GitLab

Internal changes

--

PiperOrigin-RevId: 316837667

* Merged commit includes the following changes:
311933687  by Sergio Guadarrama:

    Removes spurios use of tf.compat.v2, which results in spurious tf.compat.v1.compat.v2. Adds basic test to nasnet_utils.
    Replaces all remaining import tensorflow as tf with import tensorflow.compat.v1 as tf

--
311766063  by Sergio Guadarrama:

    Removes explicit tf.compat.v1 in all call sites (we already import tf.compat.v1, so this code was  doing tf.compat.v1.compat.v1). The existing code worked in latest version of tensorflow, 2.2, (and 1.15) but not in 1.14 or in 2.0.0a, this CL fixes it.

--
311624958  by Sergio Guadarrama:

    Updates README that doesn't render properly in github documentation

--
310980959  by Sergio Guadarrama:

    Moves research_models/slim off tf.contrib.slim/layers/framework to tf_slim

--
310263156  by Sergio Guadarrama:

    Adds model breakdown for MobilenetV3

--
308640...

257914648  by lzc:

    Internal changes

--
257525973  by Zhichao Lu:

    Fixes bug that silently prevents checkpoints from loading when training w/ eager + functions. Also sets up scripts to run training.

--
257296614  by Zhichao Lu:

    Adding detection_features to model outputs

--
257234565  by Zhichao Lu:

    Fix wrong order of `classes_with_max_scores` in class-agnostic NMS caused by
    sorting in partitioned-NMS.

--
257232002  by ronnyvotel:

    Supporting `filter_nonoverlapping` option in np_box_list_ops.clip_to_window().

--
257198282  by Zhichao Lu:

    Adding the focal loss and l1 loss from the Objects as Points paper.

--
257089535  by Zhichao Lu:

    Create Keras based ssd + resnetv1 + fpn.

--
257087407  by Zhichao Lu:

    Make object_detection/data_decoders Python3-compatible.

--
257004582  by Zhichao Lu:

    Updates _decode_raw_data_into_masks_and_boxes to the latest binary masks-to-string encoding fo...

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.

--
221458536  by Zhichao Lu:

    Fix saver defer build bug in object detection train codepath.

--
221391590  by Zhichao Lu:

    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.

--
221367993  by Zhichao Lu:

    Bug fixes (1) Make RandomPadImage work, (2) Fix keep_checkpoint_every_n_hours.

--
221266403  by rathodv:

    Use detection boxes as proposals to compute correct mask loss in eval jobs.

--
220845934  by lzc:

    Internal change.

--
220778850  by Zhichao Lu:

    Incorporating existing metrics into Estimator framework.
    Should restore:
    -oid_challenge_detection_metrics
    -pascal_voc_detection_metrics
    -weighted_pascal_voc_detection_metrics
    -pascal_voc_instance_segmentation_metrics
    -weighted_pascal_voc_instance_segmentation_metrics
    -oid_V2_detection_metrics

--
220370391  by alirezafathi:

    Adding precision and recall to the metrics.

--
220321268  by Zhichao Lu:

    Allow the option of setting max_examples_to_draw to zero.

--
220193337  by Zhichao Lu:

    This CL fixes a bug where the Keras convolutional box predictor was applying heads in the non-deterministic dict order. The consequence of this bug was that variables were created in non-deterministic orders. This in turn led different workers in a multi-gpu training setup to have slightly different graphs which had variables assigned to mismatched parameter servers. As a result, roughly half of all workers were unable to initialize and did no work, and training time was slowed down approximately 2x.

--
220136508  by huizhongc:

    Add weight equalization loss to SSD meta arch.

--
220125875  by pengchong:

    Rename label_scores to label_weights

--
219730108  by Zhichao Lu:

    Add description of detection_keypoints in postprocessed_tensors to docstring.

--
219577519  by pengchong:

    Support parsing the class confidences and training using them.

--
219547611  by lzc:

    Stop using static shapes in GPU eval jobs.

--
219536476  by Zhichao Lu:

    Migrate TensorFlow Lite out of tensorflow/contrib

    This change moves //tensorflow/contrib/lite to //tensorflow/lite in preparation
    for TensorFlow 2.0's deprecation of contrib/. If you refer to TF Lite build
    targets or headers, you will need to update them manually. If you use TF Lite
    from the TensorFlow python package, "tf.contrib.lite" now points to "tf.lite".
    Please update your imports as soon as possible.

    For more details, see https://groups.google.com/a/tensorflow.org/forum/#!topic/tflite/iIIXOTOFvwQ

    @angersson and @aselle are conducting this migration. Please contact them if
    you have any further questions.

--
219190083  by Zhichao Lu:

    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.

--
218924451  by pengchong:

    Add a new way to assign training targets using groundtruth confidences.

--
218760524  by chowdhery:

    Modify export script to add option for regular NMS in TFLite post-processing op.

--

PiperOrigin-RevId: 223075771

* 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. Adds test for faster_rcnn_meta_arch for predict and postprocess in inference mode for first and second stages.

PiperOrigin-RevId: 214329565

* Fix model_lib eval_spec_names assignment (integer->string).

PiperOrigin-RevId: 214335461

* Refactor Mask HEAD to optionally upsample after applying convolutions on ROI crops.

PiperOrigin-RevId: 214338440

* Uses final_exporter_name as exporter_name for the first eval spec for backward compatibility.

PiperOrigin-RevId: 214522032

* Add reshaped `mask_predictions` tensor to the prediction dictionary in `_predict_third_stage` method to allow computing mask loss in eval job.

PiperOrigin-RevId: 214620716

* Add support for fully conv training to fpn.

PiperOrigin-RevId: 214626274

* Fix the proprocess() function in Resnet v1 to make it work for any number of input channels.

Note: If the #channels != 3, this will simply skip the mean subtraction in preprocess() function.
PiperOrigin-RevId: 214635428

* Wrap result_dict_for_single_example in eval_util to run for batched examples.

PiperOrigin-RevId: 214678514

* Adds PNASNet-based (ImageNet model) feature extractor for SSD.

PiperOrigin-RevId: 214988331

* Update documentation

PiperOrigin-RevId: 215243502

* Correct index used to compute number of groundtruth/detection boxes in COCOMaskEvaluator.

Due to an incorrect indexing in cl/214295305 only the first detection mask and first groundtruth mask for a given image are fed to the COCO Mask evaluation library. Since groundtruth masks are arranged in no particular order, the first and highest scoring detection mask (detection masks are ordered by score) won't match the the first and only groundtruth retained in all cases. This is I think why mask evaluation metrics do not get better than ~11 mAP. Note that this code path is only active when using model_main.py binary for evaluation.

This change fixes the indices and modifies an existing test case to cover it.

PiperOrigin-RevId: 215275936

* Fixing grayscale_image_resizer to accept mask as input.

PiperOrigin-RevId: 215345836

* Add an option not to clip groundtruth boxes during preprocessing. Clipping boxes adversely affects training for partially occluded or large objects, especially for fully conv models. Clipping already occurs during postprocessing, and should not occur during training.

PiperOrigin-RevId: 215613379

* Always return recalls and precisions with length equal to the number of classes.

The previous behavior of ObjectDetectionEvaluation was somewhat dangerous: when no groundtruth boxes were present, the lists of per-class precisions and recalls were simply truncated. Unless you were aware of this phenomenon (and consulted the `num_gt_instances_per_class` vector) it was difficult to associate each metric with each class.

PiperOrigin-RevId: 215633711

* Expose the box feature node in SSD.

PiperOrigin-RevId: 215653316

* Fix ssd mobilenet v2 _CONV_DEFS overwriting issue.

PiperOrigin-RevId: 215654160

* More documentation updates

PiperOrigin-RevId: 215656580

* Add pooling + residual option in multi_resolution_feature_maps. It adds an average pooling and a residual layer between feature maps with matching depth. Designed to be used with WeightSharedBoxPredictor.

PiperOrigin-RevId: 215665619

* Only call create_modificed_mobilenet_config on init if use_depthwise is true.

PiperOrigin-RevId: 215784290

* Only call create_modificed_mobilenet_config on init if use_depthwise is true.

PiperOrigin-RevId: 215837524

* Don't prune keypoints if clip_boxes is false.

PiperOrigin-RevId: 216187642

* Makes sure "key" field exists in the result dictionary.

PiperOrigin-RevId: 216456543

* Add add_background_class parameter to allow disabling the inclusion of a background class.

PiperOrigin-RevId: 216567612

* Update expected_classification_loss_under_sampling to better account for expected sampling.

PiperOrigin-RevId: 216712287

* Let the evaluation receive a evaluation class in its constructor.

PiperOrigin-RevId: 216769374

* This CL adds model building & training support for end-to-end Keras-based SSD models. If a Keras feature extractor's name is specified in the model config (e.g. 'ssd_mobilenet_v2_keras'), the model will use that feature extractor and a corresponding Keras-based box predictor.

This CL makes sure regularization losses & batch norm updates work correctly when training models that have Keras-based components. It also updates the default hyperparameter settings of the keras-based mobilenetV2 (when not overriding hyperparams) to more closely match the legacy Slim training scope.

PiperOrigin-RevId: 216938707

* Adding the ability in the coco evaluator to indicate whether an image has been annotated. For a non-annotated image, detections and groundtruth are not supplied.

PiperOrigin-RevId: 217316342

* Release the 8k minival dataset ids for MSCOCO, used in Huang et al. "Speed/accuracy trade-offs for modern convolutional object detectors" (https://arxiv.org/abs/1611.10012)

PiperOrigin-RevId: 217549353

* Exposes weighted_sigmoid_focal loss for faster rcnn classifier

PiperOrigin-RevId: 217601740

* Add detection_features to output nodes. The shape of the feature is [batch_size, max_detections, depth].

PiperOrigin-RevId: 217629905

* FPN uses a custom NN resize op for TPU-compatibility. Replace this op with the Tensorflow version at export time for TFLite-compatibility.

PiperOrigin-RevId: 217721184

* Compute `num_groundtruth_boxes` in inputs.tranform_input_data_fn after data augmentation instead of decoders.

PiperOrigin-RevId: 217733432

* 1. Stop gradients from flowing into groundtruth masks with zero paddings.
2. Normalize pixelwise cross entropy loss across the whole batch.

PiperOrigin-RevId: 217735114

* Optimize Input pipeline for Mask R-CNN on TPU with blfoat16: improve the step time from:
1663.6 ms -> 1184.2 ms, about 28.8% improvement.

PiperOrigin-RevId: 217748833

* Fixes to export a TPU compatible model

Adds nodes to each of the output tensor. Also increments the value of class labels by 1.

PiperOrigin-RevId: 217856760

* API changes:
 - change the interface of target assigner to return per-class weights.
 - change the interface of classification loss to take per-class weights.

PiperOrigin-RevId: 217968393

* Add an option to override pipeline config in export_saved_model using command line arg

PiperOrigin-RevId: 218429292

* Include Quantized trained MobileNet V2 SSD and FaceSsd in model zoo.

PiperOrigin-RevId: 218530947

* Write final config to disk in `train` mode only.

PiperOrigin-RevId: 218735512

Release iNaturalist Species-trained models, refactor of evaluation, box predictor for object detection. (#5289)

* Merged commit includes the following changes:
212389173  by Zhichao Lu:

    1. Replace tf.boolean_mask with tf.where

--
212282646  by Zhichao Lu:

    1. Fix a typo in model_builder.py and add a test to cover it.

--
212142989  by Zhichao Lu:

    Only resize masks in meta architecture if it has not already been resized in the input pipeline.

--
212136935  by Zhichao Lu:

    Choose matmul or native crop_and_resize in the model builder instead of faster r-cnn meta architecture.

--
211907984  by Zhichao Lu:

    Make eval input reader repeated field and update config util to handle this field.

--
211858098  by Zhichao Lu:

    Change the implementation of merge_boxes_with_multiple_labels.

--
211843915  by Zhichao Lu:

    Add Mobilenet v2 + FPN support.

--
211655076  by Zhichao Lu:

    Bug fix for generic keys in config overrides

    In generic configuration overrides, we had a duplicate entry for train_input_config and we were missing the eval_input_config and eval_config.

    This change also introduces testing for all config overrides.

--
211157501  by Zhichao Lu:

    Make the locally-modified conv defs a copy.

    So that it doesn't modify MobileNet conv defs globally for other code that
    transitively imports this package.

--
211112813  by Zhichao Lu:

    Refactoring visualization tools for Estimator's eval_metric_ops. This will make it easier for future models to take advantage of a single interface and mechanics.

--
211109571  by Zhichao Lu:

    A test decorator.

--
210747685  by Zhichao Lu:

    For FPN, when use_depthwise is set to true, use slightly modified mobilenet v1 config.

--
210723882  by Zhichao Lu:

    Integrating the losses mask into the meta architectures. When providing groundtruth, one can optionally specify annotation information (i.e. which images are labeled vs. unlabeled). For any image that is unlabeled, there is no loss accumulation.

--
210673675  by Zhichao Lu:

    Internal change.

--
210546590  by Zhichao Lu:

    Internal change.

--
210529752  by Zhichao Lu:

    Support batched inputs with ops.matmul_crop_and_resize.

    With this change the new inputs are images of shape [batch, heigh, width, depth] and boxes of shape [batch, num_boxes, 4]. The output tensor is of the shape [batch, num_boxes, crop_height, crop_width, depth].

--
210485912  by Zhichao Lu:

    Fix TensorFlow version check in object_detection_tutorial.ipynb

--
210484076  by Zhichao Lu:

    Reduce TPU memory required for single image matmul_crop_and_resize.

    Using tf.einsum eliminates intermediate tensors, tiling and expansion. for an image of size [40, 40, 1024] and boxes of shape [300, 4] HBM memory usage goes down from 3.52G to 1.67G.

--
210468361  by Zhichao Lu:

    Remove PositiveAnchorLossCDF/NegativeAnchorLossCDF to resolve "Main thread is not in main loop error" issue in local training.

--
210100253  by Zhichao Lu:

    Pooling pyramid feature maps: add option to replace max pool with convolution layers.

--
209995842  by Zhichao Lu:

    Fix a bug which prevents variable sharing in Faster RCNN.

--
209965526  by Zhichao Lu:

    Add support for enabling export_to_tpu through the estimator.

--
209946440  by Zhichao Lu:

    Replace deprecated tf.train.Supervisor with tf.train.MonitoredSession. MonitoredSession also takes away the hassle of starting queue runners.

--
209888003  by Zhichao Lu:

    Implement function to handle data where source_id is not set.

    If the field source_id is found to be the empty string for any image during runtime, it will be replaced with a random string. This avoids hash-collisions on dataset where many examples do not have source_id set. Those hash-collisions have unintended site effects and may lead to bugs in the detection pipeline.

--
209842134  by Zhichao Lu:

    Converting loss mask into multiplier, rather than using it as a boolean mask (which changes tensor shape). This is necessary, since other utilities (e.g. hard example miner) require a loss matrix with the same dimensions as the original prediction tensor.

--
209768066  by Zhichao Lu:

    Adding ability to remove loss computation from specific images in a batch, via an optional boolean mask.

--
209722556  by Zhichao Lu:

    Remove dead code.

    (_USE_C_API was flipped to True by default in TensorFlow 1.8)

--
209701861  by Zhichao Lu:

    This CL cleans-up some tf.Example creation snippets, by reusing the convenient tf.train.Feature building functions in dataset_util.

--
209697893  by Zhichao Lu:

    Do not overwrite num_epoch for eval input. This leads to errors in some cases.

--
209694652  by Zhichao Lu:

    Sample boxes by jittering around the currently given boxes.

--
209550300  by Zhichao Lu:

    `create_category_index_from_labelmap()` function now accepts `use_display_name` parameter.
    Also added create_categories_from_labelmap function for convenience

--
209490273  by Zhichao Lu:

    Check result_dict type before accessing image_id via key.

--
209442529  by Zhichao Lu:

    Introducing the capability to sample examples for evaluation. This makes it easy to specify one full epoch of evaluation, or a subset (e.g. sample 1 of every N examples).

--
208941150  by Zhichao Lu:

    Adding the capability of exporting the results in json format.

--
208888798  by Zhichao Lu:

    Fixes wrong dictionary key for num_det_boxes_per_image.

--
208873549  by Zhichao Lu:

    Reduce the number of HLO ops created by matmul_crop_and_resize.

    Do not unroll along the channels dimension. Instead, transpose the input image dimensions, apply tf.matmul and transpose back.

    The number of HLO instructions for 1024 channels reduce from 12368 to 110.

--
208844315  by Zhichao Lu:

    Add an option to use tf.non_maximal_supression_padded in SSD post-process

--
208731380  by Zhichao Lu:

    Add field in box_predictor config to enable mask prediction and update builders accordingly.

--
208699405  by Zhichao Lu:

    This CL creates a keras-based multi-resolution feature map extractor.

--
208557208  by Zhichao Lu:

    Add TPU tests for Faster R-CNN Meta arch.

    * Tests that two_stage_predict and total_loss tests run successfully on TPU.
    * Small mods to multiclass_non_max_suppression to preserve static shapes.

--
208499278  by Zhichao Lu:

    This CL makes sure the Keras convolutional box predictor & head layers apply activation layers *after* normalization (as opposed to before).

--
208391694  by Zhichao Lu:

    Updating visualization tool to produce multiple evaluation images.

--
208275961  by Zhichao Lu:

    This CL adds a Keras version of the Convolutional Box Predictor, as well as more general infrastructure for making Keras Prediction heads & Keras box predictors.

--
208275585  by Zhichao Lu:

    This CL enables the Keras layer hyperparameter object to build a dedicated activation layer, and to disable activation by default in the op layer construction kwargs.

    This is necessary because in most cases the normalization layer must be applied before the activation layer. So, in Keras models we must set the convolution activation in a dedicated layer after normalization is applied, rather than setting it in the convolution layer construction args.

--
208263792  by Zhichao Lu:

    Add a new SSD mask meta arch that can predict masks for SSD models.
    Changes including:
     - overwrite loss function to add mask loss computation.
     - update ssd_meta_arch to handle masks if predicted in predict and postprocessing.

--
208000218  by Zhichao Lu:

    Make FasterRCNN choose static shape operations only in training mode.

--
207997797  by Zhichao Lu:

    Add static boolean_mask op to box_list_ops.py and use that in faster_rcnn_meta_arch.py to support use_static_shapes option.

--
207993460  by Zhichao Lu:

    Include FGVC detection models in model zoo.

--
207971213  by Zhichao Lu:

    remove the restriction to run tf.nn.top_k op on CPU

--
207961187  by Zhichao Lu:

    Build the first stage NMS function in the model builder and pass it to FasterRCNN meta arch.

--
207960608  by Zhichao Lu:

    Internal Change.

--
207927015  by Zhichao Lu:

    Have an option to use the TPU compatible NMS op cl/206673787, in the batch_multiclass_non_max_suppression function. On setting pad_to_max_output_size to true, the output nmsed boxes are padded to be of length max_size_per_class.

    This can be used in first stage Region Proposal Network in FasterRCNN model by setting the first_stage_nms_pad_to_max_proposals field to true in config proto.

--
207809668  by Zhichao Lu:

    Add option to use depthwise separable conv instead of conv2d in FPN and WeightSharedBoxPredictor. More specifically, there are two related configs:
    - SsdFeatureExtractor.use_depthwise
    - WeightSharedConvolutionalBoxPredictor.use_depthwise

--
207808651  by Zhichao Lu:

    Fix the static balanced positive negative sampler's TPU tests

--
207798658  by Zhichao Lu:

    Fixes a post-refactoring bug where the pre-prediction convolution layers in the convolutional box predictor are ignored.

--
207796470  by Zhichao Lu:

    Make slim endpoints visible in FasterRCNNMetaArch.

--
207787053  by Zhichao Lu:

    Refactor ssd_meta_arch so that the target assigner instance is passed into the SSDMetaArch constructor rather than constructed inside.

--

PiperOrigin-RevId: 212389173

* Fix detection model zoo typo.

* Modify tf example decoder to handle label maps with either `display_name` or `name` fields seamlessly.

Currently, tf example decoder uses only `name` field to look up ids for class text field present in the data. This change uses both `display_name` and `name` fields in the label map to fetch ids for class text.

PiperOrigin-RevId: 212672223

* Modify create_coco_tf_record tool to write out class text instead of class labels.

PiperOrigin-RevId: 212679112

* Fix detection model zoo typo.

PiperOrigin-RevId: 212715692

* Adding the following two optional flags to WeightSharedConvolutionalBoxHead:
1) In the box head, apply clipping to box encodings in the box head.
2) In the class head, apply sigmoid to class predictions at inference time.

PiperOrigin-RevId: 212723242

* Support class confidences in merge boxes with multiple labels.

PiperOrigin-RevId: 212884998

* Creates multiple eval specs for object detection.

PiperOrigin-RevId: 212894556

* Set batch_norm on last layer in Mask Head to None.

PiperOrigin-RevId: 213030087

* Enable bfloat16 training for object detection models.

PiperOrigin-RevId: 213053547

* Skip padding op when unnecessary.

PiperOrigin-RevId: 213065869

* Modify `Matchers` to use groundtruth weights before performing matching.

Groundtruth weights tensor is used to indicate padding in groundtruth box tensor. It is handled in `TargetAssigner` by creating appropriate classification and regression target weights based on the groundtruth box each anchor matches to. However, options such as `force_match_all_rows` in `ArgmaxMatcher` force certain anchors to match to groundtruth boxes that are just paddings thereby reducing the number of anchors that could otherwise match to real groundtruth boxes.

For single stage models like SSD the effect of this is negligible as there are two orders of magnitude more anchors than the number of padded groundtruth boxes. But for Faster R-CNN and Mask R-CNN where there are only 300 anchors in the second stage, a significant number of these match to groundtruth paddings reducing the number of anchors regressing to real groundtruth boxes degrading the performance severely.

Therefore, this change introduces an additional boolean argument `valid_rows` to `Matcher.match` methods and the implementations now ignore such padded groudtruth boxes during matching.

PiperOrigin-RevId: 213345395

* Add release note for iNaturalist Species trained models.

PiperOrigin-RevId: 213347179

* Fix the bug of uninitialized gt_is_crowd_list variable.

PiperOrigin-RevId: 213364858

* ...text exposed to open source public git repo...

PiperOrigin-RevId: 213554260

* Merged commit includes the following changes:
206852642  by Zhichao Lu:

    Build the balanced_positive_negative_sampler in the model builder for FasterRCNN. Also adds an option to use the static implementation of the sampler.

--
206803260  by Zhichao Lu:

    Fixes a misplaced argument in resnet fpn feature extractor.

--
206682736  by Zhichao Lu:

    This CL modifies the SSD meta architecture to support both Slim-based and Keras-based box predictors, and begins preparation for Keras box predictor support in the other meta architectures.

    Concretely, this CL adds a new `KerasBoxPredictor` base class and makes the meta architectures appropriately call whichever box predictors they are using.

    We can switch the non-ssd meta architectures to fully support Keras box predictors once the Keras Convolutional Box Predictor CL is submitted.

--
206669634  by Zhichao Lu:

    Adds an alternate method for balanced positive negative sampler using static shapes.

--
206643278  by Zhichao Lu:

    This CL adds a Keras layer hyperparameter configuration object to the hyperparams_builder.

    It automatically converts from Slim layer hyperparameter configs to Keras layer hyperparameters. Namely, it:
    - Builds Keras initializers/regularizers instead of Slim ones
    - sets weights_regularizer/initializer to kernel_regularizer/initializer
    - converts batchnorm decay to momentum
    - converts Slim l2 regularizer weights to the equivalent Keras l2 weights

    This will be used in the conversion of object detection feature extractors & box predictors to newer Tensorflow APIs.

--
206611681  by Zhichao Lu:

    Internal changes.

--
206591619  by Zhichao Lu:

    Clip the to shape when the input tensors are larger than the expected padded static shape

--
206517644  by Zhichao Lu:

    Make MultiscaleGridAnchorGenerator more consistent with MultipleGridAnchorGenerator.

--
206415624  by Zhichao Lu:

    Make the hardcoded feature pyramid network (FPN) levels configurable for both SSD
    Resnet and SSD Mobilenet.

--
206398204  by Zhichao Lu:

    This CL modifies the SSD meta architecture to support both Slim-based and Keras-based feature extractors.

    This allows us to begin the conversion of object detection to newer Tensorflow APIs.

--
206213448  by Zhichao Lu:

    Adding a method to compute the expected classification loss by background/foreground weighting.

--
206204232  by Zhichao Lu:

    Adding the keypoint head to the Mask RCNN pipeline.

--
206200352  by Zhichao Lu:

    - Create Faster R-CNN target assigner in the model builder. This allows configuring matchers in Target assigner to use TPU compatible ops (tf.gather in this case) without any change in meta architecture.
    - As a +ve side effect of the refactoring, we can now re-use a single target assigner for all of second stage heads in Faster R-CNN.

--
206178206  by Zhichao Lu:

    Force ssd feature extractor builder to use keyword arguments so values won't be passed to wrong arguments.

--
206168297  by Zhichao Lu:

    Updating exporter to use freeze_graph.freeze_graph_with_def_protos rather than a homegrown version.

--
206080748  by Zhichao Lu:

    Merge external contributions.

--
206074460  by Zhichao Lu:

    Update to preprocessor to apply temperature and softmax to the multiclass scores on read.

--
205960802  by Zhichao Lu:

    Fixing a bug in hierarchical label expansion script.

--
205944686  by Zhichao Lu:

    Update exporter to support exporting quantized model.

--
205912529  by Zhichao Lu:

    Add a two stage matcher to allow for thresholding by one criteria and then argmaxing on the other.

--
205909017  by Zhichao Lu:

    Add test for grayscale image_resizer

--
205892801  by Zhichao Lu:

    Add flag to decide whether to apply batch norm to conv layers of weight shared box predictor.

--
205824449  by Zhichao Lu:

    make sure that by default mask rcnn box predictor predicts 2 stages.

--
205730139  by Zhichao Lu:

    Updating warning message to be more explicit about variable size mismatch.

--
205696992  by Zhichao Lu:

    Remove utils/ops.py's dependency on core/box_list_ops.py. This will allow re-using TPU compatible ops from utils/ops.py in core/box_list_ops.py.

--
205696867  by Zhichao Lu:

    Refactoring mask rcnn predictor so have each head in a separate file.
    This CL lets us to add new heads more easily in the future to mask rcnn.

--
205492073  by Zhichao Lu:

    Refactor R-FCN box predictor to be TPU compliant.

    - Change utils/ops.py:position_sensitive_crop_regions to operate on single image and set of boxes without `box_ind`
    - Add a batch version that operations on batches of images and batches of boxes.
    - Refactor R-FCN box predictor to use the batched version of position sensitive crop regions.

--
205453567  by Zhichao Lu:

    Fix bug that cannot export inference graph when write_inference_graph flag is True.

--
205316039  by Zhichao Lu:

    Changing input tensor name.

--
205256307  by Zhichao Lu:

    Fix model zoo links for quantized model.

--
205164432  by Zhichao Lu:

    Fixes eval error when label map contains non-ascii characters.

--
205129842  by Zhichao Lu:

    Adds a option to clip the anchors to the window size without filtering the overlapped boxes in Faster-RCNN

--
205094863  by Zhichao Lu:

    Update to label map util to allow the option of adding a background class and fill in gaps in the label map. Useful for using multiclass scores which require a complete label map with explicit background label.

--
204989032  by Zhichao Lu:

    Add tf.prof support to exporter.

--
204825267  by Zhichao Lu:

    Modify mask rcnn box predictor tests for TPU compatibility.

--
204778749  by Zhichao Lu:

    Remove score filtering from postprocessing.py and rely on filtering logic in tf.image.non_max_suppression

--
204775818  by Zhichao Lu:

    Python3 fixes for object_detection.

--
204745920  by Zhichao Lu:

    Object Detection Dataset visualization tool (documentation).

--
204686993  by Zhichao Lu:

    Internal changes.

--
204559667  by Zhichao Lu:

    Refactor box_predictor.py into multiple files.
    The abstract base class remains in the object_detection/core, The other classes have moved to a separate file each in object_detection/predictors

--
204552847  by Zhichao Lu:

    Update blog post link.

--
204508028  by Zhichao Lu:

    Bump down the batch size to 1024 to be a bit more tolerant to OOM and double the number of iterations. This job still converges to 20.5 mAP in 3 hours.

--

PiperOrigin-RevId: 206852642

* Add original post-processing back.

199348852  by Zhichao Lu:

    Small typos fixes in VRD evaluation.

--
199315191  by Zhichao Lu:

    Change padding shapes when additional channels are available.

--
199309180  by Zhichao Lu:

    Adds minor fixes to the Object Detection API implementation.

--
199298605  by Zhichao Lu:

    Force num_readers to be 1 when only input file is not sharded.

--
199292952  by Zhichao Lu:

    Adds image-level labels parsing into TfExampleDetectionAndGTParser.

--
199259866  by Zhichao Lu:

    Visual Relationships Evaluation executable.

--
199208330  by Zhichao Lu:

    Infer train_config.batch_size as the effective batch size. Therefore we need to divide the effective batch size in trainer by train_config.replica_to_aggregate to get per worker batch size.

--
199207842  by Zhichao Lu:

    Internal change.

--
199204222  by Zhichao Lu:

    In case the image has more than three channels, we only take the first three channels for visualization.

--
199194388  by Zhichao Lu:

    Correcting protocols description: VOC 2007 -> VOC 2012.

--
199188290  by Zhichao Lu:

    Adds per-relationship APs and mAP computation to VRD evaluation.

--
199158801  by Zhichao Lu:

    If available, additional channels are merged with input image.

--
199099637  by Zhichao Lu:

    OpenImages Challenge metric support:
    -adding verified labels standard field for TFExample;
    -adding tfrecord creation functionality.

--
198957391  by Zhichao Lu:

    Allow tf record sharding when creating pets dataset.

--
198925184  by Zhichao Lu:

    Introduce moving average support for evaluation. Also adding the ability to override this configuration via config_util.

--
198918186  by Zhichao Lu:

    Handles the case where there are 0 box masks.

--
198809009  by Zhichao Lu:

    Plumb groundtruth weights into target assigner for Faster RCNN.

--
198759987  by Zhichao Lu:

    Fix object detection test broken by shape inference.

--
198668602  by Zhichao Lu:

    Adding a new input field in data_decoders/tf_example_decoder.py for storing additional channels.

--
198530013  by Zhichao Lu:

    An util for hierarchical expandion of boxes and labels of OID dataset.

--
198503124  by Zhichao Lu:

    Fix dimension mismatch error introduced by
    https://github.com/tensorflow/tensorflow/pull/18251, or cl/194031845.
    After above change, conv2d strictly checks for conv_dims + 2 == input_rank.

--
198445807  by Zhichao Lu:

    Enabling Object Detection Challenge 2018 metric in evaluator.py framework for
    running eval job.
    Renaming old OpenImages V2 metric.

--
198413950  by Zhichao Lu:

    Support generic configuration override using namespaced keys

    Useful for adding custom hyper-parameter tuning fields without having to add custom override methods to config_utils.py.

--
198106437  by Zhichao Lu:

    Enable fused batchnorm now that quantization is supported.

--
198048364  by Zhichao Lu:

    Add support for keypoints in tf sequence examples and some util ops.

--
198004736  by Zhichao Lu:

    Relax postprocessing unit tests that are based on assumption that tf.image.non_max_suppression are stable with respect to input.

--
197997513  by Zhichao Lu:

    More lenient validation for normalized box boundaries.

--
197940068  by Zhichao Lu:

    A couple of minor updates/fixes:
    - Updating input reader proto with option to use display_name when decoding data.
    - Updating visualization tool to specify whether using absolute or normalized box coordinates. Appropriate boxes will now appear in TB when using model_main.py

--
197920152  by Zhichao Lu:

    Add quantized training support in the new OD binaries and a config for SSD Mobilenet v1 quantized training that is TPU compatible.

--
197213563  by Zhichao Lu:

    Do not share batch_norm for classification and regression tower in weight shared box predictor.

--
197196757  by Zhichao Lu:

    Relax the box_predictor api to return box_prediction of shape [batch_size, num_anchors, code_size] in addition to [batch_size, num_anchors, (1|q), code_size].

--
196898361  by Zhichao Lu:

    Allow per-channel scalar value to pad input image with when using keep aspect ratio resizer (when pad_to_max_dimension=True).

    In Object Detection Pipeline, we pad image before normalization and this skews batch_norm statistics during training. The option to set per channel pad value lets us truly pad with zeros.

--
196592101  by Zhichao Lu:

    Fix bug regarding tfrecord shuffling in object_detection

--
196320138  by Zhichao Lu:

    Fix typo in exporting_models.md

--

PiperOrigin-RevId: 199348852

184048729  by Zhichao Lu:

    Modify target_assigner so that it creates regression targets taking keypoints into account.

--
184027183  by Zhichao Lu:

    Resnet V1 FPN based feature extractors for SSD meta architecture in Object Detection V2 API.

--
184004730  by Zhichao Lu:

    Expose a lever to override the configured mask_type.

--
183933113  by Zhichao Lu:

    Weight shared convolutional box predictor as described in https://arxiv.org/abs/1708.02002

--
183929669  by Zhichao Lu:

    Expanding box list operations for future data augmentations.

--
183916792  by Zhichao Lu:

    Fix unrecognized assertion function in tests.

--
183906851  by Zhichao Lu:

    - Change ssd meta architecture to use regression weights to compute loss normalizer.

--
183871003  by Zhichao Lu:

    Fix config_util_test wrong dependency.

--
183782120  by Zhichao Lu:

    Add __init__ file to third_party directories.

--
183779109  by Zhichao Lu:

    Setup regular version sync.

--
183768772  by Zhichao Lu:

    Make test compatible with numpy 1.12 and higher

--
183767893  by Zhichao Lu:

    Make test compatible with numpy 1.12 and higher

--
183719318  by Zhichao Lu:

    Use the new test interface in ssd feature extractor.

--
183714671  by Zhichao Lu:

    Use the new test_case interface for all anchor generators.

--
183708155  by Zhichao Lu:

    Change variable scopes in ConvolutionalBoxPredictor such that previously trained checkpoints are still compatible after the change in BoxPredictor interface

--
183705798  by Zhichao Lu:

    Internal change.

--
183636023  by Zhichao Lu:

    Fixing argument name for np_box_list_ops.concatenate() function.

--
183490404  by Zhichao Lu:

    Make sure code that relies in SSD older code still works.

--
183426762  by Zhichao Lu:

    Internal change

183412315  by Zhichao Lu:

    Internal change

183337814  by Zhichao Lu:

    Internal change

183303933  by Zhichao Lu:

    Internal change

183257349  by Zhichao Lu:

    Internal change

183254447  by Zhichao Lu:

    Internal change

183251200  by Zhichao Lu:

    Internal change

183135002  by Zhichao Lu:

    Internal change

182851500  by Zhichao Lu:

    Internal change

182839607  by Zhichao Lu:

    Internal change

182830719  by Zhichao Lu:

    Internal change

182533923  by Zhichao Lu:

    Internal change

182391090  by Zhichao Lu:

    Internal change

182262339  by Zhichao Lu:

    Internal change

182244645  by Zhichao Lu:

    Internal change

182241613  by Zhichao Lu:

    Internal change

182133027  by Zhichao Lu:

    Internal change

182058807  by Zhichao Lu:

    Internal change

181812028  by Zhichao Lu:

    Internal change

181788857  by Zhichao Lu:

    Internal change

181656761  by Zhichao Lu:

    Internal change

181541125  by Zhichao Lu:

    Internal change

181538702  by Zhichao Lu:

    Internal change

181125385  by Zhichao Lu:

    Internal change

180957758  by Zhichao Lu:

    Internal change

180941434  by Zhichao Lu:

    Internal change

180852569  by Zhichao Lu:

    Internal change

180846001  by Zhichao Lu:

    Internal change

180832145  by Zhichao Lu:

    Internal change

180740495  by Zhichao Lu:

    Internal change

180729150  by Zhichao Lu:

    Internal change

180589008  by Zhichao Lu:

    Internal change

180585408  by Zhichao Lu:

    Internal change

180581039  by Zhichao Lu:

    Internal change

180286388  by Zhichao Lu:

    Internal change

179934081  by Zhichao Lu:

    Internal change

179841242  by Zhichao Lu:

    Internal change

179831694  by Zhichao Lu:

    Internal change

179761005  by Zhichao Lu:

    Internal change

179610632  by Zhichao Lu:

    Internal change

179605363  by Zhichao Lu:

    Internal change

179603774  by Zhichao Lu:

    Internal change

179598614  by Zhichao Lu:

    Internal change

179597809  by Zhichao Lu:

    Internal change

179494630  by Zhichao Lu:

    Internal change

179367492  by Zhichao Lu:

    Internal change

179250050  by Zhichao Lu:

    Internal change

179247385  by Zhichao Lu:

    Internal change

179207897  by Zhichao Lu:

    Internal change

179076230  by Zhichao Lu:

    Internal change

178862066  by Zhichao Lu:

    Internal change

178854216  by Zhichao Lu:

    Internal change

178853109  by Zhichao Lu:

    Internal change

178709753  by Zhichao Lu:

    Internal change

178640707  by Zhichao Lu:

    Internal change

178421534  by Zhichao Lu:

    Internal change

178287174  by Zhichao Lu:

    Internal change

178257399  by Zhichao Lu:

    Internal change

177681867  by Zhichao Lu:

    Internal change

177654820  by Zhichao Lu:

    Internal change

177654052  by Zhichao Lu:

    Internal change

177638787  by Zhichao Lu:

    Internal change

177598305  by Zhichao Lu:

    Internal change

177538488  by Zhichao Lu:

    Internal change

177474197  by Zhichao Lu:

    Internal change

177271928  by Zhichao Lu:

    Internal change

177250285  by Zhichao Lu:

    Internal change

177210762  by Zhichao Lu:

    Internal change

177197135  by Zhichao Lu:

    Internal change

177037781  by Zhichao Lu:

    Internal change

176917394  by Zhichao Lu:

    Internal change

176683171  by Zhichao Lu:

    Internal change

176450793  by Zhichao Lu:

    Internal change

176388133  by Zhichao Lu:

    Internal change

176197721  by Zhichao Lu:

    Internal change

176195315  by Zhichao Lu:

    Internal change

176128748  by Zhichao Lu:

    Internal change

175743440  by Zhichao Lu:

    Use Toggle instead of bool to make the layout optimizer name and usage consistent with other optimizers.

--
175578178  by Zhichao Lu:

    Internal change

175463518  by Zhichao Lu:

    Internal change

175316616  by Zhichao Lu:

    Internal change

175302470  by Zhichao Lu:

    Internal change

175300323  by Zhichao Lu:

    Internal change

175269680  by Zhichao Lu:

    Internal change

175260574  by Zhichao Lu:

    Internal change

175122281  by Zhichao Lu:

    Internal change

175111708  by Zhichao Lu:

    Internal change

175110183  by Zhichao Lu:

    Internal change

174877166  by Zhichao Lu:

    Internal change

174868399  by Zhichao Lu:

    Internal change

174754200  by Zhichao Lu:

    Internal change

174544534  by Zhichao Lu:

    Internal change

174536143  by Zhichao Lu:

    Internal change

174513795  by Zhichao Lu:

    Internal change

174463713  by Zhichao Lu:

    Internal change

174403525  by Zhichao Lu:

    Internal change

174385170  by Zhichao Lu:

    Internal change

174358498  by Zhichao Lu:

    Internal change

174249903  by Zhichao Lu:

    Fix nasnet image classification and object detection by moving the option to turn ON or OFF batch norm training into it's own arg_scope used only by detection

--
174216508  by Zhichao Lu:

    Internal change

174065370  by Zhichao Lu:

    Internal change

174048035  by Zhichao Lu:

    Fix the pointer for downloading the NAS Faster-RCNN model.

--
174042677  by Zhichao Lu:

    Internal change

173964116  by Zhichao Lu:

    Internal change

173790182  by Zhichao Lu:

    Internal change

173779919  by Zhichao Lu:

    Internal change

173753775  by Zhichao Lu:

    Internal change

173753160  by Zhichao Lu:

    Internal change

173737519  by Zhichao Lu:

    Internal change

173696066  by Zhichao Lu:

    Internal change

173611554  by Zhichao Lu:

    Internal change

173475124  by Zhichao Lu:

    Internal change

173412497  by Zhichao Lu:

    Internal change

173404010  by Zhichao Lu:

    Internal change

173375014  by Zhichao Lu:

    Internal change

173345107  by Zhichao Lu:

    Internal change

173298413  by Zhichao Lu:

    Internal change

173289754  by Zhichao Lu:

    Internal change

173275544  by Zhichao Lu:

    Internal change

173273275  by Zhichao Lu:

    Internal change

173271885  by Zhichao Lu:

    Internal change

173264856  by Zhichao Lu:

    Internal change

173263791  by Zhichao Lu:

    Internal change

173261215  by Zhichao Lu:

    Internal change

173175740  by Zhichao Lu:

    Internal change

173010193  by Zhichao Lu:

    Internal change

172815204  by Zhichao Lu:

    Allow for label maps in tf.Example decoding.

--
172696028  by Zhichao Lu:

    Internal change

172509113  by Zhichao Lu:

    Allow for label maps in tf.Example decoding.

--
172475999  by Zhichao Lu:

    Internal change

172166621  by Zhichao Lu:

    Internal change

172151758  by Zhichao Lu:

    Minor updates to some README files.

    As a result of these friendly issues:
    https://github.com/tensorflow/models/issues/2530
    https://github.com/tensorflow/models/issues/2534

--
172147420  by Zhichao Lu:

    Fix illegal summary name and move from slim's get_or_create_global_step deprecated use of tf.contrib.framework* to tf.train*.

--
172111377  by Zhichao Lu:

    Internal change

172004247  by Zhichao Lu:

    Internal change

171996881  by Zhichao Lu:

    Internal change

171835204  by Zhichao Lu:

    Internal change

171826090  by Zhichao Lu:

    Internal change

171784016  by Zhichao Lu:

    Internal change

171699876  by Zhichao Lu:

    Internal change

171053425  by Zhichao Lu:

    Internal change

170905734  by Zhichao Lu:

    Internal change

170889179  by Zhichao Lu:

    Internal change

170734389  by Zhichao Lu:

    Internal change

170705852  by Zhichao Lu:

    Internal change

170401574  by Zhichao Lu:

    Internal change

170352571  by Zhichao Lu:

    Internal change

170215443  by Zhichao Lu:

    Internal change

170184288  by Zhichao Lu:

    Internal change

169936898  by Zhichao Lu:

    Internal change

169763373  by Zhichao Lu:

    Fix broken GitHub links in tensorflow and tensorflow_models resulting from The Great Models Move (a.k.a. the research subfolder)

--
169744825  by Zhichao Lu:

    Internal change

169638135  by Zhichao Lu:

    Internal change

169561814  by Zhichao Lu:

    Internal change

169444091  by Zhichao Lu:

    Internal change

169292330  by Zhichao Lu:

    Internal change

169145185  by Zhichao Lu:

    Internal change

168906035  by Zhichao Lu:

    Internal change

168790411  by Zhichao Lu:

    Internal change

168708911  by Zhichao Lu:

    Internal change

168611969  by Zhichao Lu:

    Internal change

168535975  by Zhichao Lu:

    Internal change

168381815  by Zhichao Lu:

    Internal change

168244740  by Zhichao Lu:

    Internal change

168240024  by Zhichao Lu:

    Internal change

168168016  by Zhichao Lu:

    Internal change

168071571  by Zhichao Lu:

    Move display strings to below the bounding box if they would otherwise be outside the image.

--
168067771  by Zhichao Lu:

    Internal change

167970950  by Zhichao Lu:

    Internal change

167884533  by Zhichao Lu:

    Internal change

167626173  by Zhichao Lu:

    Internal change

167277422  by Zhichao Lu:

    Internal change

167249393  by Zhichao Lu:

    Internal change

167248954  by Zhichao Lu:

    Internal change

167189395  by Zhichao Lu:

    Internal change

167107797  by Zhichao Lu:

    Internal change

167061250  by Zhichao Lu:

    Internal change

166871147  by Zhichao Lu:

    Internal change

166867617  by Zhichao Lu:

    Internal change

166862112  by Zhichao Lu:

    Internal change

166715648  by Zhichao Lu:

    Internal change

166635615  by Zhichao Lu:

    Internal change

166383182  by Zhichao Lu:

    Internal change

166371326  by Zhichao Lu:

    Internal change

166254711  by Zhichao Lu:

    Internal change

166106294  by Zhichao Lu:

    Internal change

166081204  by Zhichao Lu:

    Internal change

165972262  by Zhichao Lu:

    Internal change

165816702  by Zhichao Lu:

    Internal change

165764471  by Zhichao Lu:

    Internal change

165724134  by Zhichao Lu:

    Internal change

165655829  by Zhichao Lu:

    Internal change

165587904  by Zhichao Lu:

    Internal change

165534540  by Zhichao Lu:

    Internal change

165177692  by Zhichao Lu:

    Internal change

165091822  by Zhichao Lu:

    Internal change

165019730  by Zhichao Lu:

    Internal change

165002942  by Zhichao Lu:

    Internal change

164897728  by Zhichao Lu:

    Internal change

164782618  by Zhichao Lu:

    Internal change

164710379  by Zhichao Lu:

    Internal change

164639237  by Zhichao Lu:

    Internal change

164069251  by Zhichao Lu:

    Internal change

164058169  by Zhichao Lu:

    Internal change

163913796  by Zhichao Lu:

    Internal change

163756696  by Zhichao Lu:

    Internal change

163524665  by Zhichao Lu:

    Internal change

163393399  by Zhichao Lu:

    Internal change

163385733  by Zhichao Lu:

    Internal change

162525065  by Zhichao Lu:

    Internal change

162376984  by Zhichao Lu:

    Internal change

162026661  by Zhichao Lu:

    Internal change

161956004  by Zhichao Lu:

    Internal change

161817520  by Zhichao Lu:

    Internal change

161718688  by Zhichao Lu:

    Internal change

161624398  by Zhichao Lu:

    Internal change

161575120  by Zhichao Lu:

    Internal change

161483997  by Zhichao Lu:

    Internal change

161462189  by Zhichao Lu:

    Internal change

161452968  by Zhichao Lu:

    Internal change

161443992  by Zhichao Lu:

    Internal change

161408607  by Zhichao Lu:

    Internal change

161262084  by Zhichao Lu:

    Internal change

161214023  by Zhichao Lu:

    Internal change

161025667  by Zhichao Lu:

    Internal change

160982216  by Zhichao Lu:

    Internal change

160666760  by Zhichao Lu:

    Internal change

160570489  by Zhichao Lu:

    Internal change

160553112  by Zhichao Lu:

    Internal change

160458261  by Zhichao Lu:

    Internal change

160349302  by Zhichao Lu:

    Internal change

160296092  by Zhichao Lu:

    Internal change

160287348  by Zhichao Lu:

    Internal change

160199279  by Zhichao Lu:

    Internal change

160160156  by Zhichao Lu:

    Internal change

160151954  by Zhichao Lu:

    Internal change

160005404  by Zhichao Lu:

    Internal change

159983265  by Zhichao Lu:

    Internal change

159819896  by Zhichao Lu:

    Internal change

159749419  by Zhichao Lu:

    Internal change

159596448  by Zhichao Lu:

    Internal change

159587801  by Zhichao Lu:

    Internal change

159587342  by Zhichao Lu:

    Internal change

159476256  by Zhichao Lu:

    Internal change

159463992  by Zhichao Lu:

    Internal change

159455585  by Zhichao Lu:

    Internal change

159270798  by Zhichao Lu:

    Internal change

159256633  by Zhichao Lu:

    Internal change

159141989  by Zhichao Lu:

    Internal change

159079098  by Zhichao Lu:

    Internal change

159078559  by Zhichao Lu:

    Internal change

159077055  by Zhichao Lu:

    Internal change

159072046  by Zhichao Lu:

    Internal change

159071092  by Zhichao Lu:

    Internal change

159069262  by Zhichao Lu:

    Internal change

159037430  by Zhichao Lu:

    Internal change

159035747  by Zhichao Lu:

    Internal change

159023868  by Zhichao Lu:

    Internal change

158939092  by Zhichao Lu:

    Internal change

158912561  by Zhichao Lu:

    Internal change

158903825  by Zhichao Lu:

    Internal change

158894348  by Zhichao Lu:

    Internal change

158884934  by Zhichao Lu:

    Internal change

158878010  by Zhichao Lu:

    Internal change

158874620  by Zhichao Lu:

    Internal change

158869501  by Zhichao Lu:

    Internal change

158842623  by Zhichao Lu:

    Internal change

158801298  by Zhichao Lu:

    Internal change

158775487  by Zhichao Lu:

    Internal change

158773668  by Zhichao Lu:

    Internal change

158771394  by Zhichao Lu:

    Internal change

158668928  by Zhichao Lu:

    Internal change

158596865  by Zhichao Lu:

    Internal change

158587317  by Zhichao Lu:

    Internal change

158586348  by Zhichao Lu:

    Internal change

158585707  by Zhichao Lu:

    Internal change

158577134  by Zhichao Lu:

    Internal change

158459749  by Zhichao Lu:

    Internal change

158459678  by Zhichao Lu:

    Internal change

158328972  by Zhichao Lu:

    Internal change

158324255  by Zhichao Lu:

    Internal change

158319576  by Zhichao Lu:

    Internal change

158290802  by Zhichao Lu:

    Internal change

158273041  by Zhichao Lu:

    Internal change

158240477  by Zhichao Lu:

    Internal change

158204316  by Zhichao Lu:

    Internal change

158154161  by Zhichao Lu:

    Internal change

158077203  by Zhichao Lu:

    Internal change

158041397  by Zhichao Lu:

    Internal change

158029233  by Zhichao Lu:

    Internal change

157976306  by Zhichao Lu:

    Internal change

157966896  by Zhichao Lu:

    Internal change

157945642  by Zhichao Lu:

    Internal change

157943135  by Zhichao Lu:

    Internal change

157942158  by Zhichao Lu:

    Internal change

157897866  by Zhichao Lu:

    Internal change

157866667  by Zhichao Lu:

    Internal change

157845915  by Zhichao Lu:

    Internal change

157842592  by Zhichao Lu:

    Internal change

157832761  by Zhichao Lu:

    Internal change

157824451  by Zhichao Lu:

    Internal change

157816531  by Zhichao Lu:

    Internal change

157782130  by Zhichao Lu:

    Internal change

157733752  by Zhichao Lu:

    Internal change

157654577  by Zhichao Lu:

    Internal change

157639285  by Zhichao Lu:

    Internal change

157530694  by Zhichao Lu:

    Internal change

157518469  by Zhichao Lu:

    Internal change

157514626  by Zhichao Lu:

    Internal change

157481413  by Zhichao Lu:

    Internal change

157267863  by Zhichao Lu:

    Internal change

157263616  by Zhichao Lu:

    Internal change

157234554  by Zhichao Lu:

    Internal change

157174595  by Zhichao Lu:

    Internal change

157169681  by Zhichao Lu:

    Internal change

157156425  by Zhichao Lu:

    Internal change

157024436  by Zhichao Lu:

    Internal change

157016195  by Zhichao Lu:

    Internal change

156941658  by Zhichao Lu:

    Internal change

156880859  by Zhichao Lu:

    Internal change

156790636  by Zhichao Lu:

    Internal change

156565969  by Zhichao Lu:

    Internal change

156522345  by Zhichao Lu:

    Internal change

156518570  by Zhichao Lu:

    Internal change

156509878  by Zhichao Lu:

    Internal change

156509134  by Zhichao Lu:

    Internal change

156472497  by Zhichao Lu:

    Internal change

156471429  by Zhichao Lu:

    Internal change

156470865  by Zhichao Lu:

    Internal change

156461563  by Zhichao Lu:

    Internal change

156437521  by Zhichao Lu:

    Internal change

156334994  by Zhichao Lu:

    Internal change

156319604  by Zhichao Lu:

    Internal change

156234305  by Zhichao Lu:

    Internal change

156226207  by Zhichao Lu:

    Internal change

156215347  by Zhichao Lu:

    Internal change

156127227  by Zhichao Lu:

    Internal change

156120405  by Zhichao Lu:

    Internal change

156113752  by Zhichao Lu:

    Internal change

156098936  by Zhichao Lu:

    Internal change

155924066  by Zhichao Lu:

    Internal change

155883241  by Zhichao Lu:

    Internal change

155806887  by Zhichao Lu:

    Internal change

155641849  by Zhichao Lu:

    Internal change

155593034  by Zhichao Lu:

    Internal change

155570702  by Zhichao Lu:

    Internal change

155515306  by Zhichao Lu:

    Internal change

155514787  by Zhichao Lu:

    Internal change

155445237  by Zhichao Lu:

    Internal change

155438672  by Zhichao Lu:

    Internal change

155264448  by Zhichao Lu:

    Internal change

155222148  by Zhichao Lu:

    Internal change

155106590  by Zhichao Lu:

    Internal change

155090562  by Zhichao Lu:

    Internal change

154973775  by Zhichao Lu:

    Internal change

154972880  by Zhichao Lu:

    Internal change

154871596  by Zhichao Lu:

    Internal change

154835007  by Zhichao Lu:

    Internal change

154788175  by Zhichao Lu:

    Internal change

154731169  by Zhichao Lu:

    Internal change

154721261  by Zhichao Lu:

    Internal change

154594626  by Zhichao Lu:

    Internal change

154588305  by Zhichao Lu:

    Internal change

154578994  by Zhichao Lu:

    Internal change

154571515  by Zhichao Lu:

    Internal change

154552873  by Zhichao Lu:

    Internal change

154549672  by Zhichao Lu:

    Internal change

154463631  by Zhichao Lu:

    Internal change

154437690  by Zhichao Lu:

    Internal change

154412359  by Zhichao Lu:

    Internal change

154374026  by Zhichao Lu:

    Internal change

154361648  by Zhichao Lu:

    Internal change

154310164  by Zhichao Lu:

    Internal change

154220862  by Zhichao Lu:

    Internal change

154187281  by Zhichao Lu:

    Internal change

154186651  by Zhichao Lu:

    Internal change

154119783  by Zhichao Lu:

    Internal change

154114285  by Zhichao Lu:

    Internal change

154095717  by Zhichao Lu:

    Internal change

154057972  by Zhichao Lu:

    Internal change

154055285  by Zhichao Lu:

    Internal change

153659288  by Zhichao Lu:

    Internal change

153637797  by Zhichao Lu:

    Internal change

153561771  by Zhichao Lu:

    Internal change

153540765  by Zhichao Lu:

    Internal change

153496128  by Zhichao Lu:

    Internal change

153473323  by Zhichao Lu:

    Internal change

153368812  by Zhichao Lu:

    Internal change

153367292  by Zhichao Lu:

    Internal change

153201890  by Zhichao Lu:

    Internal change

153074177  by Zhichao Lu:

    Internal change

152980017  by Zhichao Lu:

    Internal change

152978434  by Zhichao Lu:

    Internal change

152951821  by Zhichao Lu:

    Internal change

152904076  by Zhichao Lu:

    Internal change

152883703  by Zhichao Lu:

    Internal change

152869747  by Zhichao Lu:

    Internal change

152827463  by Zhichao Lu:

    Internal change

152756886  by Zhichao Lu:

    Internal change

152752840  by Zhichao Lu:

    Internal change

152736347  by Zhichao Lu:

    Internal change

152728184  by Zhichao Lu:

    Internal change

152720120  by Zhichao Lu:

    Internal change

152710964  by Zhichao Lu:

    Internal change

152706735  by Zhichao Lu:

    Internal change

152681133  by Zhichao Lu:

    Internal change

152517758  by Zhichao Lu:

    Internal change

152516381  by Zhichao Lu:

    Internal change

152511258  by Zhichao Lu:

    Internal change

152319164  by Zhichao Lu:

    Internal change

152316404  by Zhichao Lu:

    Internal change

152309261  by Zhichao Lu:

    Internal change

152308007  by Zhichao Lu:

    Internal change

152296551  by Zhichao Lu:

    Internal change

152188069  by Zhichao Lu:

    Internal change

152158644  by Zhichao Lu:

    Internal change

152153578  by Zhichao Lu:

    Internal change

152152285  by Zhichao Lu:

    Internal change

152055035  by Zhichao Lu:

    Internal change

152036778  by Zhichao Lu:

    Internal change

152020728  by Zhichao Lu:

    Internal change

152014842  by Zhichao Lu:

    Internal change

151848225  by Zhichao Lu:

    Internal change

151741308  by Zhichao Lu:

    Internal change

151740499  by Zhichao Lu:

    Internal change

151736189  by Zhichao Lu:

    Internal change

151612892  by Zhichao Lu:

    Internal change

151599502  by Zhichao Lu:

    Internal change

151538547  by Zhichao Lu:

    Internal change

151496530  by Zhichao Lu:

    Internal change

151476070  by Zhichao Lu:

    Internal change

151448662  by Zhichao Lu:

    Internal change

151411627  by Zhichao Lu:

    Internal change

151397737  by Zhichao Lu:

    Internal change

151169523  by Zhichao Lu:

    Internal change

151148956  by Zhichao Lu:

    Internal change

150944227  by Zhichao Lu:

    Internal change

150276683  by Zhichao Lu:

    Internal change

149986687  by Zhichao Lu:

    Internal change

149218749  by Zhichao Lu:

    Internal change

PiperOrigin-RevId: 184048729

* Creates a new batch_decode method in SSD Meta architecture that can handle
  dynamic batch size.
* use combined_shapes in _get_feature_maps_spatial_dims method to handle
  dynamic batch image_size.
* Add dynamic batch size tests to check preprocess, predict and postprocess
  methods in SSD Meta architecture.

For details see our paper:
"Speed/accuracy trade-offs for modern convolutional object detectors."
Huang J, Rathod V, Sun C, Zhu M, Korattikara A, Fathi A, Fischer I,
Wojna Z, Song Y, Guadarrama S, Murphy K, CVPR 2017
https://arxiv.org/abs/1611.10012