Keras

Approximate non one to one mapping using mixture density networks.

Construct a powerful object detection pipeline to detect marine animals

Learn about the tradeoffs of reducing losses using `sum()`, and reducing losses using `mean()`.

Overview of a common pitfall Keras users hit when writing subclass models

Overview of the first ever official Keras object detection API.

In this post Luke discusses how Keras users write their code, and how he designs APIs accordingly.

Deep dive into the internals of the Keras model class by writing a custom training loop duplicating the behavior of `keras.Model`.

TensorFlow has limited complex number support. Write the operations yourself to maintain automatic differentiation.