TensorFlow 2.0 Beta is available Learn more

Research and experimentation

Eager execution provides an imperative, define-by-run interface for advanced operations. Write custom layers, forward passes, and training loops with auto differentiation. Start with these notebooks, then read the eager execution guide.

  1. Tensors and operations
  2. Custom layers
  3. Automatic differentiation
  4. Custom training: basics
  5. Custom training: walkthrough
  6. TF function and AutoGraph