GitLab

duplicate eval metric: change the fourth metric from ## Weighted PASCAL VOC detection metric to ##  Weighted PASCAL VOC instance segmentation metric .

Squashed commit of the following:

commit 5a6887b50ce35df0c62fe6a1d4dddf89296b58af
Author: Ilya Mironov <mironov@google.com>
Date:   Tue Apr 3 13:21:32 2018 -0700

    Renaming pate2_paper to ICLR2018. Adding mironov@google.com to README.md.

commit 666ac8800a68a965508dec4c148134723f5d2725
Author: Ilya Mironov <mironov@google.com>
Date:   Tue Apr 3 13:16:54 2018 -0700

    Moving everything under research/differential_privacy/pate

commit 1810be3e31279391b5f339c29c4e25d631409736
Author: Ilya Mironov <mironov@google.com>
Date:   Mon Apr 2 15:18:49 2018 -0700

    Addressing Ananth's comments:
     - added link to https://github.com/abseil/abseil-py
     - added "pip install absl-py"
     - fixed import statement in core_test.py

    Added requirement of write access.

commit e2f7e01462815bdd957952769edfea8f94407ce6
Author: Ilya Mironov <mironov@google.com>
Date:   Mon Apr 2 12:32:27 2018 -0700

    Overview section of README.md is revised.

commit 692680868cb1a691ff09f2bce194298603c80467
Author: Ilya Mironov <mironov@google.com>
Date:   Mon Apr 2 11:55:53 2018 -0700

    Massive restructuring:
    - Files renamed from pate.py to core.py, pate_smooth_sensitivity to smooth_sensitivity.py.
    - Absolute references changed to relative.
    - BUILDs removed.
    - README.md amended.

commit b2dc2246c50a51a6eb455c6736d351387bad4e31
Author: Ilya Mironov <mironov@gmail.com>
Date:   Fri Mar 30 10:10:51 2018 -0700

    Editing README files.

commit 4762823e1ca58d2b7a4e28d7bda191aff137a245
Author: Ilya Mironov <mironov@gmail.com>
Date:   Thu Mar 29 22:07:25 2018 -0700

    Adding download.py file.

commit e488d1a4a9e066fa83fa948cb5b71fe134a73c12
Author: Ilya Mironov <mironov@google.com>
Date:   Thu Mar 29 21:44:43 2018 -0700

    Adding the copyright statement.

commit 5b5759c9399914731340031bc668e69bc2c83d48
Author: Ilya Mironov <mironov@google.com>
Date:   Thu Mar 29 19:07:01 2018 -0700

    Moving everything under research/

commit 50ff075ce1e14700328ebc4f42ee418d7a7874f5
Author: Ilya Mironov <mironov@google.com>
Date:   Thu Mar 29 18:56:20 2018 -0700

    Initial commit

PiperOrigin-RevId: 191377056

PiperOrigin-RevId: 191369912

PiperOrigin-RevId: 191358138

PiperOrigin-RevId: 191342074

- Fix externally broken test input_test.py
- Add Cython to object detection REQUIRED_PACKAGES

PiperOrigin-RevId: 191338837

PiperOrigin-RevId: 191248237

PiperOrigin-RevId: 191112757

PiperOrigin-RevId: 191014662

PiperOrigin-RevId: 190996725

PiperOrigin-RevId: 190972737

Updating model to infer when labels are padded, rather than relying solely on the mode. This is necessary for evaluating on train data.

PiperOrigin-RevId: 190960173

Use keyword arguments in model builder for ssd feature extractor. This was incorreclty setting reuse argument.

PiperOrigin-RevId: 190940462

PiperOrigin-RevId: 190790653

Removing flag defaults for train steps and eval steps. If not provided, will revert to the values specified in the config.

PiperOrigin-RevId: 190706470

PiperOrigin-RevId: 190705850

PiperOrigin-RevId: 190688309

PiperOrigin-RevId: 190682119

Add warning if shuffle=false but num_readers > 1. The latter would cause the input data stream to still be shuffled.

PiperOrigin-RevId: 190678792

PiperOrigin-RevId: 190651873

PiperOrigin-RevId: 190636417

Cython is must installed package for building cocoapi. else the build will not
initiate.

PiperOrigin-RevId: 190553060

Tfmini requires positive values for the dimensions. Therefore, we need to test for no paddings in both width and height direction.

PiperOrigin-RevId: 190520529

PiperOrigin-RevId: 190505306

Switch line orders in trainer so that restore_map is called after moving average variables are created.

Moving averages are now properly loaded during fine-tuning, instead of being recreated.

PiperOrigin-RevId: 190496046

PiperOrigin-RevId: 190292280

PiperOrigin-RevId: 190115628

PiperOrigin-RevId: 190098000

The C API improves static shape inference, making more errors caught at graph construction time instead of runtime.

PiperOrigin-RevId: 190095450