- 15 Dec, 2021 4 commits
-
-
Yeqing Li authored
PiperOrigin-RevId: 416593512
-
Hongkun Yu authored
PiperOrigin-RevId: 416569827
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 416564362
-
Hongkun Yu authored
PiperOrigin-RevId: 416450920
-
- 14 Dec, 2021 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 416322339
-
- 13 Dec, 2021 6 commits
-
-
Liangzhe Yuan authored
PiperOrigin-RevId: 416144744
-
Liangzhe Yuan authored
#movinet Change the flag 'causal = True' by default in tools/convert_3d_2plus1d.py because in most cases the script is used for the stream models. PiperOrigin-RevId: 416144733
-
Liangzhe Yuan authored
PiperOrigin-RevId: 416126695
-
Liangzhe Yuan authored
PiperOrigin-RevId: 416121213
-
Hongkun Yu authored
PiperOrigin-RevId: 416088533
-
Hongkun Yu authored
PiperOrigin-RevId: 416070060
-
- 10 Dec, 2021 1 commit
-
-
Pulkit Sinha authored
PiperOrigin-RevId: 415539696
-
- 09 Dec, 2021 3 commits
-
-
Liangzhe Yuan authored
PiperOrigin-RevId: 415367972
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 415310092
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 415120503
-
- 08 Dec, 2021 1 commit
-
-
Smit Hinsu authored
TPUs don't support dynamic Squeeze as it won't be able to identify the dimensions to remove if the input shape is dynamic. For example, [<=16, 1] could return a vector or scalar result depending on the size of the dynamic dim. PiperOrigin-RevId: 415083667
-
- 07 Dec, 2021 3 commits
-
-
Hongkun Yu authored
PiperOrigin-RevId: 414599442
-
Le Hou authored
PiperOrigin-RevId: 414577439
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 414542003
-
- 06 Dec, 2021 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 414542003
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 414459375
-
- 04 Dec, 2021 4 commits
-
-
Fan Yang authored
PiperOrigin-RevId: 414061675
-
Yeqing Li authored
PiperOrigin-RevId: 414057732
-
SunJong Park authored
-- f544441ff132c14c0d95026181eb12c69b4eac1d by SunJong Park <53969182+ryan0507@users.noreply.github.com>: Assemblenet++ Migration with TF2 (#10288) * Assemblenet++ implementation with TF2 (UCF101 Dataset) * pylint.sh passed * train.py document updated * README.md updated - AssembleNet and AssembleNet++ * YAML and configuration updated - AssembleNet and AssembleNet++ COPYBARA_INTEGRATE_REVIEW=https://github.com/tensorflow/models/pull/10355 from tensorflow:assemblenet f544441ff132c14c0d95026181eb12c69b4eac1d PiperOrigin-RevId: 414047541
-
Fan Yang authored
PiperOrigin-RevId: 414045177
-
- 03 Dec, 2021 10 commits
-
-
Yuexin Wu authored
PiperOrigin-RevId: 414032298
-
Yuexin Wu authored
PiperOrigin-RevId: 414027254
-
Yeqing Li authored
PiperOrigin-RevId: 413981781
-
Yeqing Li authored
PiperOrigin-RevId: 413981781
-
Dinghua Li authored
PiperOrigin-RevId: 413973623
-
Yeqing Li authored
PiperOrigin-RevId: 413972002
-
Yuqi Li authored
PiperOrigin-RevId: 413820673
-
Fan Yang authored
PiperOrigin-RevId: 413811970
-
Zihan Wang authored
-
Khanh LeViet authored
Unfreeze keras version as incorrect version issue was fixed. This also resolved the endless TF ODT API pip install issue. PiperOrigin-RevId: 413804051
-
- 02 Dec, 2021 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 413710486
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 413710486
-
- 01 Dec, 2021 3 commits
-
-
Le Hou authored
PiperOrigin-RevId: 413452708
-
Le Hou authored
PiperOrigin-RevId: 413452708
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 413438617
-