Models Versions Save

This release of the Official Models targets TensorFlow 2.16.1 Note that Research/tutorial/sample models have been removed.

Release branch is: https://github.com/tensorflow/models/tree/r2.16.0

This release of the Official Models targets TensorFlow 2.15.0 Note that Research/tutorial/sample models have been removed.

Release branch is: https://github.com/tensorflow/models/tree/r2.15.0

This release of the Official Models targets TensorFlow 2.14.0 Note that Research/tutorial/sample models have been removed.

Release branch is: https://github.com/tensorflow/models/tree/r2.14.2

This release is to avoid breakage in TF officials pip package.

This release of the Official Models targets TensorFlow 2.14.0 Note that Research/tutorial/sample models have been removed.

Release branch is: https://github.com/tensorflow/models/commits/r2.14.1

This release of the Official Models targets TensorFlow 2.14.0 Note that Research/tutorial/sample models have been removed.

Release branch is: https://github.com/tensorflow/models/tree/r2.14.0

This release is to fix dependency conflict with PYyaml versions with latest release of Cython and to avoid breakage in TF models official pip package.

This release fix breakage in TF models official pip package by restricting the PyYAML version to <5.4.0 and uses latest version of Cython.

This release fixes the issue of preemption_watcher which would cause failed cases in TPU environments.

This release of the Official Models targets TensorFlow 2.13.0. Note that Research/tutorial/sample models have been removed.

New features:

1. Checkpoints added for ResNet-(50, 101, 152), SpineNet-(49, 96, 143) and DeepLabV3+.
2. Implementation of Perceiver IO: A General Architecture for Structured Inputs & Outputs.
3. Implementation of Linformer: Self-Attention with Linear Complexity with tasks on long range arena.

Release branch is: https://github.com/tensorflow/models/tree/r2.13.0