1. 18 Aug, 2020 8 commits
    • Jaeyoun Kim's avatar
      Update README.md · a54f7d00
      Jaeyoun Kim authored
      Change TF badges
      a54f7d00
    • A. Unique TensorFlower's avatar
      Internal change · 3a972c26
      A. Unique TensorFlower authored
      PiperOrigin-RevId: 327248242
      3a972c26
    • Dan Anghel's avatar
      README update for DELG training (#9112) · c4e7d734
      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
      Co-authored-by: default avatarAndre Araujo <andrearaujo@google.com>
      c4e7d734
    • Hongkun Yu's avatar
      Rename tagging_data_loader to tagging_dataloader for consistent naming. · 8cbb5924
      Hongkun Yu authored
      PiperOrigin-RevId: 327179271
      8cbb5924
    • A. Unique TensorFlower's avatar
      Minor change in EncoderScaffold · 1b5b2fe4
      A. Unique TensorFlower authored
      PiperOrigin-RevId: 327160430
      1b5b2fe4
    • A. Unique TensorFlower's avatar
      Internal change · 55b5100e
      A. Unique TensorFlower authored
      PiperOrigin-RevId: 327149314
      55b5100e
    • Hongkun Yu's avatar
      Fix unit test model config, we need to use kwargs to make dataclass correct. · 92ea3959
      Hongkun Yu authored
      PiperOrigin-RevId: 327139660
      92ea3959
    • Manoj Plakal's avatar
      Added TF-Lite-compatible feature extractor and model exporter for YAMNet (#9098) · 8da48573
      Manoj Plakal authored
      * Added TF-Lite-compatible feature extractor and model exporter for YAMNet.
      
      - Added a TF-Lite compatible feature extractor. With the latest TF-Lite,
        that involves a DFT-multiplication replacement for tf.abs(tf.signal.stft())
        and not a lot else. Note that TF-Lite now allows variable-length inputs.
      - Added a YAMNet exporter that produces TF2 SavedModels, TF-Lite models,
        and TF-JS models.
      - Cleanups: switched hyperparameters to a dataclass, got rid of
        some lingering cruft in yamnet_test.
      
      * Responded to DAn's comments in https://github.com/tensorflow/models/pull/9098
      
      - Switched some hparams to float
      - Made class map asset available on the exported model, and tested that
        it can be loaded from the various exports.
      8da48573
  2. 17 Aug, 2020 7 commits
  3. 15 Aug, 2020 1 commit
  4. 14 Aug, 2020 16 commits
  5. 13 Aug, 2020 8 commits