GitLab

* Add CIFAR-10 support for keras application models.

Explicitly pass values kwarg to tf.name_scope as it is currently being treated as the default_name kwarg instead. This causes an exception to be thrown in eager mode.

Add more eval metrics to model_main and support group norm for mobilenet v1 based models.

Allow custom parse record method in resnet input functions

Add training and eval code for efficient-hrl

Move tensorflow_models/research/astronet to google-research/exoplanet-ml

Code clean up

PiperOrigin-RevId: 223839440

Fix #5814

Comments wrongly say dropout is used

223075771  by lzc:

    Bring in external fixes.

--
222919755  by ronnyvotel:

    Bug fix in faster r-cnn model builder. Was previously using `inplace_batchnorm_update` for `reuse_weights`.

--
222885680  by Zhichao Lu:

    Use the result_dict_for_batched_example in models_lib
    Also fixes the visualization size on when eval is on GPU

--
222883648  by Zhichao Lu:

    Fix _unmatched_class_label for the _add_background_class == False case in ssd_meta_arch.py.

--
222836663  by Zhichao Lu:

    Adding support for visualizing grayscale images. Without this change, the images are black-red instead of grayscale.

--
222501978  by Zhichao Lu:

    Fix a bug that caused convert_to_grayscale flag not to be respected.

--
222432846  by richardmunoz:

    Fix mapping of groundtruth_confidences from shape [num_boxes] to [num_boxes, num_classes] when the input contains the groundtruth_confidences field.

--
221725755  by richardmunoz:

    Internal change.

--
221458...

223150784  by Sergio Guadarrama:

    Allow using batch norm scale parameters for Inception models.

--
221391590  by Sergio Guadarrama:

    Add support for group normalization in the object detection API. Just adding MobileNet-v1 SSD currently. This may serve as a road map for other models that wish to support group normalization as an option.

--
221342582  by Sergio Guadarrama:

    Internal change

220817084  by Sergio Guadarrama:

    Internal change

216005108  by Sergio Guadarrama:

    Introduce hparam `use_bounded_activation` for NASNet. The hparam decides whether to use
    1. bounded activation
    2. clip_by_value for the add operands and bounded activation after add operator.
    3. bounded activation before 'none' and 'pooling' branch
    The restriction on the tensor value range makes it compatible with quantized inference.

--

PiperOrigin-RevId: 223150784

Reorganize astronet directory structure

PiperOrigin-RevId: 223442581

PiperOrigin-RevId: 223437592

Also fix a few lint errors in unit tests.

PiperOrigin-RevId: 223434695

PiperOrigin-RevId: 223433850

* Add a second expected_loss_weights function using an alternative expectation calculation compared to previous. Integrate this op into ssd_meta_arch and losses builder. Affects files that use losses_builder.build to handle the returning of an additional element.

PiperOrigin-RevId: 219190083

* Fix dependency issues.

PiperOrigin-RevId: 222888231

* Update CODEOWNERS 

Add @masonliuw and @yinxiaoli to /research/lstm_object_detection/

Add @masonliuw and @yinxiaoli to /research/lstm_object_detection/

PiperOrigin-RevId: 222888231

Add a second expected_loss_weights function using an alternative expectation calculation compared to previous. Integrate this op into ssd_meta_arch and losses builder. Affects files that use losses_builder.build to handle the returning of an additional element.

PiperOrigin-RevId: 219190083

Open souring mobile video object detection framework

Updated to 1.9 for consistency with running_pets.md

We've deprecated the "tower" terminology in DistributionStrategy, so the "cross_tower_ops" argument is now "cross_device_ops", matching the current name of "AllReduceCrossDeviceOps".

Another error appears when an incompatible version of Tensorboard is installed. Need to ensure Tensorboard is 1.9 as well

Switching to more robust pysoundfile for reading wav files

Explicitly mention Python 2.7 in README for research/im2txt

Freeze environment using Conda for research/im2txt

Added struct2depth model

Improved performance of deeplab inference