Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "5513e48ab8aea483f1e332c45af1dfdc0b71968b"
Switch branch/tag
  1. 06 May, 2021 1 commit
  3. 27 Apr, 2021 1 commit
  5. 13 Apr, 2021 1 commit
    • Reed Wanderman-Milne's avatar
      Use nonexperimental mixed precision API. · 19d18c00
      Reed Wanderman-Milne authored 
      This replaces symbols in tf.keras.mixed_precision.experimental with the corresponding nonexperimental symbols. In some cases, passing a Policy is replaced with passing a policy name for conciseness.

Additionally, for the Shakespeare model, the loss_scale flag is removed, since supporting it with the nonexperimental API is slightly more verbose and it is recommended users use the default loss scale.

PiperOrigin-RevId: 368123944
      19d18c00
  7. 25 Mar, 2021 1 commit
  9. 22 Mar, 2021 3 commits
  11. 18 Mar, 2021 1 commit
  13. 11 Mar, 2021 2 commits
  15. 02 Mar, 2021 1 commit
  17. 18 Feb, 2021 1 commit
  19. 02 Feb, 2021 1 commit
  21. 23 Nov, 2020 1 commit
  23. 20 Nov, 2020 1 commit
  25. 07 Nov, 2020 1 commit
  27. 03 Nov, 2020 1 commit
  29. 29 Oct, 2020 1 commit
  31. 21 Aug, 2020 1 commit
  33. 20 Aug, 2020 1 commit
  35. 08 Aug, 2020 1 commit
  37. 07 Aug, 2020 1 commit
  39. 30 Jul, 2020 1 commit
  41. 29 Jul, 2020 2 commits
  43. 23 Jul, 2020 1 commit
  45. 17 Jul, 2020 1 commit
  47. 11 Jul, 2020 2 commits
  49. 10 Jul, 2020 1 commit
    • vivek rathod's avatar
      Merged commit includes the following changes: (#8829) · c9eb3554
      vivek rathod authored 
      

320618558  by rathodv:

    Internal Change.

--
320597532  by ronnyvotel:

    Exposing DensePose visualizations to model_lib_v2.py.

--
320533669  by ronnyvotel:

    Adding utilities to visualize DensePose outputs.

--
320529647  by lzc:

    Fix saved_model issue in object_detection_tutorial notebook.

--
320510127  by aom:

    Internal change.

--
320490236  by derekjchow:

    Update Dockerfiles to use setup.py

--
320443572  by rathodv:

    Update `Tensorflow` to `TensorFlow` in documentation.

--
320426460  by ronnyvotel:

    DensePose proto and model builder.

--
320352611  by rathodv:

    Update documentation to reflect the support for TF1 and TF2. Provide separate sets of instructions to reduce confusion.

--
320350724  by rathodv:

    Internal Change.

--

PiperOrigin-RevId: 320618558
Co-authored-by: default avatarkmindspark <kaushikshiv@google.com>
      c9eb3554
  51. 09 Jul, 2020 1 commit
    • vivek rathod's avatar
      Merged commit includes the following changes: (#8809) · 0ad4922f
      vivek rathod authored 
      

320335495  by rathodv:

    Remove hparams support form TF1 main binaries as its not available in TF1.15 runtime on cloud ai platform.

--
320278161  by ronnyvotel:

    Exposing DensePose fields to model libraries.

--
320277319  by rathodv:

    Remove TPU Name check since TPU is automatically inferred under cloud AI platform.

--
320258215  by rathodv:

    Internal Change.

--
320245458  by yuhuic:

    Updated the CenterNet restore_from_objects function to be compatible with
    existing configs that load converted checkpoints.

--
320225405  by jonathanhuang:

    Small change to Keras box predictor and box heads to fix export errors for SSD and Faster R-CNN.

--
320145077  by aom:

    Implements EfficientDet feature extractor.

--

PiperOrigin-RevId: 320335495
Co-authored-by: default avatarTF Object Detection Team <no-reply@google.com>
      0ad4922f
  53. 01 Jul, 2020 1 commit
  55. 30 Jun, 2020 4 commits
  57. 26 Jun, 2020 3 commits
    • vivek rathod's avatar
      Merged commit includes the following changes: (#8741) · 6ef140dc
      vivek rathod authored 
      318545448  by jonathanhuang:

    Modifies visualization code in TF2 evaluation loop so that we don't write out image summaries to disk for every single image.  This change will reduce summary file sizes by ~2 orders of magnitude on average and speed up evaluation cycles (20 minutes per COCO eval cycle vs 2 hours for RetinaNet).

--
318514741  by sbeery:

    Adding link to the blog post

--

PiperOrigin-RevId: 318545448
      6ef140dc
    • vivek rathod's avatar
      Merged commit includes the following changes: (#8740) · a555f1b0
      vivek rathod authored 
      318497061  by rathodv:

    1. Replace strategy.run() with strategy.experimental_run_v2() and replace tensor.ref() with tensor.experimental_ref() to be compatible with TF2.1 runtime on cloud.
    2. Fix expected string in failing PY3 tests.

--
318493408  by aom:

    Implements "Bidirectional Feature Pyramid Network Generators" for BiFPN-based feature extractors (e.g. EfficientDet).

--

PiperOrigin-RevId: 318497061
      a555f1b0
    • vivek rathod's avatar
      Merged commit includes the following changes: (#8739) · 0f0c7745
      vivek rathod authored 
      318417714  by jonathanhuang:

    Internal change.

--
318367213  by sbeery:

    Pointing users to more documentation for beam

--
318358685  by sbeery:

    Context R-CNN sample config for GPU

--
318309800  by rathodv:

    Internal

--
318303364  by ronnyvotel:

    Adding the option for parsing and including DensePose annotations. http://densepose.org/

--
318291319  by aom:

    Adds conv_bn_act conv_block option, and naming convention changes for BiFPN utils.

--
318200598  by ronnyvotel:

    Updating the TF Example Decoder to parse DensePose annotations.

--
318174065  by jonathanhuang:

    Internal change.

--
318167805  by rathodv:

    Add use_tpu flag to TF2 binary.

--
318145285  by aom:

    Adds option for convolutional keras box predictor to force use_bias.

--

PiperOrigin-RevId: 318417714
      0f0c7745
  59. 25 Jun, 2020 1 commit