 37.9907 - sparse_categorical_accuracy: 0.3215



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 37.9848 - sparse_categorical_accuracy: 0.3215



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 37.9791 - sparse_categorical_accuracy: 0.3214



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 37.9734 - sparse_categorical_accuracy: 0.3214



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 37.9678 - sparse_categorical_accuracy: 0.3213



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 37.9623 - sparse_categorical_accuracy: 0.3212



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 37.9570 - sparse_categorical_accuracy: 0.3211



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 37.9519 - sparse_categorical_accuracy: 0.3211



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 37.9469 - sparse_categorical_accuracy: 0.3210



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 37.9424 - sparse_categorical_accuracy: 0.3209



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 37.9380 - sparse_categorical_accuracy: 0.3208



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 37.9341 - sparse_categorical_accuracy: 0.3208



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 37.9304 - sparse_categorical_accuracy: 0.3207



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 37.9269 - sparse_categorical_accuracy: 0.3206



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 37.9234 - sparse_categorical_accuracy: 0.3206



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 37.9199 - sparse_categorical_accuracy: 0.3205



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 37.9165 - sparse_categorical_accuracy: 0.3204



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 37.9135 - sparse_categorical_accuracy: 0.3203



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 37.9104 - sparse_categorical_accuracy: 0.3202



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 37.9071 - sparse_categorical_accuracy: 0.3202



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 37.9039 - sparse_categorical_accuracy: 0.3201



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 37.9007 - sparse_categorical_accuracy: 0.3201



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 37.8974 - sparse_categorical_accuracy: 0.3200



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 37.8941 - sparse_categorical_accuracy: 0.3200



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 37.8908 - sparse_categorical_accuracy: 0.3200



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 37.8875 - sparse_categorical_accuracy: 0.3199



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 37.8840 - sparse_categorical_accuracy: 0.3199



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 37.8806 - sparse_categorical_accuracy: 0.3199



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 37.8770 - sparse_categorical_accuracy: 0.3198



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 37.8734 - sparse_categorical_accuracy: 0.3198



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 37.8697 - sparse_categorical_accuracy: 0.3197



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 37.8660 - sparse_categorical_accuracy: 0.3197 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 37.8622 - sparse_categorical_accuracy: 0.3196



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 37.8583 - sparse_categorical_accuracy: 0.3195



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 37.8545 - sparse_categorical_accuracy: 0.3195



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 37.8505 - sparse_categorical_accuracy: 0.3194



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 37.8465 - sparse_categorical_accuracy: 0.3194



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 37.8424 - sparse_categorical_accuracy: 0.3193



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 37.8384 - sparse_categorical_accuracy: 0.3193



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 37.8342 - sparse_categorical_accuracy: 0.3192



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 37.8286 - sparse_categorical_accuracy: 0.3192



100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 37.8231 - sparse_categorical_accuracy: 0.3192 - val_loss: 1330149064704.0000 - val_sparse_categorical_accuracy: 0.3367

Epoch 8/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.6512 - sparse_categorical_accuracy: 0.2500



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 36.6798 - sparse_categorical_accuracy: 0.2734



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.6432 - sparse_categorical_accuracy: 0.2899



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.5739 - sparse_categorical_accuracy: 0.3132



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.5407 - sparse_categorical_accuracy: 0.3268



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.5485 - sparse_categorical_accuracy: 0.3331



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.5576 - sparse_categorical_accuracy: 0.3371



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.5698 - sparse_categorical_accuracy: 0.3385



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.5745 - sparse_categorical_accuracy: 0.3394



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.5792 - sparse_categorical_accuracy: 0.3389



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.5810 - sparse_categorical_accuracy: 0.3376



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.5798 - sparse_categorical_accuracy: 0.3361



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.5791 - sparse_categorical_accuracy: 0.3352



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.5762 - sparse_categorical_accuracy: 0.3354



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.5728 - sparse_categorical_accuracy: 0.3355



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.5684 - sparse_categorical_accuracy: 0.3359



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.5666 - sparse_categorical_accuracy: 0.3356



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.5648 - sparse_categorical_accuracy: 0.3348



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.5629 - sparse_categorical_accuracy: 0.3337



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.5608 - sparse_categorical_accuracy: 0.3327



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.5580 - sparse_categorical_accuracy: 0.3321



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.5553 - sparse_categorical_accuracy: 0.3314



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.5536 - sparse_categorical_accuracy: 0.3305



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.5524 - sparse_categorical_accuracy: 0.3294



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.5546 - sparse_categorical_accuracy: 0.3286



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.5562 - sparse_categorical_accuracy: 0.3276



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.5576 - sparse_categorical_accuracy: 0.3267



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.5586 - sparse_categorical_accuracy: 0.3258



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.5592 - sparse_categorical_accuracy: 0.3251



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.5596 - sparse_categorical_accuracy: 0.3245



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.5592 - sparse_categorical_accuracy: 0.3241



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.5586 - sparse_categorical_accuracy: 0.3238



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.5576 - sparse_categorical_accuracy: 0.3236



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 36.5560 - sparse_categorical_accuracy: 0.3234



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.5542 - sparse_categorical_accuracy: 0.3233



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.5522 - sparse_categorical_accuracy: 0.3231



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.5500 - sparse_categorical_accuracy: 0.3231



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.5481 - sparse_categorical_accuracy: 0.3230



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.5463 - sparse_categorical_accuracy: 0.3228



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.5443 - sparse_categorical_accuracy: 0.3227



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.5423 - sparse_categorical_accuracy: 0.3225



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.5402 - sparse_categorical_accuracy: 0.3223 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.5381 - sparse_categorical_accuracy: 0.3220



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.5362 - sparse_categorical_accuracy: 0.3218



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.5354 - sparse_categorical_accuracy: 0.3215



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.5343 - sparse_categorical_accuracy: 0.3212



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.5330 - sparse_categorical_accuracy: 0.3209



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.5316 - sparse_categorical_accuracy: 0.3207



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.5302 - sparse_categorical_accuracy: 0.3205



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.5287 - sparse_categorical_accuracy: 0.3204



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.5272 - sparse_categorical_accuracy: 0.3203



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.5257 - sparse_categorical_accuracy: 0.3202



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.5242 - sparse_categorical_accuracy: 0.3201



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.5229 - sparse_categorical_accuracy: 0.3200



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.5216 - sparse_categorical_accuracy: 0.3199



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.5203 - sparse_categorical_accuracy: 0.3197



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.5188 - sparse_categorical_accuracy: 0.3196



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.5173 - sparse_categorical_accuracy: 0.3195



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.5157 - sparse_categorical_accuracy: 0.3194



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.5140 - sparse_categorical_accuracy: 0.3193



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.5122 - sparse_categorical_accuracy: 0.3192



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.5105 - sparse_categorical_accuracy: 0.3192



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.5086 - sparse_categorical_accuracy: 0.3191



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.5067 - sparse_categorical_accuracy: 0.3191



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.5048 - sparse_categorical_accuracy: 0.3191



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.5030 - sparse_categorical_accuracy: 0.3191



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.5011 - sparse_categorical_accuracy: 0.3191



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.4993 - sparse_categorical_accuracy: 0.3191



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.4974 - sparse_categorical_accuracy: 0.3191



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.4955 - sparse_categorical_accuracy: 0.3192



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.4937 - sparse_categorical_accuracy: 0.3192



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.4919 - sparse_categorical_accuracy: 0.3193



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.4902 - sparse_categorical_accuracy: 0.3194



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.4886 - sparse_categorical_accuracy: 0.3194



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.4871 - sparse_categorical_accuracy: 0.3194



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.4858 - sparse_categorical_accuracy: 0.3194



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.4845 - sparse_categorical_accuracy: 0.3195



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.4834 - sparse_categorical_accuracy: 0.3195



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.4824 - sparse_categorical_accuracy: 0.3195



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.4813 - sparse_categorical_accuracy: 0.3195



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.4804 - sparse_categorical_accuracy: 0.3195



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.4794 - sparse_categorical_accuracy: 0.3195



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.4785 - sparse_categorical_accuracy: 0.3195



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.4776 - sparse_categorical_accuracy: 0.3195



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.4767 - sparse_categorical_accuracy: 0.3196



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.4759 - sparse_categorical_accuracy: 0.3196



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.4750 - sparse_categorical_accuracy: 0.3196



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.4742 - sparse_categorical_accuracy: 0.3196



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.4735 - sparse_categorical_accuracy: 0.3196



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.4727 - sparse_categorical_accuracy: 0.3197



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.4719 - sparse_categorical_accuracy: 0.3197 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.4711 - sparse_categorical_accuracy: 0.3197



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.4702 - sparse_categorical_accuracy: 0.3198



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.4693 - sparse_categorical_accuracy: 0.3198



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.4686 - sparse_categorical_accuracy: 0.3198



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.4678 - sparse_categorical_accuracy: 0.3198



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.4670 - sparse_categorical_accuracy: 0.3198



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.4663 - sparse_categorical_accuracy: 0.3198



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.4656 - sparse_categorical_accuracy: 0.3198



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.4633 - sparse_categorical_accuracy: 0.3198



100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 36.4611 - sparse_categorical_accuracy: 0.3198 - val_loss: 55461990629376.0000 - val_sparse_categorical_accuracy: 0.3805

Epoch 9/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:48 1s/step - loss: 36.1902 - sparse_categorical_accuracy: 0.4062



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.1628 - sparse_categorical_accuracy: 0.3594



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.1877 - sparse_categorical_accuracy: 0.3438



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 36.2174 - sparse_categorical_accuracy: 0.3320



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.2312 - sparse_categorical_accuracy: 0.3294



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.2290 - sparse_categorical_accuracy: 0.3309



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.2177 - sparse_categorical_accuracy: 0.3321



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.2049 - sparse_categorical_accuracy: 0.3331



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.2052 - sparse_categorical_accuracy: 0.3319



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.2082 - sparse_categorical_accuracy: 0.3309



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.2106 - sparse_categorical_accuracy: 0.3298



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.2138 - sparse_categorical_accuracy: 0.3292



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.2142 - sparse_categorical_accuracy: 0.3288



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.2186 - sparse_categorical_accuracy: 0.3282



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.2206 - sparse_categorical_accuracy: 0.3278



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.2294 - sparse_categorical_accuracy: 0.3283



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.2382 - sparse_categorical_accuracy: 0.3287



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.2450 - sparse_categorical_accuracy: 0.3294



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.2496 - sparse_categorical_accuracy: 0.3303



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.2549 - sparse_categorical_accuracy: 0.3309



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.2586 - sparse_categorical_accuracy: 0.3315



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.2609 - sparse_categorical_accuracy: 0.3324



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.2630 - sparse_categorical_accuracy: 0.3330



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.2647 - sparse_categorical_accuracy: 0.3333



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 36.2664 - sparse_categorical_accuracy: 0.3339



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.2682 - sparse_categorical_accuracy: 0.3343



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.2697 - sparse_categorical_accuracy: 0.3344



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.2714 - sparse_categorical_accuracy: 0.3345



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.2728 - sparse_categorical_accuracy: 0.3344



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 36.2743 - sparse_categorical_accuracy: 0.3343



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.2755 - sparse_categorical_accuracy: 0.3340



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.2773 - sparse_categorical_accuracy: 0.3338



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.2785 - sparse_categorical_accuracy: 0.3337



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.2792 - sparse_categorical_accuracy: 0.3336



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.2797 - sparse_categorical_accuracy: 0.3336



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.2802 - sparse_categorical_accuracy: 0.3336



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.2807 - sparse_categorical_accuracy: 0.3336



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.2810 - sparse_categorical_accuracy: 0.3336



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.2810 - sparse_categorical_accuracy: 0.3336



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.2809 - sparse_categorical_accuracy: 0.3336



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 36.2809 - sparse_categorical_accuracy: 0.3336



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.2820 - sparse_categorical_accuracy: 0.3336 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.2831 - sparse_categorical_accuracy: 0.3337



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.2839 - sparse_categorical_accuracy: 0.3337



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.2848 - sparse_categorical_accuracy: 0.3337



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.2857 - sparse_categorical_accuracy: 0.3336



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 36.2874 - sparse_categorical_accuracy: 0.3335



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.2893 - sparse_categorical_accuracy: 0.3335



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.2912 - sparse_categorical_accuracy: 0.3334



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.2930 - sparse_categorical_accuracy: 0.3333



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 36.2946 - sparse_categorical_accuracy: 0.3334



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.2961 - sparse_categorical_accuracy: 0.3334



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 36.2975 - sparse_categorical_accuracy: 0.3334



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.2989 - sparse_categorical_accuracy: 0.3334



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.3000 - sparse_categorical_accuracy: 0.3335



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.3012 - sparse_categorical_accuracy: 0.3336



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.3021 - sparse_categorical_accuracy: 0.3336



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.3031 - sparse_categorical_accuracy: 0.3336



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.3040 - sparse_categorical_accuracy: 0.3336



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 36.3048 - sparse_categorical_accuracy: 0.3336



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.3055 - sparse_categorical_accuracy: 0.3336



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.3060 - sparse_categorical_accuracy: 0.3336



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.3065 - sparse_categorical_accuracy: 0.3337



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.3070 - sparse_categorical_accuracy: 0.3337



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.3075 - sparse_categorical_accuracy: 0.3338



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.3080 - sparse_categorical_accuracy: 0.3338



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.3088 - sparse_categorical_accuracy: 0.3338



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.3095 - sparse_categorical_accuracy: 0.3339



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.3101 - sparse_categorical_accuracy: 0.3339



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.3108 - sparse_categorical_accuracy: 0.3340



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.3115 - sparse_categorical_accuracy: 0.3341



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.3121 - sparse_categorical_accuracy: 0.3342



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.3127 - sparse_categorical_accuracy: 0.3342



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.3133 - sparse_categorical_accuracy: 0.3343



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.3142 - sparse_categorical_accuracy: 0.3344



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.3150 - sparse_categorical_accuracy: 0.3345



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.3158 - sparse_categorical_accuracy: 0.3345



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.3166 - sparse_categorical_accuracy: 0.3346



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.3174 - sparse_categorical_accuracy: 0.3347



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.3180 - sparse_categorical_accuracy: 0.3348



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.3186 - sparse_categorical_accuracy: 0.3350



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.3191 - sparse_categorical_accuracy: 0.3352



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.3194 - sparse_categorical_accuracy: 0.3353



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.3198 - sparse_categorical_accuracy: 0.3355



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.3201 - sparse_categorical_accuracy: 0.3357



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.3204 - sparse_categorical_accuracy: 0.3358



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.3207 - sparse_categorical_accuracy: 0.3359



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.3210 - sparse_categorical_accuracy: 0.3360



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.3215 - sparse_categorical_accuracy: 0.3361



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.3218 - sparse_categorical_accuracy: 0.3362



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.3222 - sparse_categorical_accuracy: 0.3363 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.3225 - sparse_categorical_accuracy: 0.3364



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.3228 - sparse_categorical_accuracy: 0.3365



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.3230 - sparse_categorical_accuracy: 0.3365



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.3232 - sparse_categorical_accuracy: 0.3366



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.3234 - sparse_categorical_accuracy: 0.3367



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.3235 - sparse_categorical_accuracy: 0.3368



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.3236 - sparse_categorical_accuracy: 0.3368



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.3236 - sparse_categorical_accuracy: 0.3369



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.3222 - sparse_categorical_accuracy: 0.3370



100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 36.3207 - sparse_categorical_accuracy: 0.3371 - val_loss: 79361986265088.0000 - val_sparse_categorical_accuracy: 0.3680

Epoch 10/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 58:50 36s/step - loss: 36.7173 - sparse_categorical_accuracy: 0.4062



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 36.4852 - sparse_categorical_accuracy: 0.3906 



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.3769 - sparse_categorical_accuracy: 0.3819



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.3024 - sparse_categorical_accuracy: 0.3822



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 36.2685 - sparse_categorical_accuracy: 0.3845



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.2423 - sparse_categorical_accuracy: 0.3855



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.2239 - sparse_categorical_accuracy: 0.3840



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.2047 - sparse_categorical_accuracy: 0.3843



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 36.1833 - sparse_categorical_accuracy: 0.3837



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.1658 - sparse_categorical_accuracy: 0.3825



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.1490 - sparse_categorical_accuracy: 0.3816



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.1342 - sparse_categorical_accuracy: 0.3804



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.1258 - sparse_categorical_accuracy: 0.3792



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.1192 - sparse_categorical_accuracy: 0.3783



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.1131 - sparse_categorical_accuracy: 0.3771



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 36.1093 - sparse_categorical_accuracy: 0.3756



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 36.1054 - sparse_categorical_accuracy: 0.3740



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 36.1022 - sparse_categorical_accuracy: 0.3727



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 36.1001 - sparse_categorical_accuracy: 0.3713



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 36.0968 - sparse_categorical_accuracy: 0.3706



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 36.0938 - sparse_categorical_accuracy: 0.3700



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 36.0911 - sparse_categorical_accuracy: 0.3692



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 36.0882 - sparse_categorical_accuracy: 0.3684



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.0863 - sparse_categorical_accuracy: 0.3673



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 36.0843 - sparse_categorical_accuracy: 0.3664



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 36.0827 - sparse_categorical_accuracy: 0.3657



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 36.0816 - sparse_categorical_accuracy: 0.3648



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 36.0803 - sparse_categorical_accuracy: 0.3640



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 36.0787 - sparse_categorical_accuracy: 0.3633



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 36.0772 - sparse_categorical_accuracy: 0.3627



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 36.0758 - sparse_categorical_accuracy: 0.3622



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.0746 - sparse_categorical_accuracy: 0.3617



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 36.0738 - sparse_categorical_accuracy: 0.3611



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.0728 - sparse_categorical_accuracy: 0.3605



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 36.0722 - sparse_categorical_accuracy: 0.3600



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 36.0717 - sparse_categorical_accuracy: 0.3595



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 36.0716 - sparse_categorical_accuracy: 0.3590



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 36.0718 - sparse_categorical_accuracy: 0.3585



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 36.0723 - sparse_categorical_accuracy: 0.3580



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 36.0727 - sparse_categorical_accuracy: 0.3574



41/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.0730 - sparse_categorical_accuracy: 0.3568 



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 36.0735 - sparse_categorical_accuracy: 0.3562



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 36.0742 - sparse_categorical_accuracy: 0.3557



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 36.0748 - sparse_categorical_accuracy: 0.3552



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 36.0752 - sparse_categorical_accuracy: 0.3548



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 36.0757 - sparse_categorical_accuracy: 0.3544



47/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 36.0761 - sparse_categorical_accuracy: 0.3540



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.0769 - sparse_categorical_accuracy: 0.3536



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 36.0776 - sparse_categorical_accuracy: 0.3532



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 36.0782 - sparse_categorical_accuracy: 0.3529



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.0788 - sparse_categorical_accuracy: 0.3527



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 36.0793 - sparse_categorical_accuracy: 0.3525



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 36.0799 - sparse_categorical_accuracy: 0.3523



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.0804 - sparse_categorical_accuracy: 0.3521



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 36.0808 - sparse_categorical_accuracy: 0.3520



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 36.0812 - sparse_categorical_accuracy: 0.3519



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 36.0816 - sparse_categorical_accuracy: 0.3518



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 36.0819 - sparse_categorical_accuracy: 0.3517



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 36.0821 - sparse_categorical_accuracy: 0.3516



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 36.0823 - sparse_categorical_accuracy: 0.3515



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 36.0826 - sparse_categorical_accuracy: 0.3514



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 36.0829 - sparse_categorical_accuracy: 0.3513



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 36.0832 - sparse_categorical_accuracy: 0.3512



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 36.0835 - sparse_categorical_accuracy: 0.3511



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 36.0838 - sparse_categorical_accuracy: 0.3510



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 36.0841 - sparse_categorical_accuracy: 0.3508



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 36.0846 - sparse_categorical_accuracy: 0.3507



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 36.0851 - sparse_categorical_accuracy: 0.3505



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 36.0856 - sparse_categorical_accuracy: 0.3503



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 36.0861 - sparse_categorical_accuracy: 0.3501



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 36.0867 - sparse_categorical_accuracy: 0.3499



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 36.0872 - sparse_categorical_accuracy: 0.3497



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 36.0878 - sparse_categorical_accuracy: 0.3495



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 36.0883 - sparse_categorical_accuracy: 0.3494



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 36.0888 - sparse_categorical_accuracy: 0.3492



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 36.0894 - sparse_categorical_accuracy: 0.3490



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 36.0899 - sparse_categorical_accuracy: 0.3488



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 36.0903 - sparse_categorical_accuracy: 0.3487



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 36.0906 - sparse_categorical_accuracy: 0.3485



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 36.0911 - sparse_categorical_accuracy: 0.3484



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 36.0914 - sparse_categorical_accuracy: 0.3483



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 36.0917 - sparse_categorical_accuracy: 0.3482



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 36.0920 - sparse_categorical_accuracy: 0.3481



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 36.0922 - sparse_categorical_accuracy: 0.3480



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 36.0925 - sparse_categorical_accuracy: 0.3479



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 36.0928 - sparse_categorical_accuracy: 0.3478



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 36.0930 - sparse_categorical_accuracy: 0.3478



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 36.0932 - sparse_categorical_accuracy: 0.3477



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 36.0935 - sparse_categorical_accuracy: 0.3476



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 36.0937 - sparse_categorical_accuracy: 0.3476



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 36.0939 - sparse_categorical_accuracy: 0.3476 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 36.0941 - sparse_categorical_accuracy: 0.3475



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 36.0943 - sparse_categorical_accuracy: 0.3475



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 36.0944 - sparse_categorical_accuracy: 0.3475



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 36.0947 - sparse_categorical_accuracy: 0.3474



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 36.0950 - sparse_categorical_accuracy: 0.3474



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 36.0955 - sparse_categorical_accuracy: 0.3474



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 36.0961 - sparse_categorical_accuracy: 0.3474



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 36.0966 - sparse_categorical_accuracy: 0.3475



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 36.0956 - sparse_categorical_accuracy: 0.3475



100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 36.0947 - sparse_categorical_accuracy: 0.3475 - val_loss: 14927241216.0000 - val_sparse_categorical_accuracy: 0.3054

Epoch 11/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 58:42 36s/step - loss: 36.1768 - sparse_categorical_accuracy: 0.3438



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 36.3035 - sparse_categorical_accuracy: 0.3125 



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.3690 - sparse_categorical_accuracy: 0.3090



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 36.4012 - sparse_categorical_accuracy: 0.3138



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 36.4168 - sparse_categorical_accuracy: 0.3198



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 36.4449 - sparse_categorical_accuracy: 0.3247



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 36.4684 - sparse_categorical_accuracy: 0.3287



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 36.4986 - sparse_categorical_accuracy: 0.3305



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 36.5271 - sparse_categorical_accuracy: 0.3328



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 36.5636 - sparse_categorical_accuracy: 0.3336



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 36.6122 - sparse_categorical_accuracy: 0.3342



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 36.6884 - sparse_categorical_accuracy: 0.3348



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 36.7833 - sparse_categorical_accuracy: 0.3353



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 36.8994 - sparse_categorical_accuracy: 0.3350



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 37.0178 - sparse_categorical_accuracy: 0.3349



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 37.1292 - sparse_categorical_accuracy: 0.3337



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 37.2272 - sparse_categorical_accuracy: 0.3332



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 37.3126 - sparse_categorical_accuracy: 0.3323



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 37.3916 - sparse_categorical_accuracy: 0.3314



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 37.4582 - sparse_categorical_accuracy: 0.3308



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 37.5152 - sparse_categorical_accuracy: 0.3302



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 37.5639 - sparse_categorical_accuracy: 0.3298



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 37.6056 - sparse_categorical_accuracy: 0.3292



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 37.6425 - sparse_categorical_accuracy: 0.3286



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 37.6735 - sparse_categorical_accuracy: 0.3283



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 37.6993 - sparse_categorical_accuracy: 0.3281



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 37.7214 - sparse_categorical_accuracy: 0.3280



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 37.7406 - sparse_categorical_accuracy: 0.3277



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 37.7565 - sparse_categorical_accuracy: 0.3274



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 37.7714 - sparse_categorical_accuracy: 0.3272



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 37.7842 - sparse_categorical_accuracy: 0.3268



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 37.7953 - sparse_categorical_accuracy: 0.3264



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 37.8040 - sparse_categorical_accuracy: 0.3260



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 37.8219 - sparse_categorical_accuracy: 0.3258



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 37.8379 - sparse_categorical_accuracy: 0.3256



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 37.8525 - sparse_categorical_accuracy: 0.3254



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 37.8659 - sparse_categorical_accuracy: 0.3253



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 37.8796 - sparse_categorical_accuracy: 0.3250



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 37.8931 - sparse_categorical_accuracy: 0.3247



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 37.9096 - sparse_categorical_accuracy: 0.3244



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 37.9253 - sparse_categorical_accuracy: 0.3241



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 37.9405 - sparse_categorical_accuracy: 0.3238 



43/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 37.9553 - sparse_categorical_accuracy: 0.3236



44/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 37.9707 - sparse_categorical_accuracy: 0.3235



45/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 37.9869 - sparse_categorical_accuracy: 0.3232



46/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 38.0034 - sparse_categorical_accuracy: 0.3231



47/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 38.0206 - sparse_categorical_accuracy: 0.3229



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 38.0382 - sparse_categorical_accuracy: 0.3227



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 38.0558 - sparse_categorical_accuracy: 0.3226



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 38.0737 - sparse_categorical_accuracy: 0.3224



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 38.0920 - sparse_categorical_accuracy: 0.3222



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 38.1100 - sparse_categorical_accuracy: 0.3221



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 38.1299 - sparse_categorical_accuracy: 0.3220



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 38.1498 - sparse_categorical_accuracy: 0.3220



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 38.1689 - sparse_categorical_accuracy: 0.3219



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 38.1871 - sparse_categorical_accuracy: 0.3218



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 38.2045 - sparse_categorical_accuracy: 0.3217



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 38.2213 - sparse_categorical_accuracy: 0.3216



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 38.2376 - sparse_categorical_accuracy: 0.3215



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 38.2533 - sparse_categorical_accuracy: 0.3214



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 38.2683 - sparse_categorical_accuracy: 0.3213



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 38.2826 - sparse_categorical_accuracy: 0.3213



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 38.2961 - sparse_categorical_accuracy: 0.3212



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 38.3092 - sparse_categorical_accuracy: 0.3211



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 38.3217 - sparse_categorical_accuracy: 0.3210



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 38.3339 - sparse_categorical_accuracy: 0.3209



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 38.3452 - sparse_categorical_accuracy: 0.3208



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 38.3558 - sparse_categorical_accuracy: 0.3208



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 38.3657 - sparse_categorical_accuracy: 0.3207



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 38.3748 - sparse_categorical_accuracy: 0.3207



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 38.3835 - sparse_categorical_accuracy: 0.3206



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 38.3918 - sparse_categorical_accuracy: 0.3205



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 38.3994 - sparse_categorical_accuracy: 0.3204



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 38.4065 - sparse_categorical_accuracy: 0.3203



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 38.4139 - sparse_categorical_accuracy: 0.3202



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 38.4209 - sparse_categorical_accuracy: 0.3200



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 38.4286 - sparse_categorical_accuracy: 0.3199



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 38.4358 - sparse_categorical_accuracy: 0.3198



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 38.4423 - sparse_categorical_accuracy: 0.3197



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 38.4483 - sparse_categorical_accuracy: 0.3196



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 38.4539 - sparse_categorical_accuracy: 0.3196



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 38.4589 - sparse_categorical_accuracy: 0.3195



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 38.4636 - sparse_categorical_accuracy: 0.3195



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 38.4679 - sparse_categorical_accuracy: 0.3194



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 38.4719 - sparse_categorical_accuracy: 0.3194



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 38.4755 - sparse_categorical_accuracy: 0.3193



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 38.4788 - sparse_categorical_accuracy: 0.3193



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 38.4819 - sparse_categorical_accuracy: 0.3192



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 38.4846 - sparse_categorical_accuracy: 0.3191



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 38.4870 - sparse_categorical_accuracy: 0.3191



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 38.4891 - sparse_categorical_accuracy: 0.3190 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 38.4916 - sparse_categorical_accuracy: 0.3190



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 38.4937 - sparse_categorical_accuracy: 0.3189



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 38.4957 - sparse_categorical_accuracy: 0.3189



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 38.4974 - sparse_categorical_accuracy: 0.3188



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 38.4990 - sparse_categorical_accuracy: 0.3188



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 38.5005 - sparse_categorical_accuracy: 0.3188



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 38.5019 - sparse_categorical_accuracy: 0.3188



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 38.5032 - sparse_categorical_accuracy: 0.3187



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 38.5028 - sparse_categorical_accuracy: 0.3187



100/100 ━━━━━━━━━━━━━━━━━━━━ 141s 1s/step - loss: 38.5024 - sparse_categorical_accuracy: 0.3187 - val_loss: 1930753792.0000 - val_sparse_categorical_accuracy: 0.2315

Epoch 12/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:00:07 36s/step - loss: 42.1152 - sparse_categorical_accuracy: 0.3750



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 40.9939 - sparse_categorical_accuracy: 0.3359 



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 997ms/step - loss: 40.3854 - sparse_categorical_accuracy: 0.3212



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 40.0082 - sparse_categorical_accuracy: 0.3151 



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 39.7856 - sparse_categorical_accuracy: 0.3121



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1000ms/step - loss: 39.6142 - sparse_categorical_accuracy: 0.3078



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 39.4890 - sparse_categorical_accuracy: 0.3072 



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1000ms/step - loss: 39.3828 - sparse_categorical_accuracy: 0.3059



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 39.2872 - sparse_categorical_accuracy: 0.3032 



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 39.1979 - sparse_categorical_accuracy: 0.3025



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 39.1176 - sparse_categorical_accuracy: 0.3022



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 39.0417 - sparse_categorical_accuracy: 0.3026



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 38.9724 - sparse_categorical_accuracy: 0.3032



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 38.9077 - sparse_categorical_accuracy: 0.3041



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 38.8489 - sparse_categorical_accuracy: 0.3044



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 38.7940 - sparse_categorical_accuracy: 0.3044



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 38.7408 - sparse_categorical_accuracy: 0.3048



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.6905 - sparse_categorical_accuracy: 0.3049



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.6466 - sparse_categorical_accuracy: 0.3050



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 38.6091 - sparse_categorical_accuracy: 0.3051



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 38.5744 - sparse_categorical_accuracy: 0.3053



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 38.5416 - sparse_categorical_accuracy: 0.3052



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 38.5095 - sparse_categorical_accuracy: 0.3049



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 38.4786 - sparse_categorical_accuracy: 0.3046



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 38.4478 - sparse_categorical_accuracy: 0.3044



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 38.4185 - sparse_categorical_accuracy: 0.3044



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 38.3905 - sparse_categorical_accuracy: 0.3044



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 38.3624 - sparse_categorical_accuracy: 0.3047



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 38.3360 - sparse_categorical_accuracy: 0.3051



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 38.3099 - sparse_categorical_accuracy: 0.3056



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 38.2850 - sparse_categorical_accuracy: 0.3060



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 38.2604 - sparse_categorical_accuracy: 0.3064



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 38.2364 - sparse_categorical_accuracy: 0.3069



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 38.2127 - sparse_categorical_accuracy: 0.3075



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 38.1893 - sparse_categorical_accuracy: 0.3082



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 38.1665 - sparse_categorical_accuracy: 0.3089



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 38.1445 - sparse_categorical_accuracy: 0.3094



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 38.1229 - sparse_categorical_accuracy: 0.3100



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 38.1031 - sparse_categorical_accuracy: 0.3107



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 38.0841 - sparse_categorical_accuracy: 0.3113



41/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 38.0655 - sparse_categorical_accuracy: 0.3119 



42/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 38.0472 - sparse_categorical_accuracy: 0.3125



43/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 38.0293 - sparse_categorical_accuracy: 0.3130



44/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 38.0117 - sparse_categorical_accuracy: 0.3136



45/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 37.9946 - sparse_categorical_accuracy: 0.3140



46/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 37.9778 - sparse_categorical_accuracy: 0.3144



47/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 37.9615 - sparse_categorical_accuracy: 0.3149



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 37.9455 - sparse_categorical_accuracy: 0.3153



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 37.9298 - sparse_categorical_accuracy: 0.3156



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 37.9144 - sparse_categorical_accuracy: 0.3160



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 37.8994 - sparse_categorical_accuracy: 0.3163



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 37.8846 - sparse_categorical_accuracy: 0.3167



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 37.8702 - sparse_categorical_accuracy: 0.3171



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 37.8563 - sparse_categorical_accuracy: 0.3174



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 37.8424 - sparse_categorical_accuracy: 0.3178



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 37.8294 - sparse_categorical_accuracy: 0.3181



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 37.8166 - sparse_categorical_accuracy: 0.3184



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 37.8041 - sparse_categorical_accuracy: 0.3186



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 37.7917 - sparse_categorical_accuracy: 0.3189



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 37.7796 - sparse_categorical_accuracy: 0.3192



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 37.7678 - sparse_categorical_accuracy: 0.3194



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 37.7561 - sparse_categorical_accuracy: 0.3196



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 37.7444 - sparse_categorical_accuracy: 0.3198



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 37.7330 - sparse_categorical_accuracy: 0.3200



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 37.7218 - sparse_categorical_accuracy: 0.3202



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 37.7106 - sparse_categorical_accuracy: 0.3204



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 37.6996 - sparse_categorical_accuracy: 0.3205



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 37.6887 - sparse_categorical_accuracy: 0.3207



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 37.6780 - sparse_categorical_accuracy: 0.3209



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 37.6676 - sparse_categorical_accuracy: 0.3210



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 37.6572 - sparse_categorical_accuracy: 0.3212



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 37.6470 - sparse_categorical_accuracy: 0.3213



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 37.6370 - sparse_categorical_accuracy: 0.3215



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 37.6272 - sparse_categorical_accuracy: 0.3216



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 37.6175 - sparse_categorical_accuracy: 0.3218



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 37.6079 - sparse_categorical_accuracy: 0.3219



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 37.5986 - sparse_categorical_accuracy: 0.3221



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 37.5894 - sparse_categorical_accuracy: 0.3222



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 37.5804 - sparse_categorical_accuracy: 0.3223



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 37.5721 - sparse_categorical_accuracy: 0.3224



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 37.5639 - sparse_categorical_accuracy: 0.3226



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 37.5557 - sparse_categorical_accuracy: 0.3227



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 37.5477 - sparse_categorical_accuracy: 0.3229



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 37.5400 - sparse_categorical_accuracy: 0.3230



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 37.5324 - sparse_categorical_accuracy: 0.3232



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 37.5249 - sparse_categorical_accuracy: 0.3233



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 37.5174 - sparse_categorical_accuracy: 0.3235



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 37.5100 - sparse_categorical_accuracy: 0.3237



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 37.5027 - sparse_categorical_accuracy: 0.3238



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 37.4956 - sparse_categorical_accuracy: 0.3240



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 37.4886 - sparse_categorical_accuracy: 0.3241 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 37.4816 - sparse_categorical_accuracy: 0.3243



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 37.4747 - sparse_categorical_accuracy: 0.3244



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 37.4679 - sparse_categorical_accuracy: 0.3246



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 37.4613 - sparse_categorical_accuracy: 0.3247



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 37.4547 - sparse_categorical_accuracy: 0.3249



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 37.4482 - sparse_categorical_accuracy: 0.3250



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 37.4417 - sparse_categorical_accuracy: 0.3252



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 37.4353 - sparse_categorical_accuracy: 0.3253



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 37.4279 - sparse_categorical_accuracy: 0.3255



100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 37.4206 - sparse_categorical_accuracy: 0.3256 - val_loss: 1793616557963500563988480.0000 - val_sparse_categorical_accuracy: 0.2328

Epoch 13/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 59:52 36s/step - loss: 43.0665 - sparse_categorical_accuracy: 0.1875



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 41.4007 - sparse_categorical_accuracy: 0.2344 



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 40.5478 - sparse_categorical_accuracy: 0.2361



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.9836 - sparse_categorical_accuracy: 0.2513



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.6005 - sparse_categorical_accuracy: 0.2623



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 39.4050 - sparse_categorical_accuracy: 0.2663



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 39.2307 - sparse_categorical_accuracy: 0.2659



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 39.0731 - sparse_categorical_accuracy: 0.2688



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 38.9341 - sparse_categorical_accuracy: 0.2721



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 38.8113 - sparse_categorical_accuracy: 0.2768



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 38.7010 - sparse_categorical_accuracy: 0.2811



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 38.6074 - sparse_categorical_accuracy: 0.2837



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 38.5211 - sparse_categorical_accuracy: 0.2853



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 38.4446 - sparse_categorical_accuracy: 0.2863



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 38.3741 - sparse_categorical_accuracy: 0.2876



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 38.3085 - sparse_categorical_accuracy: 0.2893



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 38.2497 - sparse_categorical_accuracy: 0.2910



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 38.1954 - sparse_categorical_accuracy: 0.2925



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 38.1438 - sparse_categorical_accuracy: 0.2942



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 38.0973 - sparse_categorical_accuracy: 0.2962



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 38.0548 - sparse_categorical_accuracy: 0.2978



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 38.0137 - sparse_categorical_accuracy: 0.2996



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 37.9745 - sparse_categorical_accuracy: 0.3013



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 37.9374 - sparse_categorical_accuracy: 0.3029



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 37.9020 - sparse_categorical_accuracy: 0.3044



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 37.8688 - sparse_categorical_accuracy: 0.3058



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 37.8374 - sparse_categorical_accuracy: 0.3069



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 37.8071 - sparse_categorical_accuracy: 0.3081



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 37.7780 - sparse_categorical_accuracy: 0.3092



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 37.7549 - sparse_categorical_accuracy: 0.3103



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 37.7322 - sparse_categorical_accuracy: 0.3112



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 37.7103 - sparse_categorical_accuracy: 0.3122



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 37.6895 - sparse_categorical_accuracy: 0.3130



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 37.6693 - sparse_categorical_accuracy: 0.3139



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 37.6500 - sparse_categorical_accuracy: 0.3147



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 37.6313 - sparse_categorical_accuracy: 0.3155



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 37.6136 - sparse_categorical_accuracy: 0.3163



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 37.5964 - sparse_categorical_accuracy: 0.3170



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 37.5801 - sparse_categorical_accuracy: 0.3176



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 37.5643 - sparse_categorical_accuracy: 0.3182



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 37.5490 - sparse_categorical_accuracy: 0.3187



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 37.5343 - sparse_categorical_accuracy: 0.3192 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 37.5202 - sparse_categorical_accuracy: 0.3197



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 37.5065 - sparse_categorical_accuracy: 0.3202



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 37.4937 - sparse_categorical_accuracy: 0.3207



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 37.4820 - sparse_categorical_accuracy: 0.3210



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 37.4705 - sparse_categorical_accuracy: 0.3213



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 37.4600 - sparse_categorical_accuracy: 0.3216



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 37.4499 - sparse_categorical_accuracy: 0.3220



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 37.4459 - sparse_categorical_accuracy: 0.3223



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 37.4418 - sparse_categorical_accuracy: 0.3226



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 37.4394 - sparse_categorical_accuracy: 0.3229



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 37.4379 - sparse_categorical_accuracy: 0.3231



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 37.4367 - sparse_categorical_accuracy: 0.3233



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 37.4355 - sparse_categorical_accuracy: 0.3234



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 37.4344 - sparse_categorical_accuracy: 0.3236



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 37.4333 - sparse_categorical_accuracy: 0.3237



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 37.4332 - sparse_categorical_accuracy: 0.3239



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 37.4330 - sparse_categorical_accuracy: 0.3240



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 37.4355 - sparse_categorical_accuracy: 0.3242



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 37.4376 - sparse_categorical_accuracy: 0.3243



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 37.4397 - sparse_categorical_accuracy: 0.3244



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 37.4570 - sparse_categorical_accuracy: 0.3245



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 37.4780 - sparse_categorical_accuracy: 0.3246



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 37.4992 - sparse_categorical_accuracy: 0.3246



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 37.5211 - sparse_categorical_accuracy: 0.3247



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 37.5453 - sparse_categorical_accuracy: 0.3248



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 37.6848 - sparse_categorical_accuracy: 0.3249



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 37.8449 - sparse_categorical_accuracy: 0.3250



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 38.0000 - sparse_categorical_accuracy: 0.3250



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 38.1557 - sparse_categorical_accuracy: 0.3251



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 38.5126 - sparse_categorical_accuracy: 0.3250



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 39.0564 - sparse_categorical_accuracy: 0.3250



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 39.5901 - sparse_categorical_accuracy: 0.3249



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 40.1041 - sparse_categorical_accuracy: 0.3249



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 40.6028 - sparse_categorical_accuracy: 0.3248



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 41.1546 - sparse_categorical_accuracy: 0.3247



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 41.7197 - sparse_categorical_accuracy: 0.3246



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 42.2922 - sparse_categorical_accuracy: 0.3245



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 42.8838 - sparse_categorical_accuracy: 0.3244



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 43.4631 - sparse_categorical_accuracy: 0.3243



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 44.0304 - sparse_categorical_accuracy: 0.3242



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 44.8038 - sparse_categorical_accuracy: 0.3241



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 45.5640 - sparse_categorical_accuracy: 0.3240



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 46.2985 - sparse_categorical_accuracy: 0.3240



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 47.0196 - sparse_categorical_accuracy: 0.3239



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 47.7189 - sparse_categorical_accuracy: 0.3238



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 48.3950 - sparse_categorical_accuracy: 0.3237



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 49.0544 - sparse_categorical_accuracy: 0.3236



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 49.6933 - sparse_categorical_accuracy: 0.3235



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 50.3141 - sparse_categorical_accuracy: 0.3234 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 51.0231 - sparse_categorical_accuracy: 0.3234



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 51.7102 - sparse_categorical_accuracy: 0.3233



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 52.3764 - sparse_categorical_accuracy: 0.3232



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 53.0224 - sparse_categorical_accuracy: 0.3231



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 53.6491 - sparse_categorical_accuracy: 0.3230



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 54.2575 - sparse_categorical_accuracy: 0.3230



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 54.8483 - sparse_categorical_accuracy: 0.3229



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 55.4269 - sparse_categorical_accuracy: 0.3228



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 55.9873 - sparse_categorical_accuracy: 0.3227



100/100 ━━━━━━━━━━━━━━━━━━━━ 142s 1s/step - loss: 56.5366 - sparse_categorical_accuracy: 0.3226 - val_loss: 505209651200.0000 - val_sparse_categorical_accuracy: 0.2528

Epoch 14/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:46 1s/step - loss: 72.5004 - sparse_categorical_accuracy: 0.2812



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 992ms/step - loss: 84.3191 - sparse_categorical_accuracy: 0.2891



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 995ms/step - loss: 86.3062 - sparse_categorical_accuracy: 0.2865



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 102.5759 - sparse_categorical_accuracy: 0.2891 



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 111.2810 - sparse_categorical_accuracy: 0.2925



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 116.4263 - sparse_categorical_accuracy: 0.2950



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 120.4184 - sparse_categorical_accuracy: 0.2949



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 122.9799 - sparse_categorical_accuracy: 0.2976



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 123.9803 - sparse_categorical_accuracy: 0.2985



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 124.1441 - sparse_categorical_accuracy: 0.2996



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 123.8266 - sparse_categorical_accuracy: 0.2997



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 148.8502 - sparse_categorical_accuracy: 0.2999



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 167.8486 - sparse_categorical_accuracy: 0.3009



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 182.3929 - sparse_categorical_accuracy: 0.3014



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 193.6643 - sparse_categorical_accuracy: 0.3017



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 202.4236 - sparse_categorical_accuracy: 0.3023



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 209.2320 - sparse_categorical_accuracy: 0.3023



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 215.1761 - sparse_categorical_accuracy: 0.3022



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 219.8418 - sparse_categorical_accuracy: 0.3026



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 241.0950 - sparse_categorical_accuracy: 0.3032



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 262.8609 - sparse_categorical_accuracy: 0.3038



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 281.3412 - sparse_categorical_accuracy: 0.3045



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 297.2592 - sparse_categorical_accuracy: 0.3051



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 310.9528 - sparse_categorical_accuracy: 0.3058



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 322.7583 - sparse_categorical_accuracy: 0.3064



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 333.3093 - sparse_categorical_accuracy: 0.3068



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 346.8104 - sparse_categorical_accuracy: 0.3072



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 358.5458 - sparse_categorical_accuracy: 0.3073



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 368.7500 - sparse_categorical_accuracy: 0.3072



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 378.8999 - sparse_categorical_accuracy: 0.3072



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 388.4263 - sparse_categorical_accuracy: 0.3071



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 396.7980 - sparse_categorical_accuracy: 0.3070



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 404.4334 - sparse_categorical_accuracy: 0.3069



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 411.2321 - sparse_categorical_accuracy: 0.3070



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 417.2190 - sparse_categorical_accuracy: 0.3070



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 422.5132 - sparse_categorical_accuracy: 0.3070



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 427.1383 - sparse_categorical_accuracy: 0.3070



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 431.2506 - sparse_categorical_accuracy: 0.3070



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 434.8232 - sparse_categorical_accuracy: 0.3070



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 437.9098 - sparse_categorical_accuracy: 0.3068



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 440.6833 - sparse_categorical_accuracy: 0.3066



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 443.0559 - sparse_categorical_accuracy: 0.3064 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 445.1284 - sparse_categorical_accuracy: 0.3063



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 446.8688 - sparse_categorical_accuracy: 0.3062



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 448.4276 - sparse_categorical_accuracy: 0.3060



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 449.8117 - sparse_categorical_accuracy: 0.3059



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 450.9800 - sparse_categorical_accuracy: 0.3058



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 451.9573 - sparse_categorical_accuracy: 0.3058



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 452.7186 - sparse_categorical_accuracy: 0.3058



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 453.3130 - sparse_categorical_accuracy: 0.3058



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 453.7388 - sparse_categorical_accuracy: 0.3057



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 454.0486 - sparse_categorical_accuracy: 0.3056



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 454.2064 - sparse_categorical_accuracy: 0.3055



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 454.2328 - sparse_categorical_accuracy: 0.3053



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 454.1332 - sparse_categorical_accuracy: 0.3052



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 453.9173 - sparse_categorical_accuracy: 0.3050



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 453.5970 - sparse_categorical_accuracy: 0.3048



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 453.1803 - sparse_categorical_accuracy: 0.3046



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 452.6779 - sparse_categorical_accuracy: 0.3044



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 452.0964 - sparse_categorical_accuracy: 0.3042



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 451.4410 - sparse_categorical_accuracy: 0.3040



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 450.7515 - sparse_categorical_accuracy: 0.3038



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 449.9997 - sparse_categorical_accuracy: 0.3036



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 449.1942 - sparse_categorical_accuracy: 0.3034



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 448.3498 - sparse_categorical_accuracy: 0.3032



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 447.4845 - sparse_categorical_accuracy: 0.3030



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 446.5741 - sparse_categorical_accuracy: 0.3028



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 445.6242 - sparse_categorical_accuracy: 0.3026



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 444.6494 - sparse_categorical_accuracy: 0.3024



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 443.6421 - sparse_categorical_accuracy: 0.3022



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 442.6296 - sparse_categorical_accuracy: 0.3020



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 441.5871 - sparse_categorical_accuracy: 0.3019



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 440.5179 - sparse_categorical_accuracy: 0.3017



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 439.4271 - sparse_categorical_accuracy: 0.3016



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 438.3216 - sparse_categorical_accuracy: 0.3014



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 437.1978 - sparse_categorical_accuracy: 0.3013



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 436.0553 - sparse_categorical_accuracy: 0.3012



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 434.9005 - sparse_categorical_accuracy: 0.3011



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 433.7516 - sparse_categorical_accuracy: 0.3010



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 432.6144 - sparse_categorical_accuracy: 0.3010



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 431.4657 - sparse_categorical_accuracy: 0.3010



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 430.3048 - sparse_categorical_accuracy: 0.3009



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 429.1349 - sparse_categorical_accuracy: 0.3009



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 427.9555 - sparse_categorical_accuracy: 0.3009



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 426.7693 - sparse_categorical_accuracy: 0.3009



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 425.5820 - sparse_categorical_accuracy: 0.3009



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 424.3880 - sparse_categorical_accuracy: 0.3009



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 423.1917 - sparse_categorical_accuracy: 0.3009



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 421.9930 - sparse_categorical_accuracy: 0.3009



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 420.7901 - sparse_categorical_accuracy: 0.3008



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 419.5866 - sparse_categorical_accuracy: 0.3008 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 418.3845 - sparse_categorical_accuracy: 0.3008



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 417.1804 - sparse_categorical_accuracy: 0.3008



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 415.9749 - sparse_categorical_accuracy: 0.3008



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 414.7687 - sparse_categorical_accuracy: 0.3008



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 413.5732 - sparse_categorical_accuracy: 0.3007



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 412.3854 - sparse_categorical_accuracy: 0.3007



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 411.1977 - sparse_categorical_accuracy: 0.3007



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 410.0114 - sparse_categorical_accuracy: 0.3007



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 408.8264 - sparse_categorical_accuracy: 0.3007



100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 407.6649 - sparse_categorical_accuracy: 0.3007 - val_loss: 35970580884750336.0000 - val_sparse_categorical_accuracy: 0.3392

Epoch 15/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 67.1360 - sparse_categorical_accuracy: 0.1875



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 999ms/step - loss: 67.1150 - sparse_categorical_accuracy: 0.2500



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 72.1596 - sparse_categorical_accuracy: 0.2743 



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 73.8228 - sparse_categorical_accuracy: 0.2741



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 74.3511 - sparse_categorical_accuracy: 0.2730



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 75.8008 - sparse_categorical_accuracy: 0.2779



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 76.9862 - sparse_categorical_accuracy: 0.2841



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 77.6230 - sparse_categorical_accuracy: 0.2891



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 78.0145 - sparse_categorical_accuracy: 0.2932



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 78.4696 - sparse_categorical_accuracy: 0.2986



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 78.7647 - sparse_categorical_accuracy: 0.3035



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 78.8917 - sparse_categorical_accuracy: 0.3075



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 79.0025 - sparse_categorical_accuracy: 0.3108



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 79.0261 - sparse_categorical_accuracy: 0.3135



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 79.1682 - sparse_categorical_accuracy: 0.3158



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 79.2325 - sparse_categorical_accuracy: 0.3180



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 79.3086 - sparse_categorical_accuracy: 0.3197



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 79.3264 - sparse_categorical_accuracy: 0.3212



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 79.3429 - sparse_categorical_accuracy: 0.3225



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 79.3826 - sparse_categorical_accuracy: 0.3232



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 79.3818 - sparse_categorical_accuracy: 0.3240



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 79.3914 - sparse_categorical_accuracy: 0.3247



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 79.3727 - sparse_categorical_accuracy: 0.3256



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 79.3307 - sparse_categorical_accuracy: 0.3264



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 79.2707 - sparse_categorical_accuracy: 0.3271



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 79.1959 - sparse_categorical_accuracy: 0.3279



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 79.1077 - sparse_categorical_accuracy: 0.3288



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 79.0754 - sparse_categorical_accuracy: 0.3295



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 79.0420 - sparse_categorical_accuracy: 0.3301



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 78.9981 - sparse_categorical_accuracy: 0.3305



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 78.9976 - sparse_categorical_accuracy: 0.3310



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 78.9829 - sparse_categorical_accuracy: 0.3315



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 78.9716 - sparse_categorical_accuracy: 0.3319



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 78.9489 - sparse_categorical_accuracy: 0.3325



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 78.9179 - sparse_categorical_accuracy: 0.3330



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 78.8956 - sparse_categorical_accuracy: 0.3335



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 78.8663 - sparse_categorical_accuracy: 0.3339



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 78.8289 - sparse_categorical_accuracy: 0.3342



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 78.7841 - sparse_categorical_accuracy: 0.3344



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 78.7402 - sparse_categorical_accuracy: 0.3346



41/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 78.6895 - sparse_categorical_accuracy: 0.3348 



42/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 78.6423 - sparse_categorical_accuracy: 0.3351



43/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 78.6159 - sparse_categorical_accuracy: 0.3354



44/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 78.5880 - sparse_categorical_accuracy: 0.3356



45/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 78.5554 - sparse_categorical_accuracy: 0.3359



46/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 78.5176 - sparse_categorical_accuracy: 0.3362



47/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 78.5012 - sparse_categorical_accuracy: 0.3364



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 78.4792 - sparse_categorical_accuracy: 0.3367



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 78.4721 - sparse_categorical_accuracy: 0.3370



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 78.4589 - sparse_categorical_accuracy: 0.3373



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 78.4406 - sparse_categorical_accuracy: 0.3375



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 78.4466 - sparse_categorical_accuracy: 0.3378



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 78.4569 - sparse_categorical_accuracy: 0.3381



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 78.4790 - sparse_categorical_accuracy: 0.3384



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 78.4997 - sparse_categorical_accuracy: 0.3386



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 78.5142 - sparse_categorical_accuracy: 0.3388



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 78.5305 - sparse_categorical_accuracy: 0.3390



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 78.5410 - sparse_categorical_accuracy: 0.3391



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 78.5479 - sparse_categorical_accuracy: 0.3392



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 78.5502 - sparse_categorical_accuracy: 0.3392



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 78.5480 - sparse_categorical_accuracy: 0.3393



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 78.5418 - sparse_categorical_accuracy: 0.3392



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 78.5315 - sparse_categorical_accuracy: 0.3391



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 78.5173 - sparse_categorical_accuracy: 0.3390



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 78.5009 - sparse_categorical_accuracy: 0.3389



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 78.4822 - sparse_categorical_accuracy: 0.3389



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 78.4737 - sparse_categorical_accuracy: 0.3388



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 78.4618 - sparse_categorical_accuracy: 0.3388



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 78.4472 - sparse_categorical_accuracy: 0.3387



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 78.4297 - sparse_categorical_accuracy: 0.3387



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 78.4095 - sparse_categorical_accuracy: 0.3386



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 78.3903 - sparse_categorical_accuracy: 0.3386



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 78.3707 - sparse_categorical_accuracy: 0.3386



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 78.3488 - sparse_categorical_accuracy: 0.3385



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 78.3245 - sparse_categorical_accuracy: 0.3385



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 78.2985 - sparse_categorical_accuracy: 0.3384



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 78.2730 - sparse_categorical_accuracy: 0.3384



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 78.2458 - sparse_categorical_accuracy: 0.3384



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 78.2171 - sparse_categorical_accuracy: 0.3383



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 78.1887 - sparse_categorical_accuracy: 0.3382



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 78.1586 - sparse_categorical_accuracy: 0.3382



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 78.1290 - sparse_categorical_accuracy: 0.3382



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 78.0979 - sparse_categorical_accuracy: 0.3381



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 78.0656 - sparse_categorical_accuracy: 0.3381



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 78.0319 - sparse_categorical_accuracy: 0.3380



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 77.9983 - sparse_categorical_accuracy: 0.3380



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 77.9636 - sparse_categorical_accuracy: 0.3380



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 77.9280 - sparse_categorical_accuracy: 0.3380



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 77.8915 - sparse_categorical_accuracy: 0.3379



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 77.8541 - sparse_categorical_accuracy: 0.3379



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 77.8170 - sparse_categorical_accuracy: 0.3378 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 77.7791 - sparse_categorical_accuracy: 0.3378



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 77.7424 - sparse_categorical_accuracy: 0.3378



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 77.7098 - sparse_categorical_accuracy: 0.3377



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 77.6769 - sparse_categorical_accuracy: 0.3377



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 77.6433 - sparse_categorical_accuracy: 0.3377



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 77.6111 - sparse_categorical_accuracy: 0.3377



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 77.5781 - sparse_categorical_accuracy: 0.3377



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 77.5445 - sparse_categorical_accuracy: 0.3377



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 77.5074 - sparse_categorical_accuracy: 0.3377



100/100 ━━━━━━━━━━━━━━━━━━━━ 106s 1s/step - loss: 77.4712 - sparse_categorical_accuracy: 0.3377 - val_loss: 2983669504.0000 - val_sparse_categorical_accuracy: 0.2966

Epoch 16/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 992ms/step - loss: 59.8730 - sparse_categorical_accuracy: 0.2188



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 59.6142 - sparse_categorical_accuracy: 0.2734 



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:43 1s/step - loss: 59.5408 - sparse_categorical_accuracy: 0.2865



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 60.5291 - sparse_categorical_accuracy: 0.2930



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 60.9421 - sparse_categorical_accuracy: 0.3006



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 61.1234 - sparse_categorical_accuracy: 0.3052



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 61.9223 - sparse_categorical_accuracy: 0.3094



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 62.3840 - sparse_categorical_accuracy: 0.3137



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 62.6786 - sparse_categorical_accuracy: 0.3155



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 62.8811 - sparse_categorical_accuracy: 0.3171



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 63.0504 - sparse_categorical_accuracy: 0.3175



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 63.1466 - sparse_categorical_accuracy: 0.3179



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 63.1934 - sparse_categorical_accuracy: 0.3182



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 63.2089 - sparse_categorical_accuracy: 0.3186



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 63.2054 - sparse_categorical_accuracy: 0.3189



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 63.3949 - sparse_categorical_accuracy: 0.3190



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 63.6763 - sparse_categorical_accuracy: 0.3192



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 63.9220 - sparse_categorical_accuracy: 0.3192



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 64.1147 - sparse_categorical_accuracy: 0.3192



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 64.2688 - sparse_categorical_accuracy: 0.3191



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 64.3975 - sparse_categorical_accuracy: 0.3190



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 64.5064 - sparse_categorical_accuracy: 0.3191



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 64.5882 - sparse_categorical_accuracy: 0.3188



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 64.6458 - sparse_categorical_accuracy: 0.3186



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 64.6847 - sparse_categorical_accuracy: 0.3183



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 64.7102 - sparse_categorical_accuracy: 0.3180



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 64.7238 - sparse_categorical_accuracy: 0.3176



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 64.7253 - sparse_categorical_accuracy: 0.3172



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 64.7203 - sparse_categorical_accuracy: 0.3167



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 64.7130 - sparse_categorical_accuracy: 0.3163



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 64.8311 - sparse_categorical_accuracy: 0.3157



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 64.9315 - sparse_categorical_accuracy: 0.3152



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 65.0175 - sparse_categorical_accuracy: 0.3150



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 65.1062 - sparse_categorical_accuracy: 0.3148



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 65.2656 - sparse_categorical_accuracy: 0.3147



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 65.4292 - sparse_categorical_accuracy: 0.3146



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 65.5736 - sparse_categorical_accuracy: 0.3146



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 65.7009 - sparse_categorical_accuracy: 0.3146



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 65.8135 - sparse_categorical_accuracy: 0.3146



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 65.9128 - sparse_categorical_accuracy: 0.3145



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 66.0006 - sparse_categorical_accuracy: 0.3145



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 66.0767 - sparse_categorical_accuracy: 0.3144 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 66.1421 - sparse_categorical_accuracy: 0.3143



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 66.1978 - sparse_categorical_accuracy: 0.3143



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 66.2447 - sparse_categorical_accuracy: 0.3142



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 66.2840 - sparse_categorical_accuracy: 0.3142



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 66.3271 - sparse_categorical_accuracy: 0.3142



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 66.3801 - sparse_categorical_accuracy: 0.3143



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 66.4257 - sparse_categorical_accuracy: 0.3144



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 66.4652 - sparse_categorical_accuracy: 0.3144



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 66.4984 - sparse_categorical_accuracy: 0.3144



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 66.5277 - sparse_categorical_accuracy: 0.3144



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 66.5540 - sparse_categorical_accuracy: 0.3144



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 66.5844 - sparse_categorical_accuracy: 0.3144



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 66.6358 - sparse_categorical_accuracy: 0.3144



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 66.6834 - sparse_categorical_accuracy: 0.3144



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 66.7256 - sparse_categorical_accuracy: 0.3144



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 66.7642 - sparse_categorical_accuracy: 0.3144



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 66.7980 - sparse_categorical_accuracy: 0.3145



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 66.8283 - sparse_categorical_accuracy: 0.3145



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 66.8676 - sparse_categorical_accuracy: 0.3145



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 66.9055 - sparse_categorical_accuracy: 0.3145



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 66.9389 - sparse_categorical_accuracy: 0.3145



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 66.9682 - sparse_categorical_accuracy: 0.3146



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 67.0068 - sparse_categorical_accuracy: 0.3147



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 67.0413 - sparse_categorical_accuracy: 0.3147



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 67.0722 - sparse_categorical_accuracy: 0.3148



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 67.0993 - sparse_categorical_accuracy: 0.3149



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 67.1250 - sparse_categorical_accuracy: 0.3150



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 67.1480 - sparse_categorical_accuracy: 0.3150



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 67.1680 - sparse_categorical_accuracy: 0.3151



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 67.1852 - sparse_categorical_accuracy: 0.3152



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 67.2117 - sparse_categorical_accuracy: 0.3154



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 67.2353 - sparse_categorical_accuracy: 0.3155



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 67.2570 - sparse_categorical_accuracy: 0.3156



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 67.2819 - sparse_categorical_accuracy: 0.3157



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 67.3040 - sparse_categorical_accuracy: 0.3158



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 67.3234 - sparse_categorical_accuracy: 0.3159



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 67.3401 - sparse_categorical_accuracy: 0.3160



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 67.3545 - sparse_categorical_accuracy: 0.3161



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 67.3668 - sparse_categorical_accuracy: 0.3162



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 67.3805 - sparse_categorical_accuracy: 0.3164



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 67.3918 - sparse_categorical_accuracy: 0.3165



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 67.4010 - sparse_categorical_accuracy: 0.3166



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 67.4103 - sparse_categorical_accuracy: 0.3168



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 67.4179 - sparse_categorical_accuracy: 0.3169



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 67.4237 - sparse_categorical_accuracy: 0.3171



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 67.4318 - sparse_categorical_accuracy: 0.3172



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 67.4379 - sparse_categorical_accuracy: 0.3174



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 67.4424 - sparse_categorical_accuracy: 0.3175



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 67.4458 - sparse_categorical_accuracy: 0.3176 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 67.4481 - sparse_categorical_accuracy: 0.3178



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 67.4508 - sparse_categorical_accuracy: 0.3179



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 67.4519 - sparse_categorical_accuracy: 0.3180



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 67.4519 - sparse_categorical_accuracy: 0.3181



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 67.4504 - sparse_categorical_accuracy: 0.3182



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 67.4478 - sparse_categorical_accuracy: 0.3184



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 67.4438 - sparse_categorical_accuracy: 0.3185



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 67.4389 - sparse_categorical_accuracy: 0.3186



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 67.4304 - sparse_categorical_accuracy: 0.3187



100/100 ━━━━━━━━━━━━━━━━━━━━ 107s 1s/step - loss: 67.4222 - sparse_categorical_accuracy: 0.3189 - val_loss: 37.0687 - val_sparse_categorical_accuracy: 0.1477

Epoch 17/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 58:50 36s/step - loss: 54.1712 - sparse_categorical_accuracy: 0.5312



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 996ms/step - loss: 54.1433 - sparse_categorical_accuracy: 0.4844



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 54.2923 - sparse_categorical_accuracy: 0.4583 



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 54.3945 - sparse_categorical_accuracy: 0.4395



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 54.4431 - sparse_categorical_accuracy: 0.4228



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 54.4496 - sparse_categorical_accuracy: 0.4122



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 54.4618 - sparse_categorical_accuracy: 0.4031



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 54.4794 - sparse_categorical_accuracy: 0.3937



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 54.5192 - sparse_categorical_accuracy: 0.3851



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 54.5401 - sparse_categorical_accuracy: 0.3766



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 54.5954 - sparse_categorical_accuracy: 0.3710



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 54.6501 - sparse_categorical_accuracy: 0.3659



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 54.7149 - sparse_categorical_accuracy: 0.3622



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 54.7656 - sparse_categorical_accuracy: 0.3591



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 54.8022 - sparse_categorical_accuracy: 0.3567



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 54.8257 - sparse_categorical_accuracy: 0.3542



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 54.8423 - sparse_categorical_accuracy: 0.3525



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 54.9699 - sparse_categorical_accuracy: 0.3509



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 55.0764 - sparse_categorical_accuracy: 0.3496



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 55.1662 - sparse_categorical_accuracy: 0.3486



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 55.2427 - sparse_categorical_accuracy: 0.3476



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 55.3652 - sparse_categorical_accuracy: 0.3469



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 55.4674 - sparse_categorical_accuracy: 0.3462



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 55.5522 - sparse_categorical_accuracy: 0.3454



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 55.6296 - sparse_categorical_accuracy: 0.3448



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 55.6969 - sparse_categorical_accuracy: 0.3443



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 55.7546 - sparse_categorical_accuracy: 0.3437



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 55.8086 - sparse_categorical_accuracy: 0.3432



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 55.8801 - sparse_categorical_accuracy: 0.3426



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 55.9433 - sparse_categorical_accuracy: 0.3422



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 55.9972 - sparse_categorical_accuracy: 0.3418



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 56.0430 - sparse_categorical_accuracy: 0.3416



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 56.1322 - sparse_categorical_accuracy: 0.3413



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 56.2106 - sparse_categorical_accuracy: 0.3411



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 56.2797 - sparse_categorical_accuracy: 0.3408



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 56.3416 - sparse_categorical_accuracy: 0.3404



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 56.4020 - sparse_categorical_accuracy: 0.3399



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 56.5119 - sparse_categorical_accuracy: 0.3394



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 56.6107 - sparse_categorical_accuracy: 0.3390



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 56.7063 - sparse_categorical_accuracy: 0.3387



41/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 56.7925 - sparse_categorical_accuracy: 0.3384 



42/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 56.8706 - sparse_categorical_accuracy: 0.3381



43/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 56.9405 - sparse_categorical_accuracy: 0.3377



44/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 57.0081 - sparse_categorical_accuracy: 0.3373



45/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 57.0696 - sparse_categorical_accuracy: 0.3369



46/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 57.1252 - sparse_categorical_accuracy: 0.3366



47/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 57.1747 - sparse_categorical_accuracy: 0.3363



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 57.2194 - sparse_categorical_accuracy: 0.3360



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 57.2593 - sparse_categorical_accuracy: 0.3357



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 57.2964 - sparse_categorical_accuracy: 0.3355



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 57.3293 - sparse_categorical_accuracy: 0.3352



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 57.3585 - sparse_categorical_accuracy: 0.3351



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 57.3855 - sparse_categorical_accuracy: 0.3348



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 57.4333 - sparse_categorical_accuracy: 0.3346



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 57.4782 - sparse_categorical_accuracy: 0.3343



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 57.5188 - sparse_categorical_accuracy: 0.3341



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 57.5586 - sparse_categorical_accuracy: 0.3338



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 57.5993 - sparse_categorical_accuracy: 0.3335



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 57.6384 - sparse_categorical_accuracy: 0.3333



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 57.6740 - sparse_categorical_accuracy: 0.3331



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 57.7064 - sparse_categorical_accuracy: 0.3329



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 57.7355 - sparse_categorical_accuracy: 0.3327



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 57.7617 - sparse_categorical_accuracy: 0.3325



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 57.7892 - sparse_categorical_accuracy: 0.3323



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 57.8148 - sparse_categorical_accuracy: 0.3321



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 57.8380 - sparse_categorical_accuracy: 0.3320



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 57.8589 - sparse_categorical_accuracy: 0.3318



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 57.8776 - sparse_categorical_accuracy: 0.3317



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 57.8941 - sparse_categorical_accuracy: 0.3315



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 57.9087 - sparse_categorical_accuracy: 0.3314



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 57.9215 - sparse_categorical_accuracy: 0.3312



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 57.9324 - sparse_categorical_accuracy: 0.3310



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 57.9434 - sparse_categorical_accuracy: 0.3309



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 57.9529 - sparse_categorical_accuracy: 0.3307



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 57.9608 - sparse_categorical_accuracy: 0.3305



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 57.9671 - sparse_categorical_accuracy: 0.3304



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 57.9843 - sparse_categorical_accuracy: 0.3302



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 57.9998 - sparse_categorical_accuracy: 0.3300



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 58.0135 - sparse_categorical_accuracy: 0.3299



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 58.0259 - sparse_categorical_accuracy: 0.3298



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 58.0429 - sparse_categorical_accuracy: 0.3296



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 58.0585 - sparse_categorical_accuracy: 0.3295



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 58.0728 - sparse_categorical_accuracy: 0.3293



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 58.0856 - sparse_categorical_accuracy: 0.3292



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 58.1039 - sparse_categorical_accuracy: 0.3291



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 58.1206 - sparse_categorical_accuracy: 0.3290



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 58.1372 - sparse_categorical_accuracy: 0.3289



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 58.1528 - sparse_categorical_accuracy: 0.3288



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 58.1669 - sparse_categorical_accuracy: 0.3288



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 58.1796 - sparse_categorical_accuracy: 0.3287



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 58.1911 - sparse_categorical_accuracy: 0.3286 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 58.2014 - sparse_categorical_accuracy: 0.3285



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 58.2118 - sparse_categorical_accuracy: 0.3285



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 58.2212 - sparse_categorical_accuracy: 0.3284



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 58.2345 - sparse_categorical_accuracy: 0.3284



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 58.2465 - sparse_categorical_accuracy: 0.3283



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 58.2574 - sparse_categorical_accuracy: 0.3283



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 58.2673 - sparse_categorical_accuracy: 0.3283



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 58.2759 - sparse_categorical_accuracy: 0.3282



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 58.2815 - sparse_categorical_accuracy: 0.3282



100/100 ━━━━━━━━━━━━━━━━━━━━ 141s 1s/step - loss: 58.2869 - sparse_categorical_accuracy: 0.3282 - val_loss: 4191578574815232.0000 - val_sparse_categorical_accuracy: 0.3129

Epoch 18/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:39 1s/step - loss: 51.9365 - sparse_categorical_accuracy: 0.4375



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 57.0536 - sparse_categorical_accuracy: 0.3984



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:40 1s/step - loss: 57.4789 - sparse_categorical_accuracy: 0.3767



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 57.1816 - sparse_categorical_accuracy: 0.3529



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 57.1706 - sparse_categorical_accuracy: 0.3435



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 57.8198 - sparse_categorical_accuracy: 0.3349



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 58.1971 - sparse_categorical_accuracy: 0.3285



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 58.3237 - sparse_categorical_accuracy: 0.3236



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 58.3409 - sparse_categorical_accuracy: 0.3200



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 58.5552 - sparse_categorical_accuracy: 0.3165



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 58.6516 - sparse_categorical_accuracy: 0.3143



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 58.6702 - sparse_categorical_accuracy: 0.3131



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 58.6391 - sparse_categorical_accuracy: 0.3126



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 58.6047 - sparse_categorical_accuracy: 0.3125



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 58.5388 - sparse_categorical_accuracy: 0.3126



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 58.4930 - sparse_categorical_accuracy: 0.3130



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 58.5077 - sparse_categorical_accuracy: 0.3135



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 58.5053 - sparse_categorical_accuracy: 0.3142



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 58.4806 - sparse_categorical_accuracy: 0.3154



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 58.4394 - sparse_categorical_accuracy: 0.3170



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 58.4049 - sparse_categorical_accuracy: 0.3185



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 58.3601 - sparse_categorical_accuracy: 0.3198



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 58.3112 - sparse_categorical_accuracy: 0.3208



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 58.2546 - sparse_categorical_accuracy: 0.3219



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 58.1921 - sparse_categorical_accuracy: 0.3226



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 58.1254 - sparse_categorical_accuracy: 0.3234



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 58.0712 - sparse_categorical_accuracy: 0.3242



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 58.0117 - sparse_categorical_accuracy: 0.3251



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 57.9476 - sparse_categorical_accuracy: 0.3258



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 57.8802 - sparse_categorical_accuracy: 0.3267



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 57.8106 - sparse_categorical_accuracy: 0.3275



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 57.7397 - sparse_categorical_accuracy: 0.3282



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 57.6674 - sparse_categorical_accuracy: 0.3289



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 57.5958 - sparse_categorical_accuracy: 0.3295



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 57.5233 - sparse_categorical_accuracy: 0.3300



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 57.4506 - sparse_categorical_accuracy: 0.3304



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 57.3774 - sparse_categorical_accuracy: 0.3307



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 57.3046 - sparse_categorical_accuracy: 0.3310



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 57.2337 - sparse_categorical_accuracy: 0.3311



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 57.1629 - sparse_categorical_accuracy: 0.3312



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 57.0945 - sparse_categorical_accuracy: 0.3312



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 57.0267 - sparse_categorical_accuracy: 0.3313 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 56.9828 - sparse_categorical_accuracy: 0.3314



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 56.9401 - sparse_categorical_accuracy: 0.3315



45/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 56.8960 - sparse_categorical_accuracy: 0.3317



46/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 56.8507 - sparse_categorical_accuracy: 0.3319



47/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 56.8044 - sparse_categorical_accuracy: 0.3322



48/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 56.7577 - sparse_categorical_accuracy: 0.3325



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 56.7108 - sparse_categorical_accuracy: 0.3327



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 56.6634 - sparse_categorical_accuracy: 0.3329



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 56.6159 - sparse_categorical_accuracy: 0.3331



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 56.5681 - sparse_categorical_accuracy: 0.3332



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 56.5206 - sparse_categorical_accuracy: 0.3333



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 56.4731 - sparse_categorical_accuracy: 0.3333



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 56.4286 - sparse_categorical_accuracy: 0.3334



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 56.3840 - sparse_categorical_accuracy: 0.3334



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 56.3394 - sparse_categorical_accuracy: 0.3334



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 56.3065 - sparse_categorical_accuracy: 0.3335



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 56.2731 - sparse_categorical_accuracy: 0.3336



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 56.2395 - sparse_categorical_accuracy: 0.3336



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 56.2054 - sparse_categorical_accuracy: 0.3337



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 56.1711 - sparse_categorical_accuracy: 0.3338



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 56.1365 - sparse_categorical_accuracy: 0.3339



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 56.1018 - sparse_categorical_accuracy: 0.3339



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 56.0668 - sparse_categorical_accuracy: 0.3339



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 56.0318 - sparse_categorical_accuracy: 0.3339



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 55.9968 - sparse_categorical_accuracy: 0.3339



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 55.9643 - sparse_categorical_accuracy: 0.3339



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 55.9317 - sparse_categorical_accuracy: 0.3340



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 55.8996 - sparse_categorical_accuracy: 0.3340



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 55.8673 - sparse_categorical_accuracy: 0.3341



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 55.8357 - sparse_categorical_accuracy: 0.3342



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 55.8041 - sparse_categorical_accuracy: 0.3343



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 55.7725 - sparse_categorical_accuracy: 0.3343



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 55.7424 - sparse_categorical_accuracy: 0.3344



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 55.7129 - sparse_categorical_accuracy: 0.3345



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 55.6835 - sparse_categorical_accuracy: 0.3346



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 55.6543 - sparse_categorical_accuracy: 0.3346



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 55.6249 - sparse_categorical_accuracy: 0.3347



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 55.5968 - sparse_categorical_accuracy: 0.3348



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 55.5756 - sparse_categorical_accuracy: 0.3348



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 55.5541 - sparse_categorical_accuracy: 0.3349



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 55.5328 - sparse_categorical_accuracy: 0.3349



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 55.5113 - sparse_categorical_accuracy: 0.3350



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 55.4897 - sparse_categorical_accuracy: 0.3351



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 55.4680 - sparse_categorical_accuracy: 0.3351



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 55.4463 - sparse_categorical_accuracy: 0.3351



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 55.4254 - sparse_categorical_accuracy: 0.3352



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 55.4044 - sparse_categorical_accuracy: 0.3352



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 55.3833 - sparse_categorical_accuracy: 0.3352



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 55.3620 - sparse_categorical_accuracy: 0.3352 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 55.3407 - sparse_categorical_accuracy: 0.3352



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 55.3192 - sparse_categorical_accuracy: 0.3352



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 55.2975 - sparse_categorical_accuracy: 0.3352



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 55.2758 - sparse_categorical_accuracy: 0.3352



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 55.2539 - sparse_categorical_accuracy: 0.3352



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 55.2319 - sparse_categorical_accuracy: 0.3352



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 55.2103 - sparse_categorical_accuracy: 0.3352



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 55.1890 - sparse_categorical_accuracy: 0.3352



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 55.1664 - sparse_categorical_accuracy: 0.3351



100/100 ━━━━━━━━━━━━━━━━━━━━ 106s 1s/step - loss: 55.1443 - sparse_categorical_accuracy: 0.3351 - val_loss: 50221851662203486208.0000 - val_sparse_categorical_accuracy: 0.3242

Epoch 19/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 48.0290 - sparse_categorical_accuracy: 0.2188



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:44 1s/step - loss: 48.0152 - sparse_categorical_accuracy: 0.2422



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:41 1s/step - loss: 48.0897 - sparse_categorical_accuracy: 0.2622



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:38 1s/step - loss: 48.2575 - sparse_categorical_accuracy: 0.2786



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 48.2910 - sparse_categorical_accuracy: 0.2917



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 48.2856 - sparse_categorical_accuracy: 0.3012



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 48.2775 - sparse_categorical_accuracy: 0.3067



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 48.2703 - sparse_categorical_accuracy: 0.3098



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 48.2452 - sparse_categorical_accuracy: 0.3132



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:32 1s/step - loss: 48.2307 - sparse_categorical_accuracy: 0.3147



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 48.2224 - sparse_categorical_accuracy: 0.3148



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 48.2436 - sparse_categorical_accuracy: 0.3154



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:29 1s/step - loss: 48.4003 - sparse_categorical_accuracy: 0.3165



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 48.5188 - sparse_categorical_accuracy: 0.3173



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 48.6114 - sparse_categorical_accuracy: 0.3177



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 48.6889 - sparse_categorical_accuracy: 0.3188



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 48.8238 - sparse_categorical_accuracy: 0.3200



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 48.9324 - sparse_categorical_accuracy: 0.3209



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 49.0280 - sparse_categorical_accuracy: 0.3215



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 49.1080 - sparse_categorical_accuracy: 0.3221



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 49.1839 - sparse_categorical_accuracy: 0.3223



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 49.2456 - sparse_categorical_accuracy: 0.3229



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 49.3109 - sparse_categorical_accuracy: 0.3234



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 49.3649 - sparse_categorical_accuracy: 0.3238



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 49.4094 - sparse_categorical_accuracy: 0.3242



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 49.4442 - sparse_categorical_accuracy: 0.3245



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 49.4733 - sparse_categorical_accuracy: 0.3249



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 49.4992 - sparse_categorical_accuracy: 0.3254



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 49.5312 - sparse_categorical_accuracy: 0.3259



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 49.5580 - sparse_categorical_accuracy: 0.3263



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 49.5893 - sparse_categorical_accuracy: 0.3266



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 49.6143 - sparse_categorical_accuracy: 0.3269



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 49.6356 - sparse_categorical_accuracy: 0.3271



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 49.6533 - sparse_categorical_accuracy: 0.3274



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 49.6677 - sparse_categorical_accuracy: 0.3276



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 49.6871 - sparse_categorical_accuracy: 0.3280



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 49.7037 - sparse_categorical_accuracy: 0.3283



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 49.7168 - sparse_categorical_accuracy: 0.3287



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 49.7293 - sparse_categorical_accuracy: 0.3290



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 49.7390 - sparse_categorical_accuracy: 0.3293



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 49.7459 - sparse_categorical_accuracy: 0.3296



42/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 49.7542 - sparse_categorical_accuracy: 0.3298



43/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 49.7604 - sparse_categorical_accuracy: 0.3300 



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 49.7769 - sparse_categorical_accuracy: 0.3302



45/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 49.7948 - sparse_categorical_accuracy: 0.3304



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 49.8099 - sparse_categorical_accuracy: 0.3306



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 49.8228 - sparse_categorical_accuracy: 0.3307



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 49.8335 - sparse_categorical_accuracy: 0.3307



49/100 ━━━━━━━━━━━━━━━━━━━━ 52s 1s/step - loss: 49.8428 - sparse_categorical_accuracy: 0.3308



50/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 49.8501 - sparse_categorical_accuracy: 0.3308



51/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 49.8558 - sparse_categorical_accuracy: 0.3308



52/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 49.8601 - sparse_categorical_accuracy: 0.3308



53/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 49.8642 - sparse_categorical_accuracy: 0.3308



54/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 49.8671 - sparse_categorical_accuracy: 0.3309



55/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 49.8689 - sparse_categorical_accuracy: 0.3310



56/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 49.8703 - sparse_categorical_accuracy: 0.3311



57/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 49.8753 - sparse_categorical_accuracy: 0.3312



58/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 49.8791 - sparse_categorical_accuracy: 0.3313



59/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 49.8816 - sparse_categorical_accuracy: 0.3315



60/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 49.8859 - sparse_categorical_accuracy: 0.3316



61/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 49.8905 - sparse_categorical_accuracy: 0.3317



62/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 49.8946 - sparse_categorical_accuracy: 0.3318



63/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 49.8977 - sparse_categorical_accuracy: 0.3319



64/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 49.9000 - sparse_categorical_accuracy: 0.3320



65/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 49.9015 - sparse_categorical_accuracy: 0.3321



66/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 49.9024 - sparse_categorical_accuracy: 0.3322



67/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 49.9043 - sparse_categorical_accuracy: 0.3322



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 49.9063 - sparse_categorical_accuracy: 0.3322



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 49.9077 - sparse_categorical_accuracy: 0.3323



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 49.9082 - sparse_categorical_accuracy: 0.3323



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 49.9081 - sparse_categorical_accuracy: 0.3323



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 49.9074 - sparse_categorical_accuracy: 0.3323



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 49.9060 - sparse_categorical_accuracy: 0.3323



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 49.9042 - sparse_categorical_accuracy: 0.3323



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 49.9035 - sparse_categorical_accuracy: 0.3323



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 49.9023 - sparse_categorical_accuracy: 0.3323



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 49.9021 - sparse_categorical_accuracy: 0.3323



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 49.9030 - sparse_categorical_accuracy: 0.3323



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 49.9032 - sparse_categorical_accuracy: 0.3322



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 49.9029 - sparse_categorical_accuracy: 0.3322



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 49.9061 - sparse_categorical_accuracy: 0.3322



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 49.9088 - sparse_categorical_accuracy: 0.3322



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 49.9109 - sparse_categorical_accuracy: 0.3321



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 49.9124 - sparse_categorical_accuracy: 0.3321



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 49.9136 - sparse_categorical_accuracy: 0.3321



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 49.9143 - sparse_categorical_accuracy: 0.3321



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 49.9144 - sparse_categorical_accuracy: 0.3320



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 49.9143 - sparse_categorical_accuracy: 0.3320



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 49.9138 - sparse_categorical_accuracy: 0.3320



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 49.9136 - sparse_categorical_accuracy: 0.3319



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 49.9129 - sparse_categorical_accuracy: 0.3319 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 49.9119 - sparse_categorical_accuracy: 0.3318



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 49.9104 - sparse_categorical_accuracy: 0.3318



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 49.9085 - sparse_categorical_accuracy: 0.3317



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 49.9062 - sparse_categorical_accuracy: 0.3317



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 49.9041 - sparse_categorical_accuracy: 0.3317



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 49.9024 - sparse_categorical_accuracy: 0.3317



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 49.9033 - sparse_categorical_accuracy: 0.3317



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 49.9038 - sparse_categorical_accuracy: 0.3317



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 49.9019 - sparse_categorical_accuracy: 0.3317



100/100 ━━━━━━━━━━━━━━━━━━━━ 108s 1s/step - loss: 49.9001 - sparse_categorical_accuracy: 0.3317 - val_loss: 69256328.0000 - val_sparse_categorical_accuracy: 0.3579

Epoch 20/20

1/100 ━━━━━━━━━━━━━━━━━━━━ 1:42 1s/step - loss: 45.8100 - sparse_categorical_accuracy: 0.4062



2/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 990ms/step - loss: 45.8442 - sparse_categorical_accuracy: 0.4062



3/100 ━━━━━━━━━━━━━━━━━━━━ 1:37 1s/step - loss: 45.8131 - sparse_categorical_accuracy: 0.3993 



4/100 ━━━━━━━━━━━━━━━━━━━━ 1:36 1s/step - loss: 45.8064 - sparse_categorical_accuracy: 0.3913



5/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 45.8227 - sparse_categorical_accuracy: 0.3868



6/100 ━━━━━━━━━━━━━━━━━━━━ 1:35 1s/step - loss: 45.8191 - sparse_categorical_accuracy: 0.3831



7/100 ━━━━━━━━━━━━━━━━━━━━ 1:34 1s/step - loss: 45.8214 - sparse_categorical_accuracy: 0.3762



8/100 ━━━━━━━━━━━━━━━━━━━━ 1:33 1s/step - loss: 45.8634 - sparse_categorical_accuracy: 0.3702



9/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 45.8982 - sparse_categorical_accuracy: 0.3634



10/100 ━━━━━━━━━━━━━━━━━━━━ 1:31 1s/step - loss: 45.9172 - sparse_categorical_accuracy: 0.3589



11/100 ━━━━━━━━━━━━━━━━━━━━ 1:30 1s/step - loss: 45.9713 - sparse_categorical_accuracy: 0.3560



12/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 46.0114 - sparse_categorical_accuracy: 0.3548



13/100 ━━━━━━━━━━━━━━━━━━━━ 1:28 1s/step - loss: 46.0793 - sparse_categorical_accuracy: 0.3535



14/100 ━━━━━━━━━━━━━━━━━━━━ 1:27 1s/step - loss: 46.1364 - sparse_categorical_accuracy: 0.3520



15/100 ━━━━━━━━━━━━━━━━━━━━ 1:26 1s/step - loss: 46.1765 - sparse_categorical_accuracy: 0.3509



16/100 ━━━━━━━━━━━━━━━━━━━━ 1:25 1s/step - loss: 46.2080 - sparse_categorical_accuracy: 0.3504



17/100 ━━━━━━━━━━━━━━━━━━━━ 1:24 1s/step - loss: 46.2316 - sparse_categorical_accuracy: 0.3498



18/100 ━━━━━━━━━━━━━━━━━━━━ 1:23 1s/step - loss: 46.2481 - sparse_categorical_accuracy: 0.3491



19/100 ━━━━━━━━━━━━━━━━━━━━ 1:22 1s/step - loss: 46.2610 - sparse_categorical_accuracy: 0.3484



20/100 ━━━━━━━━━━━━━━━━━━━━ 1:21 1s/step - loss: 46.2706 - sparse_categorical_accuracy: 0.3473



21/100 ━━━━━━━━━━━━━━━━━━━━ 1:20 1s/step - loss: 46.2769 - sparse_categorical_accuracy: 0.3465



22/100 ━━━━━━━━━━━━━━━━━━━━ 1:19 1s/step - loss: 46.2793 - sparse_categorical_accuracy: 0.3458



23/100 ━━━━━━━━━━━━━━━━━━━━ 1:18 1s/step - loss: 46.2795 - sparse_categorical_accuracy: 0.3452



24/100 ━━━━━━━━━━━━━━━━━━━━ 1:17 1s/step - loss: 46.2889 - sparse_categorical_accuracy: 0.3452



25/100 ━━━━━━━━━━━━━━━━━━━━ 1:16 1s/step - loss: 46.2960 - sparse_categorical_accuracy: 0.3454



26/100 ━━━━━━━━━━━━━━━━━━━━ 1:15 1s/step - loss: 46.3007 - sparse_categorical_accuracy: 0.3455



27/100 ━━━━━━━━━━━━━━━━━━━━ 1:14 1s/step - loss: 46.3038 - sparse_categorical_accuracy: 0.3455



28/100 ━━━━━━━━━━━━━━━━━━━━ 1:13 1s/step - loss: 46.3053 - sparse_categorical_accuracy: 0.3455



29/100 ━━━━━━━━━━━━━━━━━━━━ 1:12 1s/step - loss: 46.3057 - sparse_categorical_accuracy: 0.3454



30/100 ━━━━━━━━━━━━━━━━━━━━ 1:11 1s/step - loss: 46.3050 - sparse_categorical_accuracy: 0.3453



31/100 ━━━━━━━━━━━━━━━━━━━━ 1:10 1s/step - loss: 46.3095 - sparse_categorical_accuracy: 0.3451



32/100 ━━━━━━━━━━━━━━━━━━━━ 1:09 1s/step - loss: 46.3201 - sparse_categorical_accuracy: 0.3449



33/100 ━━━━━━━━━━━━━━━━━━━━ 1:08 1s/step - loss: 46.3293 - sparse_categorical_accuracy: 0.3446



34/100 ━━━━━━━━━━━━━━━━━━━━ 1:07 1s/step - loss: 46.3368 - sparse_categorical_accuracy: 0.3444



35/100 ━━━━━━━━━━━━━━━━━━━━ 1:06 1s/step - loss: 46.3819 - sparse_categorical_accuracy: 0.3445



36/100 ━━━━━━━━━━━━━━━━━━━━ 1:05 1s/step - loss: 46.4228 - sparse_categorical_accuracy: 0.3445



37/100 ━━━━━━━━━━━━━━━━━━━━ 1:04 1s/step - loss: 46.4597 - sparse_categorical_accuracy: 0.3446



38/100 ━━━━━━━━━━━━━━━━━━━━ 1:03 1s/step - loss: 46.4928 - sparse_categorical_accuracy: 0.3446



39/100 ━━━━━━━━━━━━━━━━━━━━ 1:02 1s/step - loss: 46.5227 - sparse_categorical_accuracy: 0.3448



40/100 ━━━━━━━━━━━━━━━━━━━━ 1:01 1s/step - loss: 46.5496 - sparse_categorical_accuracy: 0.3448



41/100 ━━━━━━━━━━━━━━━━━━━━ 1:00 1s/step - loss: 46.5741 - sparse_categorical_accuracy: 0.3447



42/100 ━━━━━━━━━━━━━━━━━━━━ 59s 1s/step - loss: 46.5961 - sparse_categorical_accuracy: 0.3447 



43/100 ━━━━━━━━━━━━━━━━━━━━ 58s 1s/step - loss: 46.6158 - sparse_categorical_accuracy: 0.3446



44/100 ━━━━━━━━━━━━━━━━━━━━ 57s 1s/step - loss: 46.6335 - sparse_categorical_accuracy: 0.3445



45/100 ━━━━━━━━━━━━━━━━━━━━ 56s 1s/step - loss: 46.6635 - sparse_categorical_accuracy: 0.3444



46/100 ━━━━━━━━━━━━━━━━━━━━ 55s 1s/step - loss: 46.6909 - sparse_categorical_accuracy: 0.3442



47/100 ━━━━━━━━━━━━━━━━━━━━ 54s 1s/step - loss: 46.7195 - sparse_categorical_accuracy: 0.3439



48/100 ━━━━━━━━━━━━━━━━━━━━ 53s 1s/step - loss: 46.7477 - sparse_categorical_accuracy: 0.3437



49/100 ━━━━━━━━━━━━━━━━━━━━ 51s 1s/step - loss: 46.7799 - sparse_categorical_accuracy: 0.3435



50/100 ━━━━━━━━━━━━━━━━━━━━ 50s 1s/step - loss: 46.8102 - sparse_categorical_accuracy: 0.3434



51/100 ━━━━━━━━━━━━━━━━━━━━ 49s 1s/step - loss: 46.8381 - sparse_categorical_accuracy: 0.3432



52/100 ━━━━━━━━━━━━━━━━━━━━ 48s 1s/step - loss: 46.8639 - sparse_categorical_accuracy: 0.3430



53/100 ━━━━━━━━━━━━━━━━━━━━ 47s 1s/step - loss: 46.8877 - sparse_categorical_accuracy: 0.3429



54/100 ━━━━━━━━━━━━━━━━━━━━ 46s 1s/step - loss: 46.9095 - sparse_categorical_accuracy: 0.3428



55/100 ━━━━━━━━━━━━━━━━━━━━ 45s 1s/step - loss: 46.9390 - sparse_categorical_accuracy: 0.3427



56/100 ━━━━━━━━━━━━━━━━━━━━ 44s 1s/step - loss: 46.9676 - sparse_categorical_accuracy: 0.3425



57/100 ━━━━━━━━━━━━━━━━━━━━ 43s 1s/step - loss: 46.9940 - sparse_categorical_accuracy: 0.3423



58/100 ━━━━━━━━━━━━━━━━━━━━ 42s 1s/step - loss: 47.0190 - sparse_categorical_accuracy: 0.3422



59/100 ━━━━━━━━━━━━━━━━━━━━ 41s 1s/step - loss: 47.0420 - sparse_categorical_accuracy: 0.3421



60/100 ━━━━━━━━━━━━━━━━━━━━ 40s 1s/step - loss: 47.0631 - sparse_categorical_accuracy: 0.3421



61/100 ━━━━━━━━━━━━━━━━━━━━ 39s 1s/step - loss: 47.0824 - sparse_categorical_accuracy: 0.3420



62/100 ━━━━━━━━━━━━━━━━━━━━ 38s 1s/step - loss: 47.1005 - sparse_categorical_accuracy: 0.3419



63/100 ━━━━━━━━━━━━━━━━━━━━ 37s 1s/step - loss: 47.1221 - sparse_categorical_accuracy: 0.3419



64/100 ━━━━━━━━━━━━━━━━━━━━ 36s 1s/step - loss: 47.1436 - sparse_categorical_accuracy: 0.3418



65/100 ━━━━━━━━━━━━━━━━━━━━ 35s 1s/step - loss: 47.1636 - sparse_categorical_accuracy: 0.3417



66/100 ━━━━━━━━━━━━━━━━━━━━ 34s 1s/step - loss: 47.1827 - sparse_categorical_accuracy: 0.3417



67/100 ━━━━━━━━━━━━━━━━━━━━ 33s 1s/step - loss: 47.2009 - sparse_categorical_accuracy: 0.3417



68/100 ━━━━━━━━━━━━━━━━━━━━ 32s 1s/step - loss: 47.2186 - sparse_categorical_accuracy: 0.3417



69/100 ━━━━━━━━━━━━━━━━━━━━ 31s 1s/step - loss: 47.2351 - sparse_categorical_accuracy: 0.3418



70/100 ━━━━━━━━━━━━━━━━━━━━ 30s 1s/step - loss: 47.2515 - sparse_categorical_accuracy: 0.3418



71/100 ━━━━━━━━━━━━━━━━━━━━ 29s 1s/step - loss: 47.2666 - sparse_categorical_accuracy: 0.3418



72/100 ━━━━━━━━━━━━━━━━━━━━ 28s 1s/step - loss: 47.2820 - sparse_categorical_accuracy: 0.3418



73/100 ━━━━━━━━━━━━━━━━━━━━ 27s 1s/step - loss: 47.2965 - sparse_categorical_accuracy: 0.3419



74/100 ━━━━━━━━━━━━━━━━━━━━ 26s 1s/step - loss: 47.3101 - sparse_categorical_accuracy: 0.3419



75/100 ━━━━━━━━━━━━━━━━━━━━ 25s 1s/step - loss: 47.3227 - sparse_categorical_accuracy: 0.3419



76/100 ━━━━━━━━━━━━━━━━━━━━ 24s 1s/step - loss: 47.3343 - sparse_categorical_accuracy: 0.3419



77/100 ━━━━━━━━━━━━━━━━━━━━ 23s 1s/step - loss: 47.3463 - sparse_categorical_accuracy: 0.3418



78/100 ━━━━━━━━━━━━━━━━━━━━ 22s 1s/step - loss: 47.3574 - sparse_categorical_accuracy: 0.3418



79/100 ━━━━━━━━━━━━━━━━━━━━ 21s 1s/step - loss: 47.3678 - sparse_categorical_accuracy: 0.3418



80/100 ━━━━━━━━━━━━━━━━━━━━ 20s 1s/step - loss: 47.3773 - sparse_categorical_accuracy: 0.3417



81/100 ━━━━━━━━━━━━━━━━━━━━ 19s 1s/step - loss: 47.3878 - sparse_categorical_accuracy: 0.3417



82/100 ━━━━━━━━━━━━━━━━━━━━ 18s 1s/step - loss: 47.3974 - sparse_categorical_accuracy: 0.3417



83/100 ━━━━━━━━━━━━━━━━━━━━ 17s 1s/step - loss: 47.4062 - sparse_categorical_accuracy: 0.3416



84/100 ━━━━━━━━━━━━━━━━━━━━ 16s 1s/step - loss: 47.4142 - sparse_categorical_accuracy: 0.3416



85/100 ━━━━━━━━━━━━━━━━━━━━ 15s 1s/step - loss: 47.4216 - sparse_categorical_accuracy: 0.3415



86/100 ━━━━━━━━━━━━━━━━━━━━ 14s 1s/step - loss: 47.4285 - sparse_categorical_accuracy: 0.3414



87/100 ━━━━━━━━━━━━━━━━━━━━ 13s 1s/step - loss: 47.4351 - sparse_categorical_accuracy: 0.3414



88/100 ━━━━━━━━━━━━━━━━━━━━ 12s 1s/step - loss: 47.4411 - sparse_categorical_accuracy: 0.3413



89/100 ━━━━━━━━━━━━━━━━━━━━ 11s 1s/step - loss: 47.4466 - sparse_categorical_accuracy: 0.3412



90/100 ━━━━━━━━━━━━━━━━━━━━ 10s 1s/step - loss: 47.4517 - sparse_categorical_accuracy: 0.3411



91/100 ━━━━━━━━━━━━━━━━━━━━ 9s 1s/step - loss: 47.4563 - sparse_categorical_accuracy: 0.3410 



92/100 ━━━━━━━━━━━━━━━━━━━━ 8s 1s/step - loss: 47.4604 - sparse_categorical_accuracy: 0.3410



93/100 ━━━━━━━━━━━━━━━━━━━━ 7s 1s/step - loss: 47.4641 - sparse_categorical_accuracy: 0.3409



94/100 ━━━━━━━━━━━━━━━━━━━━ 6s 1s/step - loss: 47.4688 - sparse_categorical_accuracy: 0.3409



95/100 ━━━━━━━━━━━━━━━━━━━━ 5s 1s/step - loss: 47.4731 - sparse_categorical_accuracy: 0.3408



96/100 ━━━━━━━━━━━━━━━━━━━━ 4s 1s/step - loss: 47.4771 - sparse_categorical_accuracy: 0.3407



97/100 ━━━━━━━━━━━━━━━━━━━━ 3s 1s/step - loss: 47.4814 - sparse_categorical_accuracy: 0.3406



98/100 ━━━━━━━━━━━━━━━━━━━━ 2s 1s/step - loss: 47.4854 - sparse_categorical_accuracy: 0.3406



99/100 ━━━━━━━━━━━━━━━━━━━━ 1s 1s/step - loss: 47.4889 - sparse_categorical_accuracy: 0.3405



100/100 ━━━━━━━━━━━━━━━━━━━━ 0s 1s/step - loss: 47.4901 - sparse_categorical_accuracy: 0.3404



100/100 ━━━━━━━━━━━━━━━━━━━━ 106s 1s/step - loss: 47.4913 - sparse_categorical_accuracy: 0.3404 - val_loss: 1814011445248.0000 - val_sparse_categorical_accuracy: 0.3592

<keras.src.callbacks.history.History at 0x7f596cb7b8e0>

Visualize predictions

We can use matplotlib to visualize our trained model performance.

data = test_dataset.take(1)

points, labels = list(data)[0]
points = points[:8, ...]
labels = labels[:8, ...]

# run test data through model
preds = model.predict(points)
preds = ops.argmax(preds, -1)

points = points.numpy()

# plot points with predicted class and label
fig = plt.figure(figsize=(15, 10))
for i in range(8):
    ax = fig.add_subplot(2, 4, i + 1, projection="3d")
    ax.scatter(points[i, :, 0], points[i, :, 1], points[i, :, 2])
    ax.set_title(
        "pred: {:}, label: {:}".format(
            CLASS_MAP[preds[i].numpy()], CLASS_MAP[labels.numpy()[i]]
        )
    )
    ax.set_axis_off()
plt.show()

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 404ms/step



1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 405ms/step

png

Point cloud classification with PointNet
Point cloud classification
Introduction
Setup
Load dataset
Build a model
Train model
Visualize predictions