» Developer guides
Developer guides
Our developer guides are deep-dives into specific topics such as layer subclassing, fine-tuning, or model saving. They're one of the best ways to become a Keras expert.
Most of our guides are written as Jupyter notebooks and can be run in one click in Google Colab, a hosted notebook environment that requires no setup and runs in the cloud. Google Colab includes GPU and TPU runtimes.
Available guides
- The Functional API
- The Sequential model
- Making new layers & models via subclassing
- Training & evaluation with the built-in methods
- Customizing what happens in
fit() - Writing a training loop from scratch
- Serialization & saving
- Writing your own callbacks
- Working with preprocessing layers
- Working with recurrent neural networks
- Understanding masking & padding
- Multi-GPU & distributed training
- Transfer learning & fine-tuning
Hyperparameter Tuning
- Getting started with KerasTuner
- Distributed hyperparameter tuning with KerasTuner
- Tune hyperparameters in your custom training loop
- Visualize the hyperparameter tuning process
- Tailor the search space
KerasCV
- CutMix, MixUp, and RandAugment image augmentation with KerasCV
- Train an Object Detection Model on Pascal VOC 2007 using KerasCV
- High-performance image generation using Stable Diffusion in KerasCV
- Custom Image Augmentations with BaseImageAugmentationLayer