Skip to content

v0.97

Compare
Choose a tag to compare
@bvanessen bvanessen released this 12 Feb 01:29
· 3128 commits to develop since this release

============================== Release Notes: v0.97 ==============================

Support for new layers:

  • Mean absolute error and L1 norm
  • GPU implementation for activation layers
  • Log sigmoid and softsign
  • Channel-wise mean (temporary kludge)

Model portability & usability:

  • Hints for layer output dimensions
  • Confusion matrix callback
  • Metric checking callback

Internal features:

  • Removed target-layer-based features from model zoo
  • Layer unit tests check for expected output values

Retired features:

  • Smooth ReLU, bent identity, and swish layers
  • Target-layer-based metrics
  • Target-layer-based models (sequential, greedy layer-wise autoencoder, Siamese)