Terms of the offer
Keras is a powerful and easy-to-use library for building and training deep learning models. Learn how to install Keras 3 with different backends, configure your GPU environment, and access the Keras documentation and tutorials. Keras Applications Xception EfficientNet B0 to B7 EfficientNetV2 B0 to B3 and S, M, L ConvNeXt Tiny, Small, Base, Large, XLarge VGG16 and VGG19 ResNet and ResNetV2 MobileNet, MobileNetV2, and MobileNetV3 DenseNet NasNetLarge and NasNetMobile InceptionV3 InceptionResNetV2 Keras 3 is intended to work as a drop-in replacement for tf.keras (when using the TensorFlow backend). Just take your existing tf.keras code, make sure that your calls to model.save() are using the up-to-date .keras format, and you're done. Keras is a deep learning API designed for human beings, not machines. Keras focuses on debugging speed, code elegance & conciseness, maintainability, and deployability.