- 26 10月, 2020 1 次提交
-
-
由 Elizabeth Kemp 提交于
PiperOrigin-RevId: 339018438
-
- 24 10月, 2020 6 次提交
-
-
由 Abdullah Rashwan 提交于
PiperOrigin-RevId: 338789107
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 338786173
-
由 A. Unique TensorFlower 提交于
Shift all attribute assignments in functional subclass models below the super().__init__ call, and enable setattr tracking on all functional subclasses. PiperOrigin-RevId: 338759531
-
由 Chen Chen 提交于
PiperOrigin-RevId: 338740954
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 338710422
-
由 Liangzhe Yuan 提交于
Fix a bug of slicing boxes in _postprocess_keypoints_for_class_and_image and switch to use python assert in _get_shape. PiperOrigin-RevId: 338693370
-
- 23 10月, 2020 4 次提交
-
-
由 Poorva Potdar 提交于
PiperOrigin-RevId: 338521847
-
由 Jonathan Huang 提交于
PiperOrigin-RevId: 338526646
-
由 Ran Chen 提交于
This fix tensorflow_models/official/nlp/bert/run_pretraining failure with explicit allreduce. PiperOrigin-RevId: 338521478
-
由 Manoj Plakal 提交于
-
- 22 10月, 2020 4 次提交
-
-
由 Zhichao Lu 提交于
PiperOrigin-RevId: 338383183
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 338364871
-
由 Yin Cui 提交于
PiperOrigin-RevId: 338348738
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 338309524
-
- 21 10月, 2020 6 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 338249187
-
由 Vighnesh Birodkar 提交于
PiperOrigin-RevId: 338221628
-
由 Chen Chen 提交于
PiperOrigin-RevId: 338095907
-
由 Abdullah Rashwan 提交于
PiperOrigin-RevId: 338094579
-
由 Yu-hui Chen 提交于
Added few keypoint postprocessing functions to handle the one-class bounding box/keypoint use case such that the model can be converted to tf.lite format and run on CPU/GPU. PiperOrigin-RevId: 338078454
-
由 Yu-hui Chen 提交于
causes different behaviors with NaNs in reduce_min/argmin functions. Replaced the NaN values by Infs in one of the tensor to fix it. PiperOrigin-RevId: 338069303
-
- 20 10月, 2020 5 次提交
-
-
由 Taehee Jeong 提交于
PiperOrigin-RevId: 338066485
-
http://host.robots.ox.ac.uk/pascal/VOC/voc2012/由 Aman Gupta 提交于
Old link (http://host.robots.ox.ac.uk/pascal/VOC/voc2012/) is not available. So need to update the location of the dataset. (#9395)
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 337931726
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 337927475
-
由 Abdullah Rashwan 提交于
PiperOrigin-RevId: 337910656
-
- 18 10月, 2020 1 次提交
-
-
由 Reed Wanderman-Milne 提交于
Soon, AutoCastVariable.dtype will refer to the variable dtype, not the compute dtype. This change stops using AutoCastVariable.dtype. PiperOrigin-RevId: 337670544
-
- 17 10月, 2020 3 次提交
-
-
由 Ruoxin Sang 提交于
PiperOrigin-RevId: 337609198
-
由 Abdullah Rashwan 提交于
PiperOrigin-RevId: 337550702
-
由 Le Hou 提交于
PiperOrigin-RevId: 337540237
-
- 16 10月, 2020 2 次提交
-
-
由 Abdullah Rashwan 提交于
PiperOrigin-RevId: 337456452
-
由 Allen Wang 提交于
PiperOrigin-RevId: 337366497
-
- 15 10月, 2020 4 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 337251846
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 337242735
-
由 Allen Wang 提交于
PiperOrigin-RevId: 337134894
-
由 Jonathan Huang 提交于
PiperOrigin-RevId: 337134017
-
- 14 10月, 2020 4 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 336991213
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 336973004
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 336967249
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 336960641
-