“33dca040b7c72c5bce52faa6c6e6594fd4b10cf9”上不存在“dataset/mot/image_lists/prw.train”
- 19 1月, 2022 2 次提交
-
-
由 Le Hou 提交于
PiperOrigin-RevId: 422638136
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 422612138
-
- 09 12月, 2021 1 次提交
-
-
由 Smit Hinsu 提交于
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
-
- 18 11月, 2021 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 410629444
-
- 13 4月, 2021 1 次提交
-
-
由 Reed Wanderman-Milne 提交于
For all modified calls to set_mixed_precision_policy(), the loss_scale argument was removed, as it cannot be passed if the nonexperimental API is used. For all such callers, the loss_scale is later used to explicitly create a LossScaleOptimizer, so removing the argument has no impact. Switching to the non-experimental LossScaleOptimizer has no effect, as it has near identical behavior and all isinstance checks within the official models check for the non-experimental version. PiperOrigin-RevId: 368101975
-
- 10 3月, 2021 1 次提交
-
-
由 Frederick Liu 提交于
PiperOrigin-RevId: 361957289
-
- 15 12月, 2020 1 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 347505505
-
- 16 11月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 342566888
-
- 14 11月, 2020 1 次提交
-
-
由 Reed Wanderman-Milne 提交于
PiperOrigin-RevId: 342390260
-
- 27 10月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 339071563
-
- 30 9月, 2020 1 次提交
-
-
由 Chenkai Kuang 提交于
PiperOrigin-RevId: 334517779
-
- 13 9月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 331359058
-
- 22 8月, 2020 2 次提交
-
-
由 Maxim Neumann 提交于
PiperOrigin-RevId: 327838493
-
由 Maxim Neumann 提交于
PiperOrigin-RevId: 327838493
-
- 15 8月, 2020 1 次提交
-
-
由 Kevin 提交于
-
- 13 8月, 2020 2 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 326286926
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 326286926
-
- 07 8月, 2020 1 次提交
-
-
由 Kevin 提交于
-
- 23 7月, 2020 2 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 322594580
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 322594580
-
- 13 6月, 2020 1 次提交
-
-
由 Maxim Neumann 提交于
PiperOrigin-RevId: 316134518
-
- 12 6月, 2020 1 次提交
-
-
由 Maxim Neumann 提交于
Replace as well the regression loss with Keras loss object. PiperOrigin-RevId: 316062800
-
- 05 6月, 2020 1 次提交
-
-
由 Tianqi Liu 提交于
PiperOrigin-RevId: 314822016
-
- 04 6月, 2020 1 次提交
-
-
由 Maxim Neumann 提交于
PiperOrigin-RevId: 314607393
-
- 29 5月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
Deprecate old customized training loop for run_classifier.py as compile/fit fully satisfy needs/performance. PiperOrigin-RevId: 313660745
-
- 26 5月, 2020 1 次提交
-
-
由 André Susano Pinto 提交于
This allows one to finetune a BERT model into a task before using it for another task. E.g. SQuAD before finetune another QA type of tasks. PiperOrigin-RevId: 313145768
-
- 24 5月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 312923051
-
- 20 5月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
Remove is_v2_0 PiperOrigin-RevId: 312336907
-
- 19 5月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 312096778
-
- 05 5月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
Move gin flags to hyperparams_flags are they are in the same category and we will use them more widely. PiperOrigin-RevId: 309779408
-
- 22 4月, 2020 1 次提交
-
-
由 Le Hou 提交于
PiperOrigin-RevId: 307712303
-
- 21 4月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 307416709
-
- 17 4月, 2020 2 次提交
-
-
由 Chen Chen 提交于
PiperOrigin-RevId: 306986791
-
由 Jeremiah Harmsen 提交于
Thread custom callbacks through BERT classifier. This allows injection of custom callbacks for library users of run_classifier. PiperOrigin-RevId: 306966758
-
- 16 4月, 2020 1 次提交
-
-
由 Le Hou 提交于
PiperOrigin-RevId: 306664983
-
- 11 4月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 305948522
-
- 28 3月, 2020 1 次提交
-
-
由 A. Unique TensorFlower 提交于
PiperOrigin-RevId: 303356961
-
- 26 3月, 2020 2 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 303050809
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 302977474
-
- 18 3月, 2020 1 次提交
-
-
由 Hongkun Yu 提交于
PiperOrigin-RevId: 301441181
-