Release 2.9.1

Release 2.9.1 is a maintenance release that only updates documentation.

This release requires TensorFlow 2.9 and TensorFlow Probability 0.15.

If you're on Linux or Darwin (Mac OS) and Python 3.7–3.10, install the pre-compiled binary by running:

pip install tensorflow-compression==2.9.1

Release 2.9.0

Release 2.9.0 adds a new PowerLawEntropyModel class to be used as a rate penalty for the run-length gamma coding ops.

This release requires TensorFlow 2.9 and TensorFlow Probability 0.15.

If you're on Linux or Darwin (Mac OS) and Python 3.7–3.10, install the pre-compiled binary by running:

pip install tensorflow-compression==2.9.0

Release 2.8.1

Release 2.8.1 fixes a bug in mixed precision training, and adds a new entropy coding op that relies on Elias gamma and run-length coding.

This release requires TensorFlow 2.8 and TensorFlow Probability 0.15.

If you're on Linux or Darwin (Mac OS) and Python 3.7–3.10, install the pre-compiled binary by running:

pip install tensorflow-compression==2.8.1

Release 2.8.0

Release 2.8.0 adds support for mixed precision training (for details, see commit c20abdb).

This release requires TensorFlow 2.8 and TensorFlow Probability 0.15.

If you're on Linux or Darwin (Mac OS) and Python 3.7–3.10, install the pre-compiled binary by running:

pip install tensorflow-compression==2.8.0

Release 2.7.0

Release 2.7.0 is the first release using a new automated build system, which streamlines the process of building pip packages.

As part of that, we are also synchronizing the versioning of TFC with TensorFlow, so that it is clearer which TF package needs to be installed (TFC version x.y.z now requires TF version x.y.*).

The main technical updates to this release include:

• Commit 61e7977 introduces a new, more general range coder op. This is now used throughout the library. The old ops are still contained in the library, so that older pre-trained models can be run, but all development going forward should use the new implementation.
• Commits edb8df5 and 49fe704 revise the handling of quantization offsets, and refactor the entropy model classes in the process. This removes quite a bit of complexity, and possibly solves improper handling of some edge cases.

This release requires TensorFlow 2.7 and TensorFlow Probability 0.15.

If you're on Linux or Darwin (Mac OS) and Python 3.7–3.9, install the pre-compiled binary by running:

pip install tensorflow-compression==2.7.0

Release 2.2

Release 2.2 introduces a new tf.Dataset that can read YUV4MPEG (.y4m) files, adds support for stateless entropy models, reimplements RDFT kernel parameterization using tf.signal, and adds support for Python 3.9.

This release requires TensorFlow 2.5 and a compatible version of TensorFlow Probability.

If you're on Linux or Darwin (Mac OS) and Python 3.6–3.9, install the pre-compiled binary by running:

pip install tensorflow-compression==2.2

Release 2.1

Release 2.1 supports TensorFlow 2, eager mode, and a redesigned and more flexible implementation of the entropy models.

This release requires a development version of TensorFlow 2.5 (tf-nightly==2.5.0.dev*) and a compatible version of TensorFlow Probability. It replaces release 2.0, which was found to have incompatibilities with TF 2.4.

If you're on Linux or Darwin (Mac OS) and Python 3.6–3.8, install the pre-compiled binary by running:

pip install tf-nightly==2.5.0.dev20210312 tensorflow-compression==2.1

Release 2.0

Release 2.0 was meant to support TensorFlow 2, eager mode, and a redesigned and more flexible implementation of the entropy models.

This release requires TensorFlow 2.4 and a compatible version of TensorFlow Probability.

Due to incompatibilities between TFC and the TF 2.4 release (issue #71), we don't recommend using this release. It was replaced by 2.1.

Beta 2 for release 2.0

Release 2.0 will support TensorFlow 2, eager mode, and a redesigned and more flexible implementation of the entropy models.

This release requires TensorFlow 2.4 and a compatible version of TensorFlow Probability.

If you're on Linux or Darwin (Mac OS) and Python 3.6–3.8, install the pre-compiled binary by running:

pip install tensorflow-compression==2.0b2

This is a pre-release. Please note that the code may fail in unexpected ways.

Outstanding issues to be resolved for 2.0:

• Adjustments in the interface of the new entropy model classes may still happen until the final release.
• Not all example models in the models/ directory have been ported to the new code yet.

Beta 1 for release 2.0

Release 2.0 will support TensorFlow 2, eager mode, and a redesigned and more flexible implementation of the entropy models.

This release requires TensorFlow 2.3 and a compatible version of TensorFlow Probability.

If you're on Linux or Darwin (Mac OS) and Python 3.6–3.8, install the pre-compiled binary by running:

pip install tensorflow-compression==2.0b1

This is a pre-release. Please note that the code may fail in unexpected ways.

Outstanding issues to be resolved for 2.0:

• Adjustments in the interface of the new entropy model classes may still happen until the final release.
• Example models in the models/ directory have not been ported to the new code yet.