GitLab

The order of the input tensors is incorrect and therefore the sample notebook does not run.

The sample code has the order of the input tensors as `boxes, classes, scores, num_detections`, but actually the order should be `scores, boxes,  num_detections, classes`

After correcting the indexes of the input tensor, the sample notebook runs.

This will be the default behavior.

PiperOrigin-RevId: 392643474

PiperOrigin-RevId: 392539450

PiperOrigin-RevId: 392534821

PiperOrigin-RevId: 392499545

Unify DataDecoder from retinanet and maskrcnn and move it into common so it can be used by other tasks. Add DataDecoder as optional field for classification and segmentation DataConfig so overriding with DataDecoder can work for all tasks.

PiperOrigin-RevId: 392493075

PiperOrigin-RevId: 392061572

Add new owners for the video_ssl project

PiperOrigin-RevId: 391807562

Update bike video dataset path.

Add link to TF2 port with build file for compiling the ICP op.

PiperOrigin-RevId: 391678737

PiperOrigin-RevId: 391624504

PiperOrigin-RevId: 391455959

PiperOrigin-RevId: 391390019

PiperOrigin-RevId: 391332984

  * Replaced the deprecated `to_int/to_float` in `center_net_meta_arch.py` with `tf.cast()` (following the warning).
  * Added `max_norm_coord` argument to CenterNet source code to allow controlling the maximum coordinate value to be considered, to allow for the wrap-around special case for RxR data.

PiperOrigin-RevId: 391319766

PiperOrigin-RevId: 391079006

[transformer] Add a flag to return intermediate outputs. This is needed to add auxiliary loss which has been shown helpful in "Character-Level Language Modeling with Deeper Self-Attention" and "End-to-End Object Detection with Transformers"

PiperOrigin-RevId: 390505073

true_image_shape is not required and can be inferred by the prediction tensors.

PiperOrigin-RevId: 390421432

PiperOrigin-RevId: 390387877

PiperOrigin-RevId: 390359654

PiperOrigin-RevId: 390235315

PiperOrigin-RevId: 390202261

PiperOrigin-RevId: 390116640

PiperOrigin-RevId: 390025168

PiperOrigin-RevId: 389999813

PiperOrigin-RevId: 389748939

PiperOrigin-RevId: 389675343

PiperOrigin-RevId: 389672355

PiperOrigin-RevId: 389665560

PiperOrigin-RevId: 389568005

PiperOrigin-RevId: 389526906

PiperOrigin-RevId: 389310818

PiperOrigin-RevId: 389101303

PiperOrigin-RevId: 389069223

PiperOrigin-RevId: 389033478

PiperOrigin-RevId: 389025611

PiperOrigin-RevId: 389019529

PiperOrigin-RevId: 388951823

PiperOrigin-RevId: 388865163