GitLab

PiperOrigin-RevId: 386977208

PiperOrigin-RevId: 386565375

PiperOrigin-RevId: 386344633

PiperOrigin-RevId: 386299254

PiperOrigin-RevId: 386275876

--
d9b85094711b4bcd34400989618b738032c992cf by Srihari Humbarwadi <sriharihumbarwadi97@gmail.com>:

Added dataloader for Panoptic Mask R-CNN (#10112)

* Added `panoptic_maskrcnn_input.Parser`

* Added tests for `panoptic_maskrcnn_input.Parser`

* added `DataConfig`

* fixed doc-string

* Added type annotations

COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/models/pull/10144 from tensorflow:panoptic-segmentation d9b85094711b4bcd34400989618b738032c992cf
PiperOrigin-RevId: 386126918

PiperOrigin-RevId: 386105413

PiperOrigin-RevId: 385652538

PiperOrigin-RevId: 385611054

PiperOrigin-RevId: 385593727

PiperOrigin-RevId: 384509754

PiperOrigin-RevId: 384262412

Fix the issue when both numerator and denominator are 0, the dice score is incorrectly computed as 1, which should be 0.

PiperOrigin-RevId: 384257731

PiperOrigin-RevId: 384257276

PiperOrigin-RevId: 383944185

PiperOrigin-RevId: 383861528

PiperOrigin-RevId: 383856955

PiperOrigin-RevId: 383679175

PiperOrigin-RevId: 383505893

PiperOrigin-RevId: 382833629

Added use_keras_upsampling_2d flags to use keras upsampling layer instead of optimized custom spatial_transform_ops.

PiperOrigin-RevId: 382626602

PiperOrigin-RevId: 382606601

PiperOrigin-RevId: 382561014

PiperOrigin-RevId: 382462213

PiperOrigin-RevId: 382422745

PiperOrigin-RevId: 382408293

PiperOrigin-RevId: 382382393

PiperOrigin-RevId: 382240268

PiperOrigin-RevId: 382051540

PiperOrigin-RevId: 382051212

PiperOrigin-RevId: 381908843

PiperOrigin-RevId: 381516130

PiperOrigin-RevId: 381368435

Add model export config to RetinaNet, which optionally cast model outputs to floats, and normalize output box coordinates.

PiperOrigin-RevId: 381334851

PiperOrigin-RevId: 381089283

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

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

PiperOrigin-RevId: 380907598

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

PiperOrigin-RevId: 380857663