GitLab

* fix issue 'could not satisfy explicit device'

* remove the line unrelated to fix issue

PiperOrigin-RevId: 192624207

image evaluation).

PiperOrigin-RevId: 192583425

PiperOrigin-RevId: 192529600

PiperOrigin-RevId: 192512429

PiperOrigin-RevId: 192494267

PiperOrigin-RevId: 192485456

PiperOrigin-RevId: 192472546

PiperOrigin-RevId: 192421843

Returning eval_on_train_input_fn from create_estimator_and_inputs(), rather than using train_input_fn in EVAL mode (which will still have data augmentation).

PiperOrigin-RevId: 192320460

PiperOrigin-RevId: 192226678

PiperOrigin-RevId: 192195514

PiperOrigin-RevId: 192166224

PiperOrigin-RevId: 192147130

PiperOrigin-RevId: 192132440

PiperOrigin-RevId: 192006190

Migrating away from Experiment class, as it is now deprecated. Also, refactoring into a separate model library and binaries.

PiperOrigin-RevId: 192004845

PiperOrigin-RevId: 191957195

Add an option to skip the last striding in mobilenet. The modified network has nominal output stride 16 instead of 32.

PiperOrigin-RevId: 191932855

Add option to override base feature extractor hyperparams in SSD models. This would allow us to use the same set of hyperparams for the complete feature extractor (base + new layers) if desired.

PiperOrigin-RevId: 191787921

Adding an attribute to SSD model to indicate which fields in prediction dictionary have a batch dimension. This will be useful for future video models.

PiperOrigin-RevId: 191743097

PiperOrigin-RevId: 191668425

The current code does not work in py2 since the input string could
contain unicode string, and default encoding in ASCII in py2. Change
the method to only do encode() which convert string to byte array
when running python3.

* Adding cast to fp32

* Adding myself to OWNERS

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

191649512  by Zhichao Lu:

    Introduce two parameters in ssd.proto - freeze_batchnorm, inplace_batchnorm_update - and set up slim arg_scopes in ssd_meta_arch.py such that applies it to all batchnorm ops in the predict() method.

    This centralizes the control of freezing and doing inplace batchnorm updates.

--
191620303  by Zhichao Lu:

    Modifications to the preprocessor to support multiclass scores

--
191610773  by Zhichao Lu:

    Adding multiclass_scores to InputDataFields and adding padding for multiclass_scores.

--
191595011  by Zhichao Lu:

    Contains implementation of the detection metric for the Open Images Challenge.

--
191449408  by Zhichao Lu:

    Change hyperparams_builder to return a callable so the users can inherit values from outer arg_scopes. This allows us to easily set batch_norm parameters like "is_training" and "inplace_batchnorm_update" for all feature extractors from the base class and propagate it correctly to the nested scopes.

--
191437008  by Zhichao Lu:

    Contains implementation of the Recall@N and MedianRank@N metrics.

--
191385254  by Zhichao Lu:

    Add config rewrite flag to eval.py

--
191382500  by Zhichao Lu:

    Fix bug for config_util.

--

PiperOrigin-RevId: 191649512

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