GitLab

In nlp/train.py and vision/beta/train.py, certain flags are marked as required. Additionally, in certain functions, error messages are improved if a necessary flag is not specified, which is a fallback in case a file calling define_flags() does not mark the necessary flags are required. Previously if any of these flags were not specified, it would crash with a cryptic error message, making it hard to tell what went wrong.

In a subsequent change, I will mark flags as required in more files which call define_flags().

PiperOrigin-RevId: 381066985

Before, it returned None. But almost every use of get_distribution_strategy() assumes an actual strategy is returned and crashes when None is returned. Returning the default strategy fixes these issues and is equivalent to using no strategy, as the default strategy is always in effect when no other strategy is used.

PiperOrigin-RevId: 380951055

Adds a video classification export module for example. The module is subject to change in the near future.

PiperOrigin-RevId: 380907598

PiperOrigin-RevId: 380858205

Some parts of the forward pass would previously overflow in float16. Such parts are now done in float32.

PiperOrigin-RevId: 380857663

PiperOrigin-RevId: 380687139

PiperOrigin-RevId: 380650647

PiperOrigin-RevId: 380470496

PiperOrigin-RevId: 380296477

PiperOrigin-RevId: 380243629

PiperOrigin-RevId: 380237223

PiperOrigin-RevId: 380190962

PiperOrigin-RevId: 379909569

PiperOrigin-RevId: 379898918

PiperOrigin-RevId: 379875442

--
b3be14bc by Srihari Humbarwadi <sriharihumbarwadi97@gmail.com>:

Added `PanopticMaskRCNNModel` model (#10045)

* Added `PanopticMaskRCNNModel` model

* test checkpoint loading for segmentation objects

* fixed docstring

* subclassed `MaskRCNNModel`

* always enable mask and segmentation heads

* added __init__.py

* added README.md
--
35c3a79f by Srihari Humbarwadi <sriharihumbarwadi97@gmail.com>:

fixed linting errors (#10053)

COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/models/pull/10052 from tensorflow:panoptic-segmentation 35c3a79f
PiperOrigin-RevId: 379834961

PiperOrigin-RevId: 379828181

PiperOrigin-RevId: 379817535

PiperOrigin-RevId: 379815593

1) Added the score-to-scaled-distance ranking method.
2) Added the gaussian-weighted ranking method.
3) Added the hyperparameter used in the rescoring function.

PiperOrigin-RevId: 379646603

PiperOrigin-RevId: 379618127

--
63719f08

 by Anirudh Vegesana <anirudh.vegesana@gmail.com>:

YOLO Family: Updated model (#9923)

* Update YOLO model

* Fix some docstrings

* Fix docstrings

* Address some of Dr. Davis' changes

* Give descriptive names to the test cases

* Fix bugs

* Fix YOLO head imports

* docstring and variable name updates

* docstring and variable name updates

* docstring and variable name updates
Co-authored-by: vishnubanna <banna3vishnu@gmail.com>
Co-authored-by: Vishnu Banna <43182884+vishnubanna@users.noreply.github.com>
--
725b8c8c

 by Anirudh Vegesana <anirudh.vegesana@gmail.com>:

disclaimer (#10020)
Co-authored-by: Vishnu Banna <43182884+vishnubanna@users.noreply.github.com>
--
404d24b0

 by Anirudh Vegesana <anirudh.vegesana@gmail.com>:

YOLO Family: Linting (#10027)

* YOLO Family: Updated model (#9923)

* Update YOLO model

* Fix some docstrings

* Fix docstrings

* Address some of Dr. Davis' changes

* Give descriptive names to the test cases

* Fix bugs

* Fix YOLO head imports

* docstring and variable name updates

* docstring and variable name updates

* docstring and variable name updates
Co-authored-by: vishnubanna <banna3vishnu@gmail.com>
Co-authored-by: Vishnu Banna <43182884+vishnubanna@users.noreply.github.com>

* disclaimer

* Fix some PyLint errors
Co-authored-by: vishnubanna <banna3vishnu@gmail.com>
Co-authored-by: Vishnu Banna <43182884+vishnubanna@users.noreply.github.com>
COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/models/pull/10021 from tensorflow:purdue-yolo 404d24b0
PiperOrigin-RevId: 379372162

1. Make api_template always use third_party/py/keras (or keras PIP package in OSS).
2. API tests are updated to ignore tensorflow/python/keras end points.
3. All Keras-related code will be removed in a follow up change. Keras-specific APIs are tracked in google3/third_party/py/keras/api/golden/
4. There are a few APIs (optimizer/initializer) that are exposed as both tf and keras APIs. Their pbtxt are updated to reflect the latest class path change.

Once this change is submitted, the current code in tensorflow/python/keras will become a stale copy, and will be removed soon. No more changes should be made to tensorflow/python/keras.

PiperOrigin-RevId: 379353790

PiperOrigin-RevId: 379338309

PiperOrigin-RevId: 379108917

PiperOrigin-RevId: 378977617

PiperOrigin-RevId: 378923791

PiperOrigin-RevId: 378911698

PiperOrigin-RevId: 378899878

PiperOrigin-RevId: 378869744

PiperOrigin-RevId: 378853085

PiperOrigin-RevId: 378751789

378492389  by Andre Araujo:

    Internal change

--
369671840  by Andre Araujo:

    Cleanup after recent PRs in DELF github repo.

--
360692342  by Andre Araujo:

    Replace direct TF app import with absl::app.
    (1) TF::app is deprecated
    (2) direct TF import is discouraged. go/gpylint-faq#g-direct-tensorflow-import

--
359157762  by Andre Araujo:

    Internal change

--

PiperOrigin-RevId: 378492389
Co-authored-by: Andre Araujo <andrearaujo@google.com>

PiperOrigin-RevId: 378423112

* Fix attention application in DELG

* Adding DELG unit tests

* Formatting for review

* Formatting for review

* Formatting for review

PiperOrigin-RevId: 378339245

Add notebook and update ODT TFLite conversion doc to show how to make the model compatible with TFLite Task Library.

PiperOrigin-RevId: 378313314

The original Colab by malcolmslaney didn't work with the current VGGish/tensorflow.  Changed the link to an updated version.

PiperOrigin-RevId: 378190887

region for the keypoint heatmap if the instance's keypoint visibility is 0.

PiperOrigin-RevId: 378183175