Commits · 44cad43aadff9dd12b00d4526830f7ea0796c047 · ModelZoo / ResNet50_tensorflow

30 Jul, 2021 1 commit

Copybara import of the project: · 44cad43a

Jaeyoun Kim authored Jul 29, 2021

--
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

44cad43a

29 Jul, 2021 3 commits
- Internal change · 5f3600b2
  Yuexin Wu authored Jul 29, 2021
```
PiperOrigin-RevId: 387689270
```
  5f3600b2
- Internal change · 2453c4cd
  Xianzhi Du authored Jul 29, 2021
```
PiperOrigin-RevId: 387600591
```
  2453c4cd
- Fix BLEU computation when ratio=0.0 · 03a5f09a
  Yuexin Wu authored Jul 28, 2021
```
PiperOrigin-RevId: 387502039
```
  03a5f09a
28 Jul, 2021 2 commits
- SpectralNormalization: Avoid errors in export by only applying update ops when training=True. · 12856c3b
  A. Unique TensorFlower authored Jul 28, 2021
```
PiperOrigin-RevId: 387447417
```
  12856c3b
- Add options to train a quantization friendly model. · 62487257
  A. Unique TensorFlower authored Jul 28, 2021
```
PiperOrigin-RevId: 387434804
```
  62487257
27 Jul, 2021 4 commits
- Internal change · 697da657
  Xianzhi Du authored Jul 27, 2021
```
PiperOrigin-RevId: 387177259
```
  697da657
- [vision] Add cycxhwyxyx to box ops. · ef74806d
  Frederick Liu authored Jul 27, 2021
```
PiperOrigin-RevId: 387159154
```
  ef74806d
- Internal change · 9465aa0e
  A. Unique TensorFlower authored Jul 27, 2021
```
PiperOrigin-RevId: 387142853
```
  9465aa0e
- Internal change · 2de518be
  A. Unique TensorFlower authored Jul 26, 2021
```
PiperOrigin-RevId: 387004613
```
  2de518be
26 Jul, 2021 2 commits
- [vision] Add yxyxtocxcyhw to box ops. · 4afec6ba
  Frederick Liu authored Jul 26, 2021
```
PiperOrigin-RevId: 386977208
```
  4afec6ba
- Don't early return if the global step is not updated by `num_steps` as... · b26a5ca6
  Ruoxin Sang authored Jul 26, 2021
```
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
```
  b26a5ca6
24 Jul, 2021 3 commits
- Refactor multitask evaluator: consume a list of tasks and optional dictionary of eval steps. · e3c7e300
  Hongkun Yu authored Jul 24, 2021
```
PiperOrigin-RevId: 386654855
```
  e3c7e300
- Internal change · db07a725
  Tianqi Liu authored Jul 23, 2021
```
PiperOrigin-RevId: 386580562
```
  db07a725
- Make register for decoders so custom decoders can be registered. · 688a92a8
  Fan Yang authored Jul 23, 2021
```
PiperOrigin-RevId: 386565375
```
  688a92a8
23 Jul, 2021 1 commit
- Internal change · f69ef1cd
  Frederick Liu authored Jul 23, 2021
```
PiperOrigin-RevId: 386531154
```
  f69ef1cd
22 Jul, 2021 5 commits

Internal change · 7c2ff1af
Xianzhi Du authored Jul 22, 2021
```
PiperOrigin-RevId: 386344633
```
7c2ff1af
Remove kernel size redefinition. · 7bfd14d1
Dan Kondratyuk authored Jul 22, 2021
```
PiperOrigin-RevId: 386299254
```
7bfd14d1
Internal change · 835b730b
Xianzhi Du authored Jul 22, 2021
```
PiperOrigin-RevId: 386275876
```
835b730b
[NCF] Updating data preprocessing script. · 47db997c
A. Unique TensorFlower authored Jul 21, 2021
```
PiperOrigin-RevId: 386140865
```
47db997c

Copybara import of the project: · 37ec3171

Jaeyoun Kim authored Jul 21, 2021

--
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

37ec3171

21 Jul, 2021 2 commits
- Internal change · 08f9393a
  Dan Kondratyuk authored Jul 21, 2021
```
PiperOrigin-RevId: 386105413
```
  08f9393a
- Internal change · ab4c1d07
  Frederick Liu authored Jul 21, 2021
```
PiperOrigin-RevId: 386029066
```
  ab4c1d07
20 Jul, 2021 1 commit
- Add FLOPs computation into run_experiment. · 4bd2888b
  Fan Yang authored Jul 19, 2021
```
PiperOrigin-RevId: 385674527
```
  4bd2888b
19 Jul, 2021 7 commits
- Internal change · f93bea86
  Liangzhe Yuan authored Jul 19, 2021
```
PiperOrigin-RevId: 385652538
```
  f93bea86
- Add box consistency loss in DeepMAC. · 1cbb7a7d
  Vighnesh Birodkar authored Jul 19, 2021
```
PiperOrigin-RevId: 385646058
```
  1cbb7a7d
- [Ranking] Updating training scripts for ranking model. · 76640072
  A. Unique TensorFlower authored Jul 19, 2021
```
PiperOrigin-RevId: 385629372
```
  76640072
- Remove google-cloud-bigquery · 703688aa
  Hongkun Yu authored Jul 19, 2021
```
PiperOrigin-RevId: 385615968
```
  703688aa
- Remove unused use_normalization variable, and move tf.split into if branch. · 399c7b50
  A. Unique TensorFlower authored Jul 19, 2021
```
PiperOrigin-RevId: 385611054
```
  399c7b50
- Internal changes. · 04c1e39f
  Liangzhe Yuan authored Jul 19, 2021
```
PiperOrigin-RevId: 385593727
```
  04c1e39f
- Fix type annotation for length_normalization_fn, which should be Optional. · 518f0201
  Hongkun Yu authored Jul 18, 2021
```
Both unit tests and real use cases are passing None to it.

PiperOrigin-RevId: 385468558
```
  518f0201
17 Jul, 2021 2 commits
- Explain version pinning in tf2/setup.py · 7ecbac3c
  Vighnesh Birodkar authored Jul 17, 2021
```
PiperOrigin-RevId: 385342213
```
  7ecbac3c
- Internal change · 09a38af1
  A. Unique TensorFlower authored Jul 16, 2021
```
PiperOrigin-RevId: 385256430
```
  09a38af1
16 Jul, 2021 3 commits
- Pin google-cloud-bigquery version. · 078eaaf3
  Vighnesh Birodkar authored Jul 16, 2021
```
PiperOrigin-RevId: 385224486
```
  078eaaf3
- Made changes in `center_net_meta_arch.py` for the particular use case in Marky... · 4fd1790e
  A. Unique TensorFlower authored Jul 16, 2021
```
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
```
  4fd1790e
- Update the instruction to run TF2 object detection models in CAIP · c705089f
  A. Unique TensorFlower authored Jul 15, 2021
```
PiperOrigin-RevId: 385042521
```
  c705089f
15 Jul, 2021 1 commit
- Internal change · d095658a
  Hongkun Yu authored Jul 15, 2021
```
PiperOrigin-RevId: 384957416
```
  d095658a
14 Jul, 2021 1 commit

[ranking] Passing `experimental_prefetch_to_device=False` option for... · 2a185c1f

A. Unique TensorFlower authored Jul 14, 2021

[ranking] Passing `experimental_prefetch_to_device=False` option for distributed dataset of Ranking models.

PiperOrigin-RevId: 384792951

2a185c1f

13 Jul, 2021 2 commits

Release example project. · 0650ea24
Fan Yang authored Jul 13, 2021
```
PiperOrigin-RevId: 384509754
```
0650ea24

Global model training (#9904) · c9967b10

Jekaterina Jaroslavceva authored Jul 13, 2021

* Dataset utilities added.

* Global model definition

* Dataset modules added.

* Dataset modules fix.

* global features model training added

* global features fix

* Test dataset update

* PR fixes

* repo sync

* repo sync

* Syncing 2

* Syncing 2

* Global model definition added

* Global model definition added, synced

* Adding global model dataset related modules

* Global model training

* tensorboard module added

* linting issues fixed

* linting fixes.

* linting fixes.

* Fix for previous PR

* PR fixes

* Minor fixes

* Minor fixes

* Dataset download fix

* Comments fix

* sfm120k fix

* sfm120k fix

* names fix

* Update

* Update

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Fixes

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

* Merge branch 'global_model_training'

# Conflicts:
#	research/delf/delf/python/datasets/generic_dataset.py
#	research/delf/delf/python/datasets/generic_dataset_test.py
#	research/delf/delf/python/datasets/sfm120k/__init__.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k.py
#	research/delf/delf/python/datasets/sfm120k/sfm120k_test.py
#	research/delf/delf/python/datasets/tuples_dataset.py
#	research/delf/delf/python/datasets/tuples_dataset_test.py
#	research/delf/delf/python/training/global_features/__init__.py
#	research/delf/delf/python/training/global_features/train.py
#	research/delf/delf/python/training/model/global_model.py
#	research/delf/delf/python/training/model/global_model_test.py
#	research/delf/delf/python/training/tensorboard_utils.py

c9967b10