Skip to content

GitLab

Switch branch/tag
  1. 15 Dec, 2020 1 commit
  3. 14 Dec, 2020 7 commits
    • Chen Chen's avatar
      Internal change · 786346f3
      Chen Chen authored 
      PiperOrigin-RevId: 347480509
      786346f3
    • A. Unique TensorFlower's avatar
      Merge pull request #9536 from PurdueCAM2Project:yolo · a167bf93
      A. Unique TensorFlower authored 
      PiperOrigin-RevId: 347467379
      a167bf93
    • Dan Anghel's avatar
      Autoencoder in the DELG model (#9555) · 4b8f7d47
      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
Co-authored-by: default avatarAndre Araujo <andrearaujo@google.com>
      4b8f7d47
    • Chen Chen's avatar
      Add documentation to explain the input_path in QADataConfig. · a58cd931
      Chen Chen authored 
      PiperOrigin-RevId: 347443298
      a58cd931
    • Abdullah Rashwan's avatar
      Internal change · 6446619f
      Abdullah Rashwan authored 
      PiperOrigin-RevId: 347439073
      6446619f
    • Frederick Liu's avatar
      Internal change · eaf8c8c3
      Frederick Liu authored 
      PiperOrigin-RevId: 347389234
      eaf8c8c3
    • Chen Chen's avatar
      Remove the support of old tfhub model that has list as inputs/outputs to reduce code complexity. · a9edf472
      Chen Chen authored 
      The new tfhub with dict as inputs/outputs have been released for a while, and users are expected to use new tfhub models.

PiperOrigin-RevId: 347314892
      a9edf472
  5. 12 Dec, 2020 1 commit
  7. 11 Dec, 2020 5 commits
  9. 10 Dec, 2020 2 commits
  11. 09 Dec, 2020 4 commits
  13. 08 Dec, 2020 4 commits
  15. 07 Dec, 2020 2 commits
  17. 06 Dec, 2020 1 commit
  19. 05 Dec, 2020 2 commits
    • Yeqing Li's avatar
      Internal change · 09157a72
      Yeqing Li authored 
      PiperOrigin-RevId: 345796945
      09157a72
    • Sara Beery's avatar
      Context R-CNN Updates: Added capabilities to use multi-headed or multi-layered... · 30b1c958
      Sara Beery authored 
      Context R-CNN Updates: Added capabilities to use multi-headed or multi-layered attention, to place the attention heads pre- or post-second stage feature extraction, and to work with embedded features in the context feature back from pre- or post-second stage feature extraction. Added an option for RPN feature map crops to be piped through to model outputs.

PiperOrigin-RevId: 345777219
      30b1c958
  21. 04 Dec, 2020 10 commits
  23. 03 Dec, 2020 1 commit
    • Sara Beery's avatar
      Updating Context R-CNN dataset tools to fix a bug in context feature bank... · 101282ad
      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
      101282ad