- 02 Aug, 2021 2 commits
-
-
Yeqing Li authored
PiperOrigin-RevId: 388322760
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 388320599
-
- 01 Aug, 2021 2 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 388118554
-
Hongkun Yu authored
PiperOrigin-RevId: 388106758
-
- 30 Jul, 2021 2 commits
-
-
Abdullah Rashwan authored
PiperOrigin-RevId: 387878897
-
Jaeyoun Kim authored
-- b9afb6264fafff6df201e88566a411ed9887259d by Srihari Humbarwadi <sriharihumbarwadi97@gmail.com>: Added task definition and configs for Panoptic Mask R-CNN (#10165) * added PanopticMaskRCNNTask config * added tests for config * added Panoptic MaskRCNN task * added tests for Panoptic MaskRCNN task * fixed typo * set default segmentation loss weight to 1.0 * added class docstrings * support `segmentation_decoder` checkpoint * added `init_checkpoint_modules` description * compute `steps_per_epoch` with `train_batch_size` * flattened semantic_segmentation loss attributes COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/models/pull/10168 from tensorflow:panoptic-segmentation b9afb6264fafff6df201e88566a411ed9887259d PiperOrigin-RevId: 387716729
-
- 29 Jul, 2021 3 commits
-
-
Yuexin Wu authored
PiperOrigin-RevId: 387689270
-
Xianzhi Du authored
PiperOrigin-RevId: 387600591
-
Yuexin Wu authored
PiperOrigin-RevId: 387502039
-
- 28 Jul, 2021 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 387447417
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 387434804
-
- 27 Jul, 2021 4 commits
-
-
Xianzhi Du authored
PiperOrigin-RevId: 387177259
-
Frederick Liu authored
PiperOrigin-RevId: 387159154
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 387142853
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 387004613
-
- 26 Jul, 2021 2 commits
-
-
Frederick Liu authored
PiperOrigin-RevId: 386977208
-
Ruoxin Sang authored
Don't early return if the global step is not updated by `num_steps` as expected. This still allows summary and metric reporting. PiperOrigin-RevId: 386967587
-
- 24 Jul, 2021 3 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 386654855
-
Tianqi Liu authored
PiperOrigin-RevId: 386580562
-
Fan Yang authored
PiperOrigin-RevId: 386565375
-
- 23 Jul, 2021 1 commit
-
-
Frederick Liu authored
PiperOrigin-RevId: 386531154
-
- 22 Jul, 2021 5 commits
-
-
Xianzhi Du authored
PiperOrigin-RevId: 386344633
-
Dan Kondratyuk authored
PiperOrigin-RevId: 386299254
-
Xianzhi Du authored
PiperOrigin-RevId: 386275876
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 386140865
-
Jaeyoun Kim authored
-- 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
-
- 21 Jul, 2021 2 commits
-
-
Dan Kondratyuk authored
PiperOrigin-RevId: 386105413
-
Frederick Liu authored
PiperOrigin-RevId: 386029066
-
- 20 Jul, 2021 1 commit
-
-
Fan Yang authored
PiperOrigin-RevId: 385674527
-
- 19 Jul, 2021 7 commits
-
-
Liangzhe Yuan authored
PiperOrigin-RevId: 385652538
-
Vighnesh Birodkar authored
PiperOrigin-RevId: 385646058
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 385629372
-
Hongkun Yu authored
PiperOrigin-RevId: 385615968
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 385611054
-
Liangzhe Yuan authored
PiperOrigin-RevId: 385593727
-
Hongkun Yu authored
Both unit tests and real use cases are passing None to it. PiperOrigin-RevId: 385468558
-
- 17 Jul, 2021 2 commits
-
-
Vighnesh Birodkar authored
PiperOrigin-RevId: 385342213
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 385256430
-
- 16 Jul, 2021 2 commits
-
-
Vighnesh Birodkar authored
PiperOrigin-RevId: 385224486
-
A. Unique TensorFlower authored
Made changes in `center_net_meta_arch.py` for the particular use case in Marky Landmark Detection, i.e. 1. Accessing an access-protected field in the model; 2. Traverse layers to set trainability. PiperOrigin-RevId: 385136419
-