- 04 Dec, 2020 7 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345712582
-
Sara Beery authored
DEFAULT_VALUE_OK=setting prefetch batches default to 2 as using -1 can cause memory issues for some models such as context r-cnn that use sequence examples. PiperOrigin-RevId: 345682268
-
Vighnesh Birodkar authored
PiperOrigin-RevId: 345620862
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345606908
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345588520
-
Yoni Ben-Meshulam authored
PiperOrigin-RevId: 345586686
-
Yoni Ben-Meshulam authored
PiperOrigin-RevId: 345586199
-
- 03 Dec, 2020 6 commits
-
-
Sara Beery authored
Updating Context R-CNN dataset tools to fix a bug in context feature bank building logic when the number of context examples in the time horizon is greater than the specified maximum, and adding capabilities to track and save the number of embeddings stored per image. PiperOrigin-RevId: 345548385
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345529749
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345500920
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345493076
-
Yu-hui Chen authored
added a new operating mode for single-instance prediction. 1) Refactored the _postprocess_keypoints_for_class_and_image function such that it can be reused by single/multi class keypoint tasks. 2) Removed the "mod" operator to make the model compatible with WASM. PiperOrigin-RevId: 345468250
-
Hongkun Yu authored
PiperOrigin-RevId: 345383199
-
- 02 Dec, 2020 3 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345267761
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 345261173
-
pyoung2778 authored
-
- 01 Dec, 2020 3 commits
-
-
Vivek Rathod authored
Avoid explicit tf.unstack in `convert_strided_predictions_to_normalized_boxes`. This enables exporting a saved model with dynamic batch size. PiperOrigin-RevId: 345055072
-
Hongkun Yu authored
PiperOrigin-RevId: 345054031
-
Hongkun Yu authored
PiperOrigin-RevId: 344926166
-
- 30 Nov, 2020 5 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 344869679
-
Hongkun Yu authored
PiperOrigin-RevId: 344845702
-
Chen Chen authored
PiperOrigin-RevId: 344836089
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 344826362
-
Zhichao Lu authored
PiperOrigin-RevId: 344743049
-
- 27 Nov, 2020 1 commit
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 344465468
-
- 26 Nov, 2020 3 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 344355705
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 344335367
-
prabhukaliamoorthi authored
-
- 25 Nov, 2020 5 commits
-
-
Jonathan Huang authored
PiperOrigin-RevId: 344310944
-
Poorva Potdar authored
PiperOrigin-RevId: 344294492
-
Hongkun Yu authored
PiperOrigin-RevId: 344194437
-
Chen Chen authored
PiperOrigin-RevId: 344192444
-
Chen Chen authored
PiperOrigin-RevId: 344190250
-
- 24 Nov, 2020 4 commits
-
-
A. Unique TensorFlower authored
Fix the score_converter issue, which should apply on the dimension of num_class_slots per anchor separately, not on all anchors per location together (e.g. think of softmax). PiperOrigin-RevId: 344143469
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 344134923
-
Poorva Potdar authored
PiperOrigin-RevId: 344068616
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 343970720
-
- 23 Nov, 2020 3 commits
-
-
Pankaj Kanwar authored
PiperOrigin-RevId: 343920343
-
Allen Wang authored
PiperOrigin-RevId: 343893692
-
Abdullah Rashwan authored
PiperOrigin-RevId: 343888044
-