Also known as: Layers API (tf.layers) Β· tf.layers Β· Layers API tf.layers
The Layers API, or tf.layers, was a TensorFlow interface for constructing neural network layers. It provided building blocks for defining model architectures, although newer TensorFlow workflows commonly use Keras APIs instead.
A TensorFlow API for constructing a deep neural network as a composition of layers. The Layers API lets you build different types of layers, such as: - for a fully-connected layer. - for a convolutional layer. The Layers API follows the Keras layers API conventions. That is, aside from a different prefix, all functions in the Layers API have the same names and signatures as their counterparts in the Keras layers API.