Commits · e54fcee236a1258302342bd703ee27cbba0c12e3 · ModelZoo / ResNet50_tensorflow

24 Jul, 2020 10 commits
- Internal change · e54fcee2
  Ruoxin Sang authored Jul 24, 2020
```
PiperOrigin-RevId: 323098007
```
  e54fcee2
- Fix CenterNetMaskTargetAssigner for images with no annotations. · a78b05b9
  Vighnesh Birodkar authored Jul 24, 2020
```
PiperOrigin-RevId: 323059388
```
  a78b05b9
- Update centernet checkpoint in model zoo. · da23acba
  Zhichao Lu authored Jul 24, 2020
```
PiperOrigin-RevId: 323023127
```
  da23acba
- Internal change · 2e96fbee
  Allen Wang authored Jul 24, 2020
```
PiperOrigin-RevId: 323016002
```
  2e96fbee
- Change the dataset_transform_fn argument in InputReader's constructor to transform_and_batch_fn. · 2659ca30
  Chen Chen authored Jul 24, 2020
```
PiperOrigin-RevId: 323013252
```
  2659ca30
- Better error message when loading a wrong checkpoint type in CenterNet. · 07484704
  Vighnesh Birodkar authored Jul 24, 2020
```
PiperOrigin-RevId: 322967458
```
  07484704
- Fix typo. · bdaa525b
  Hongkun Yu authored Jul 24, 2020
```
PiperOrigin-RevId: 322960082
```
  bdaa525b
- Internal change · 58a0c81c
  Ruoxin Sang authored Jul 23, 2020
```
PiperOrigin-RevId: 322937598
```
  58a0c81c
- Internal change · ce93cb75
  A. Unique TensorFlower authored Jul 23, 2020
```
PiperOrigin-RevId: 322923416
```
  ce93cb75
- Update deeplab quantized instructions (#8955) · acb34644
  Yukun Zhu authored Jul 23, 2020
```
* Create convert_to_tflite.py

Script to convert quantized deeplab models to tflite

* Update quantize.md
```
  acb34644
23 Jul, 2020 12 commits
- Internal change · b91a9481
  Allen Wang authored Jul 23, 2020
```
PiperOrigin-RevId: 322884473
```
  b91a9481
- Internal change · a829e648
  A. Unique TensorFlower authored Jul 23, 2020
```
PiperOrigin-RevId: 322844988
```
  a829e648
- Add options in TF2 launch script for summaries and checkpoints. · ee3bfa1e
  Vighnesh Birodkar authored Jul 23, 2020
```
PiperOrigin-RevId: 322828673
```
  ee3bfa1e
- Merge pull request #8749 from kmindspark:context_tf2 · 2ae9c3a6
  TF Object Detection Team authored Jul 23, 2020
```
PiperOrigin-RevId: 322801804
```
  2ae9c3a6
- finalize context rcnn tf2 · b4aa41f5
  Kaushik Shivakumar authored Jul 23, 2020
  
  b4aa41f5
- finalize context rcnn tf2 · eef0a1e7
  Kaushik Shivakumar authored Jul 23, 2020
  
  eef0a1e7
- finalize context rcnn tf2 · 12110e64
  Kaushik Shivakumar authored Jul 23, 2020
  
  12110e64
- Internal change · 5af2c9d4
  A. Unique TensorFlower authored Jul 22, 2020
```
PiperOrigin-RevId: 322713374
```
  5af2c9d4
- finalize tf2 context rcnn · b44de920
  Kaushik Shivakumar authored Jul 23, 2020
  
  b44de920
- make modifications · f72dfa8d
  Kaushik Shivakumar authored Jul 23, 2020
  
  f72dfa8d
- finalize context rcnn tf2 support · 8b6a4628
  Kaushik Shivakumar authored Jul 23, 2020
  
  8b6a4628
- Internal change · ea646b04
  A. Unique TensorFlower authored Jul 22, 2020
```
PiperOrigin-RevId: 322707701
```
  ea646b04
22 Jul, 2020 7 commits
- Internal change · 7fcd7cba
  Allen Wang authored Jul 22, 2020
```
PiperOrigin-RevId: 322657835
```
  7fcd7cba
- Allow export only path takes the hub module. · acaef198
  Hongkun Yu authored Jul 22, 2020
```
PiperOrigin-RevId: 322594580
```
  acaef198
- finalize context RCNN changes for tensorflow 2.x · 6d39f5e6
  Kaushik Shivakumar authored Jul 22, 2020
  
  6d39f5e6
- Merge remote-tracking branch 'upstream/master' into context_tf2 · afd5579f
  Kaushik Shivakumar authored Jul 22, 2020
  
  afd5579f
- remove protos · dcd96e02
  Kaushik Shivakumar authored Jul 22, 2020
  
  dcd96e02
- Context RCNN support for Tensorflow 2.x · aabe1231
  Kaushik Shivakumar authored Jul 22, 2020
  
  aabe1231
- Explicit set the dtype in embedding layer. Otherwise, using the layer in TF1.x... · 567bd18d
  A. Unique TensorFlower authored Jul 21, 2020
```
Explicit set the dtype in embedding layer. Otherwise, using the layer in TF1.x will create an int32 tensor.

PiperOrigin-RevId: 322473236
```
  567bd18d
21 Jul, 2020 6 commits
- [MultiheadAttention] Apply suggestions from RFC: · 36101ab4
  Hongkun Yu authored Jul 21, 2020
```
(1) call() consume kwargs and implement _build_from_signature (layers added inside init_scope)
(2) make build/call_attention as public.

PiperOrigin-RevId: 322454619
```
  36101ab4
- make fixes · e3f88e11
  Kaushik Shivakumar authored Jul 21, 2020
  
  e3f88e11
- Internal change · 391c9dd6
  A. Unique TensorFlower authored Jul 21, 2020
```
PiperOrigin-RevId: 322428923
```
  391c9dd6
- Fix NCF input pipeline to avoid reading the same file multiple times in one epoch. · 6a2de9bb
  Bruce Fontaine authored Jul 21, 2020
```
PiperOrigin-RevId: 322415899
```
  6a2de9bb
- Remove some comments out-dated. · f97e0231
  Hongkun Yu authored Jul 21, 2020
```
PiperOrigin-RevId: 322387911
```
  f97e0231
- AttentionOCR partial TF2 migration (#8843) · 50fa3eb9
  kyscg authored Jul 21, 2020
```
* update readme according to template

* initial upgrades

* demo_inference updated, need to check tf.flags

* issues with tf.image

* manual checks needed for tf.contrib

* more tf2 updates, need to fix tf.contrib and tf.flags
```
  50fa3eb9
20 Jul, 2020 5 commits

Add in RetinaNet MLIR benchmarks. · f05df686
Allen Wang authored Jul 20, 2020
```
PiperOrigin-RevId: 322244056
```
f05df686
Internal change · 7e3fbeee
Allen Wang authored Jul 20, 2020
```
PiperOrigin-RevId: 322234532
```
7e3fbeee
Merge pull request #8909 from kmindspark:singleframe2 · df103208
TF Object Detection Team authored Jul 20, 2020
```
PiperOrigin-RevId: 322234001
```
df103208

Make hack in official/vision/detection models that enters the backend keras... · 363a36cd

Tomer Kaftan authored Jul 20, 2020

Make hack in official/vision/detection models that enters the backend keras graph stop happening once we enable the Functional API KerasTensors refactoring:

As a workaround hack for the tf op layer conversion being fragile, the detection models have to explicitly enter the Keras backend graph.

When we enable the KerasTensors refactoring of the Functional API internals, the op layer conversion will be much more reliable and this hack will not be necessary. In addition, the hack actually causes the models to break when we enable the refactoring (because it causes tensors to leak out of a graph).

So, this CL changes the existing hack to stop applying once we've enabled the KerasTensors refactoring.

PiperOrigin-RevId: 322229802

363a36cd

Internal change · cdda0906
Allen Wang authored Jul 20, 2020
```
PiperOrigin-RevId: 322216928
```
cdda0906