1. 16 Jan, 2021 2 commits
  2. 15 Jan, 2021 4 commits
  3. 14 Jan, 2021 7 commits
  4. 13 Jan, 2021 5 commits
  5. 12 Jan, 2021 7 commits
    • Frederick Liu's avatar
      Add sacrebleu metric as dependency.. · b3b18137
      Frederick Liu authored
      PiperOrigin-RevId: 351435678
      b3b18137
    • Frederick Liu's avatar
      Opensource translation task. · 0fe89de9
      Frederick Liu authored
      PiperOrigin-RevId: 351379789
      0fe89de9
    • Dan Anghel's avatar
      README update for DELF training with autoencoder (#9607) · 04af8d35
      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: default avatarAndre Araujo <andrearaujo@google.com>
      04af8d35
    • Chen Chen's avatar
      Open source text_layers.py · 184fcf84
      Chen Chen authored
      PiperOrigin-RevId: 351309008
      184fcf84
    • Frederick Liu's avatar
      Avoid computing mlm if inputs do not have masked_lm_positions. · 34e3de04
      Frederick Liu authored
      PiperOrigin-RevId: 351275455
      34e3de04
    • A. Unique TensorFlower's avatar
      Internal change · a46b2879
      A. Unique TensorFlower authored
      PiperOrigin-RevId: 351266928
      a46b2879
    • Yu-hui Chen's avatar
      Added the option to build CenterNet MobileNetV2 model with separable convolution in the · a3a379a8
      Yu-hui Chen authored
      FPN network.
      
      PiperOrigin-RevId: 351255218
      a3a379a8
  6. 11 Jan, 2021 2 commits
  7. 09 Jan, 2021 2 commits
  8. 08 Jan, 2021 6 commits
  9. 07 Jan, 2021 3 commits
  10. 06 Jan, 2021 2 commits