- 14 Jan, 2021 7 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 351890707
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 351798345
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 351758632
-
A. Unique TensorFlower authored
reported in https://github.com/tensorflow/tensorflow/issues/46293. A test case is added to export_tfhub_lib_test. PiperOrigin-RevId: 351741572
-
Abdullah Rashwan authored
PiperOrigin-RevId: 351701695
-
Rajagopal Ananthanarayanan authored
PiperOrigin-RevId: 351691859
-
Ruoxin Sang authored
don't get "while/" as name prefix. PiperOrigin-RevId: 351689649
-
- 13 Jan, 2021 5 commits
-
-
Abdullah Rashwan authored
PiperOrigin-RevId: 351655727
-
Soroosh Yazdani authored
PiperOrigin-RevId: 351619683
-
Sara Beery authored
PiperOrigin-RevId: 351610384
-
Hongkun Yu authored
PiperOrigin-RevId: 351524712
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 351512206
-
- 12 Jan, 2021 7 commits
-
-
Frederick Liu authored
PiperOrigin-RevId: 351435678
-
Frederick Liu authored
PiperOrigin-RevId: 351379789
-
Dan Anghel authored
* Merged commit includes the following changes: 326369548 by Andre Araujo: Fix import issues. -- 326159826 by Andre Araujo: Changed the implementation of the cosine weights from Keras layer to tf.Variable to manually control for L2 normalization. -- 326139082 by Andre Araujo: Support local feature matching using ratio test. To allow for easily choosing which matching type to use, we rename a flag/argument and modify all related files to avoid breakages. Also include a small change when computing nearest neighbors for geometric matching, to parallelize computation, which saves a little bit of time during execution (argument "n_jobs=-1"). -- 326119848 by Andre Araujo: Option to measure DELG latency taking binarization into account. -- 324316608 by Andre Araujo: DELG global features training. -- 323693131 by Andre Araujo: PY3 conversion for delf public lib. -- 321046157 by Andre Araujo: Purely Google refactor -- PiperOrigin-RevId: 326369548 * Added export of delg_model module. * README update to explain training DELG global features head * Added guidelines for DELF hyperparameter values * Fixed typo * Added mention about remaining training flags. * Merged commit includes the following changes: 334723489 by Andre Araujo: Backpropagate global and attention layers together. -- 334228310 by Andre Araujo: Enable scaling of local feature locations to the resized resolution. -- PiperOrigin-RevId: 334723489 * Merged commit includes the following changes: 347032253 by Andre Araujo: Updated local and global_and_local model export scripts for exporting models trained with the autoencoder layer. -- 344312455 by Andre Araujo: Implement autoencoder in training pipeline. -- 341116593 by Andre Araujo: Reduce the default save_interval, to get more frequent checkpoints. -- 341111808 by Andre Araujo: Allow checkpoint restoration in DELF training, to enable resuming of training jobs. -- 340138315 by Andre Araujo: DELF training script: make it always save the last checkpoint. -- 338731551 by Andre Araujo: Add image_size flag in DELF/G OSS training script. -- 338684879 by Andre Araujo: Clean up summaries in DELF/G training script. - Previously, the call to tf.summary.record_if() was not working, which led to summaries being recorded at every step, leading to too large events files. This is fixed. - Previously, some summaries were computed at iteration k, while others at iteration k+1. Now, we standardize summary computations to always run after backpropagation (which means that summaries are reported for step k+1, referring to the batch k). - Added a new summary: number of global steps per second; useful to see how fast training is making progress. Also a few other small modifications are included: - Improved description of the train.py script. - Some small automatic reformattings. -- PiperOrigin-RevId: 347032253 * Updated README for training with autoencoder * DELF README update after first review. Co-authored-by:Andre Araujo <andrearaujo@google.com>
-
Chen Chen authored
PiperOrigin-RevId: 351309008
-
Frederick Liu authored
PiperOrigin-RevId: 351275455
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 351266928
-
Yu-hui Chen authored
FPN network. PiperOrigin-RevId: 351255218
-
- 11 Jan, 2021 2 commits
-
-
Chen Chen authored
Our nightly package will depend on tf-text-nighly and stable release will depend on tf-text stable release. PiperOrigin-RevId: 351216197
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 351104401
-
- 09 Jan, 2021 2 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 350881115
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 350874149
-
- 08 Jan, 2021 6 commits
-
-
Abdullah Rashwan authored
PiperOrigin-RevId: 350850704
-
Yeqing Li authored
PiperOrigin-RevId: 350841628
-
Hongkun Yu authored
Remember the input shapes when build_from_signature is called and trigger the build in from_config. PiperOrigin-RevId: 350795939
-
Hongkun Yu authored
PiperOrigin-RevId: 350705651
-
Hongkun Yu authored
PiperOrigin-RevId: 350687522
-
Rajagopal Ananthanarayanan authored
PiperOrigin-RevId: 350663018
-
- 07 Jan, 2021 3 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 350648045
-
Yu-hui Chen authored
for object detection and keypoint estimation tasks. PiperOrigin-RevId: 350640225
-
Hongkun Yu authored
PiperOrigin-RevId: 350629971
-
- 06 Jan, 2021 3 commits
-
-
Yin Cui authored
PiperOrigin-RevId: 350257408
-
Abdullah Rashwan authored
PiperOrigin-RevId: 350255525
-
Hongkun Yu authored
PiperOrigin-RevId: 350245687
-
- 05 Jan, 2021 5 commits
-
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 350211580
-
A. Unique TensorFlower authored
PiperOrigin-RevId: 350180153
-
Hongkun Yu authored
PiperOrigin-RevId: 350170448
-
Srihari Humbarwadi authored
-
Chen Chen authored
Add an example of training/evaluating squad model using checkpoint from docs/pretrained_models.md for oss in train.md. PiperOrigin-RevId: 350070343
-