Learning to tokenize in Vision Transformers

pip install tensorflow-addons

import tensorflow as tf

from tensorflow import keras
from tensorflow.keras import layers
import tensorflow_addons as tfa

from datetime import datetime
import matplotlib.pyplot as plt
import numpy as np

import math

# DATA
BATCH_SIZE = 256
AUTO = tf.data.AUTOTUNE
INPUT_SHAPE = (32, 32, 3)
NUM_CLASSES = 10

# OPTIMIZER
LEARNING_RATE = 1e-3
WEIGHT_DECAY = 1e-4

# TRAINING
EPOCHS = 20

# AUGMENTATION
IMAGE_SIZE = 48  # We will resize input images to this size.
PATCH_SIZE = 6  # Size of the patches to be extracted from the input images.
NUM_PATCHES = (IMAGE_SIZE // PATCH_SIZE) ** 2

# ViT ARCHITECTURE
LAYER_NORM_EPS = 1e-6
PROJECTION_DIM = 128
NUM_HEADS = 4
NUM_LAYERS = 4
MLP_UNITS = [
    PROJECTION_DIM * 2,
    PROJECTION_DIM,
]

# TOKENLEARNER
NUM_TOKENS = 4

# Load the CIFAR-10 dataset.
(x_train, y_train), (x_test, y_test) = keras.datasets.cifar10.load_data()
(x_train, y_train), (x_val, y_val) = (
    (x_train[:40000], y_train[:40000]),
    (x_train[40000:], y_train[40000:]),
)
print(f"Training samples: {len(x_train)}")
print(f"Validation samples: {len(x_val)}")
print(f"Testing samples: {len(x_test)}")

# Convert to tf.data.Dataset objects.
train_ds = tf.data.Dataset.from_tensor_slices((x_train, y_train))
train_ds = train_ds.shuffle(BATCH_SIZE * 100).batch(BATCH_SIZE).prefetch(AUTO)

val_ds = tf.data.Dataset.from_tensor_slices((x_val, y_val))
val_ds = val_ds.batch(BATCH_SIZE).prefetch(AUTO)

test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test))
test_ds = test_ds.batch(BATCH_SIZE).prefetch(AUTO)

data_augmentation = keras.Sequential(
    [
        layers.Rescaling(1 / 255.0),
        layers.Resizing(INPUT_SHAPE[0] + 20, INPUT_SHAPE[0] + 20),
        layers.RandomCrop(IMAGE_SIZE, IMAGE_SIZE),
        layers.RandomFlip("horizontal"),
    ],
    name="data_augmentation",
)

def position_embedding(
    projected_patches, num_patches=NUM_PATCHES, projection_dim=PROJECTION_DIM
):
    # Build the positions.
    positions = tf.range(start=0, limit=num_patches, delta=1)

    # Encode the positions with an Embedding layer.
    encoded_positions = layers.Embedding(
        input_dim=num_patches, output_dim=projection_dim
    )(positions)

    # Add encoded positions to the projected patches.
    return projected_patches + encoded_positions

def mlp(x, dropout_rate, hidden_units):
    # Iterate over the hidden units and
    # add Dense => Dropout.
    for units in hidden_units:
        x = layers.Dense(units, activation=tf.nn.gelu)(x)
        x = layers.Dropout(dropout_rate)(x)
    return x

def token_learner(inputs, number_of_tokens=NUM_TOKENS):
    # Layer normalize the inputs.
    x = layers.LayerNormalization(epsilon=LAYER_NORM_EPS)(inputs)  # (B, H, W, C)

    # Applying Conv2D => Reshape => Permute
    # The reshape and permute is done to help with the next steps of
    # multiplication and Global Average Pooling.
    attention_maps = keras.Sequential(
        [
            # 3 layers of conv with gelu activation as suggested
            # in the paper.
            layers.Conv2D(
                filters=number_of_tokens,
                kernel_size=(3, 3),
                activation=tf.nn.gelu,
                padding="same",
                use_bias=False,
            ),
            layers.Conv2D(
                filters=number_of_tokens,
                kernel_size=(3, 3),
                activation=tf.nn.gelu,
                padding="same",
                use_bias=False,
            ),
            layers.Conv2D(
                filters=number_of_tokens,
                kernel_size=(3, 3),
                activation=tf.nn.gelu,
                padding="same",
                use_bias=False,
            ),
            # This conv layer will generate the attention maps
            layers.Conv2D(
                filters=number_of_tokens,
                kernel_size=(3, 3),
                activation="sigmoid",  # Note sigmoid for [0, 1] output
                padding="same",
                use_bias=False,
            ),
            # Reshape and Permute
            layers.Reshape((-1, number_of_tokens)),  # (B, H*W, num_of_tokens)
            layers.Permute((2, 1)),
        ]
    )(
        x
    )  # (B, num_of_tokens, H*W)

    # Reshape the input to align it with the output of the conv block.
    num_filters = inputs.shape[-1]
    inputs = layers.Reshape((1, -1, num_filters))(inputs)  # inputs == (B, 1, H*W, C)

    # Element-Wise multiplication of the attention maps and the inputs
    attended_inputs = (
        attention_maps[..., tf.newaxis] * inputs
    )  # (B, num_tokens, H*W, C)

    # Global average pooling the element wise multiplication result.
    outputs = tf.reduce_mean(attended_inputs, axis=2)  # (B, num_tokens, C)
    return outputs

def transformer(encoded_patches):
    # Layer normalization 1.
    x1 = layers.LayerNormalization(epsilon=LAYER_NORM_EPS)(encoded_patches)

    # Multi Head Self Attention layer 1.
    attention_output = layers.MultiHeadAttention(
        num_heads=NUM_HEADS, key_dim=PROJECTION_DIM, dropout=0.1
    )(x1, x1)

    # Skip connection 1.
    x2 = layers.Add()([attention_output, encoded_patches])

    # Layer normalization 2.
    x3 = layers.LayerNormalization(epsilon=LAYER_NORM_EPS)(x2)

    # MLP layer 1.
    x4 = mlp(x3, hidden_units=MLP_UNITS, dropout_rate=0.1)

    # Skip connection 2.
    encoded_patches = layers.Add()([x4, x2])
    return encoded_patches

def create_vit_classifier(use_token_learner=True, token_learner_units=NUM_TOKENS):
    inputs = layers.Input(shape=INPUT_SHAPE)  # (B, H, W, C)

    # Augment data.
    augmented = data_augmentation(inputs)

    # Create patches and project the pathces.
    projected_patches = layers.Conv2D(
        filters=PROJECTION_DIM,
        kernel_size=(PATCH_SIZE, PATCH_SIZE),
        strides=(PATCH_SIZE, PATCH_SIZE),
        padding="VALID",
    )(augmented)
    _, h, w, c = projected_patches.shape
    projected_patches = layers.Reshape((h * w, c))(
        projected_patches
    )  # (B, number_patches, projection_dim)

    # Add positional embeddings to the projected patches.
    encoded_patches = position_embedding(
        projected_patches
    )  # (B, number_patches, projection_dim)
    encoded_patches = layers.Dropout(0.1)(encoded_patches)

    # Iterate over the number of layers and stack up blocks of
    # Transformer.
    for i in range(NUM_LAYERS):
        # Add a Transformer block.
        encoded_patches = transformer(encoded_patches)

        # Add TokenLearner layer in the middle of the
        # architecture. The paper suggests that anywhere
        # between 1/2 or 3/4 will work well.
        if use_token_learner and i == NUM_LAYERS // 2:
            _, hh, c = encoded_patches.shape
            h = int(math.sqrt(hh))
            encoded_patches = layers.Reshape((h, h, c))(
                encoded_patches
            )  # (B, h, h, projection_dim)
            encoded_patches = token_learner(
                encoded_patches, token_learner_units
            )  # (B, num_tokens, c)

    # Layer normalization and Global average pooling.
    representation = layers.LayerNormalization(epsilon=LAYER_NORM_EPS)(encoded_patches)
    representation = layers.GlobalAvgPool1D()(representation)

    # Classify outputs.
    outputs = layers.Dense(NUM_CLASSES, activation="softmax")(representation)

    # Create the Keras model.
    model = keras.Model(inputs=inputs, outputs=outputs)
    return model

def run_experiment(model):
    # Initialize the AdamW optimizer.
    optimizer = tfa.optimizers.AdamW(
        learning_rate=LEARNING_RATE, weight_decay=WEIGHT_DECAY
    )

    # Compile the model with the optimizer, loss function
    # and the metrics.
    model.compile(
        optimizer=optimizer,
        loss="sparse_categorical_crossentropy",
        metrics=[
            keras.metrics.SparseCategoricalAccuracy(name="accuracy"),
            keras.metrics.SparseTopKCategoricalAccuracy(5, name="top-5-accuracy"),
        ],
    )

    # Define callbacks
    checkpoint_filepath = "/tmp/checkpoint"
    checkpoint_callback = keras.callbacks.ModelCheckpoint(
        checkpoint_filepath,
        monitor="val_accuracy",
        save_best_only=True,
        save_weights_only=True,
    )

    # Train the model.
    _ = model.fit(
        train_ds,
        epochs=EPOCHS,
        validation_data=val_ds,
        callbacks=[checkpoint_callback],
    )

    model.load_weights(checkpoint_filepath)
    _, accuracy, top_5_accuracy = model.evaluate(test_ds)
    print(f"Test accuracy: {round(accuracy * 100, 2)}%")
    print(f"Test top 5 accuracy: {round(top_5_accuracy * 100, 2)}%")

vit_token_learner = create_vit_classifier()
run_experiment(vit_token_learner)