GitLab

* 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/

Open souring mobile video object detection framework

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".

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

`num_replicas` is being replaced by `num_replicas_in_sync` and something that returns the number of steps running concurrently.

Update lite path + fix --config option

`lite` is no longer under `contrib`. 

Additionally, `--config=opt` fails, see: https://github.com/tensorflow/serving/issues/517

This tag should match EVAL_HP_NUM_NEG.

Revert "Use explicit relative import syntax for python 3 compatibility in audioset."

Update 4_Neural_Style_Transfer_with_Eager_Execution.ipynb

Fixed grammar errors and typos.

Use explicit relative import syntax for python 3 compatibility in audioset.

I've noticed sometimes the async process's pool processes do not die when ncf_main.py ends and kills the async process. This commit fixes the issue.

* Internal change.

PiperOrigin-RevId: 213914693

* Add original_image_spatial_shape tensor in input dictionary to store shape of the original input image

PiperOrigin-RevId: 214018767

* Remove "groundtruth_confidences" from decoders use "groundtruth_weights" to indicate label confidence.

This also solves a bug that only surfaced now - random crop routines in core/preprocessor.py did not correctly handle "groundtruth_weight" tensors returned by the decoders.

PiperOrigin-RevId: 214091843

* Update CocoMaskEvaluator to allow for a batch of image info, rather than a single image.

PiperOrigin-RevId: 214295305

* Adding the option to be able to summarize gradients.

PiperOrigin-RevId: 214310875

* Adds FasterRCNN inference on CPU

1. Adds a flag use_static_shapes_for_eval to restrict to the ops that guarantees static shape.
2. No filtering of overlapping anchors while clipping the anchors when use_static_shapes_for_eval is set to True.
3. A...

Remove progress indicator from Movielens download

update the calculation of num_batches_per_epoch

the number of batches per epoch also depends on the number of gpus. it should be `num_batches_per_epoch = (cifar10.NUM_EXAMPLES_PER_EPOCH_FOR_TRAIN / FLAGS.batch_size / FLAGS.num_gpus)`

* Keras-ify TPU embedding lookup

* delint

* pull get_variable() out of keras lambda

* delint

* move get_variable under variable scope

* Merges TPU-TC optimizations into HEAD.

* Split a line that went over 80 from a tab.

* Remove trailing whitespace.

The option is --nouse_estimator

--ml_perf now just changes the model to make it MLPerf compliant. --output_ml_perf_compliance_logging adds the MLPerf compliance logs.

prevent async process from writing alive file until the main process has created the cache root (#5614)