tensorflow / model-optimization

1 Release published by 1 person

• 0.5.0 TensorFlow Model Optimization 0.5.0

  published Sep 14, 2020

5 Pull requests merged by 1 person

• Adjust books to account for changed to the tensorflow_docs api_generator.

  #545 merged Sep 15, 2020

• Update RELEASE.md with proper release notes

  #543 merged Sep 14, 2020

• Bump version to 0.5.0 for new release.

  #537 merged Sep 14, 2020

• Update colabs to follow TF docs nbfmt formatting (https://www.tensorflow.org/community/contribute/docs#notebook_formatting). And reference formatting in CONTRIBUTORS doc.

  #540 merged Sep 11, 2020

• Add missing copyright blurb

  #536 merged Sep 11, 2020

3 Pull requests opened by 3 people

• [Clustering] Simplification of clustering registry.

  #539 opened Sep 11, 2020

• Fix _weight_name() for layers with multiple '/'

  #544 opened Sep 15, 2020

• Replace existing tf.distribute.experimental.ParameterServerStrategy usage with tf.compat.v1.distribute.experimental.ParameterServerStrategy to prepare for the upcoming TF2 ParameterServerStrategy API release.

  #547 opened Sep 17, 2020

1 Issue closed by 1 person

• Is Sigmoid activation currently supported ?

  #534 closed Sep 15, 2020

3 Issues opened by 3 people

• quantization.keras.quantize_model function runtime error with mobilenet v3

  #546 opened Sep 15, 2020

• Support for block sparse matrices

  #542 opened Sep 13, 2020

• Structured pruning (filter pruning)

  #541 opened Sep 12, 2020

5 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Add support for tf.distribute after enabling the update of cluster indices

  #531 commented on Sep 17, 2020 • 5 new comments

• Support for Conv1D Quantization

  #362 commented on Sep 14, 2020 • 2 new comments

• Quantization-Aware-Training with Sparsity and Clustering Preservation

  #513 commented on Sep 16, 2020 • 2 new comments

• sparsity.prune_low_magnitude fails with mixed precision policy mixed_float16

  #409 commented on Sep 11, 2020 • 1 new comment

• Enable differentiable training and update cluster indices

  #519 commented on Sep 17, 2020 • 1 new comment