Skip to content

GitLab

Switch branch/tag
  1. 13 Oct, 2020 9 commits
  3. 12 Oct, 2020 2 commits
  5. 09 Oct, 2020 5 commits
  7. 08 Oct, 2020 9 commits
  9. 07 Oct, 2020 4 commits
  11. 06 Oct, 2020 7 commits
    • Dan Anghel's avatar
      Backpropagate global and attention layers together (#9335) · 85f52928
      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
Co-authored-by: default avatarAndre Araujo <andrearaujo@google.com>
      85f52928
    • Abdullah Rashwan's avatar
      Internal change · f97074b0
      Abdullah Rashwan authored 
      PiperOrigin-RevId: 335692122
      f97074b0
    • Chen Chen's avatar
      Fix https://github.com/tensorflow/models/issues/9336 · 92e115a1
      Chen Chen authored 
      to support both model and encoder as key in ckpt when exporting to tfhub

PiperOrigin-RevId: 335668823
      92e115a1
    • A. Unique TensorFlower's avatar
      Update the default arguments for orbit.Controller train_and_evaluate() and... · cf9d4735
      A. Unique TensorFlower authored 
      Update the default arguments for orbit.Controller train_and_evaluate() and evaluate_continuously() to match the default for evaluate().

PiperOrigin-RevId: 335659533
      cf9d4735
    • Hongkun Yu's avatar
      Clean up internal seq2seqTransformer usage. · 662a40be
      Hongkun Yu authored 
      Add it to export. TODO: move the encoder and decoder layer out to layers/ or decoders/.

PiperOrigin-RevId: 335560860
      662a40be
    • Shixin Luo's avatar
      add default config for mobilenet v2 that replicate the expected performance · d68c7b96
      Shixin Luo authored
      d68c7b96
    • Yeqing Li's avatar
      Small changes in video classification task. · e25fe5dd
      Yeqing Li authored 
      PiperOrigin-RevId: 335548133
      e25fe5dd
  13. 05 Oct, 2020 3 commits
  15. 03 Oct, 2020 1 commit