GitLab

247226201  by ronnyvotel:

    Updating the visualization tools to accept unique_ids for color coding.

--
247067830  by Zhichao Lu:

    Add box_encodings_clip_range options for the convolutional box predictor (for TPU compatibility).

--
246888475  by Zhichao Lu:

    Remove unused _update_eval_steps function.

--
246163259  by lzc:

    Add a gather op that can handle ignore indices (which are "-1"s in this case).

--
246084944  by Zhichao Lu:

    Keras based implementation for SSD + MobilenetV2 + FPN.

--
245544227  by rathodv:

    Add batch_get_targets method to target assigner module to gather any groundtruth tensors based on the results of target assigner.

--
245540854  by rathodv:

    Update target assigner to return match tensor instead of a match object.

--
245434441  by Zhichao Lu:

    Add README for tpu_exporters package.

--
245381834  by lzc:

    Internal change.

--
245298983  by Zhichao Lu:

    Add conditional_shape_resizer to config_util

--
245134666  by Zhichao Lu:

    Adds ConditionalShapeResizer to the ImageResizer proto which enables resizing only if input image height or width is is greater or smaller than a certain size. Also enables specification of resize method in resize_to_{max, min}_dimension methods.

--
245093975  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (faster-rcnn)

--
245072421  by Zhichao Lu:

    Adds a new image resizing method "resize_to_max_dimension" which resizes images only if a dimension is greater than the maximum desired value while maintaining aspect ratio.

--
244946998  by lzc:

    Internal Changes.

--
244943693  by Zhichao Lu:

    Add a custom config to mobilenet v2 that makes it more detection friendly.

--
244754158  by derekjchow:

    Internal change.

--
244699875  by Zhichao Lu:

    Add check_range=False to box_list_ops.to_normalized_coordinates when training
    for instance segmentation.  This is consistent with other calls when training
    for object detection.  There could be wrongly annotated boxes in the dataset.

--
244507425  by rathodv:

    Support bfloat16 for ssd models.

--
244399982  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (ssd)

--
244209387  by Zhichao Lu:

    Internal change.

--
243922296  by rathodv:

    Change `raw_detection_scores` to contain softmax/sigmoid scores (not logits) for `raw_ detection_boxes`.

--
243883978  by Zhichao Lu:

    Add a sample fully conv config.

--
243369455  by Zhichao Lu:

    Fix regularization loss gap in Keras and Slim.

--
243292002  by lzc:

    Internal changes.

--
243097958  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (ssd model)

--
243007177  by Zhichao Lu:

    Exporting SavedModel for Object Detection TPU inference. (ssd model)

--
242776550  by Zhichao Lu:

    Make object detection pre-processing run on GPU.  tf.map_fn() uses
    TensorArrayV3 ops, which have no int32 GPU implementation.  Cast to int64,
    then cast back to int32.

--
242723128  by Zhichao Lu:

    Using sorted dictionaries for additional heads in non_max_suppression to ensure tensor order

--
242495311  by Zhichao Lu:

    Update documentation to reflect new TFLite examples repo location

--
242230527  by Zhichao Lu:

    Fix Dropout bugs for WeightSharedConvolutionalBoxPred.

--
242226573  by Zhichao Lu:

    Create Keras-based WeightSharedConvolutionalBoxPredictor.

--
241806074  by Zhichao Lu:

    Add inference in unit tests of TFX OD template.

--
241641498  by lzc:

    Internal change.

--
241637481  by Zhichao Lu:

    matmul_crop_and_resize(): Switch to dynamic shaping, so that not all dimensions are required to be known.

--
241429980  by Zhichao Lu:

    Internal change

--
241167237  by Zhichao Lu:

    Adds a faster_rcnn_inception_resnet_v2 Keras feature extractor, and updates the model builder to construct it.

--
241088616  by Zhichao Lu:

    Make it compatible with different dtype, e.g. float32, bfloat16, etc.

--
240897364  by lzc:

    Use image_np_expanded in object_detection_tutorial notebook.

--
240890393  by Zhichao Lu:

    Disable multicore inference for OD template as its not yet compatible.

--
240352168  by Zhichao Lu:

    Make SSDResnetV1FpnFeatureExtractor not protected to allow inheritance.

--
240351470  by lzc:

    Internal change.

--
239878928  by Zhichao Lu:

    Defines Keras box predictors for Faster RCNN and RFCN

--
239872103  by Zhichao Lu:

    Delete duplicated inputs in test.

--
239714273  by Zhichao Lu:

    Adding scope variable to all class heads

--
239698643  by Zhichao Lu:

    Create FPN feature extractor for object detection.

--
239696657  by Zhichao Lu:

    Internal Change.

--
239299404  by Zhichao Lu:

    Allows the faster rcnn meta-architecture to support Keras subcomponents

--
238502595  by Zhichao Lu:

    Lay the groundwork for symmetric quantization.

--
238496885  by Zhichao Lu:

    Add flexible_grid_anchor_generator

--
238138727  by lzc:

    Remove dead code.

    _USE_C_SHAPES has been forced True in TensorFlow releases since
    TensorFlow 1.9
    (https://github.com/tensorflow/tensorflow/commit/1d74a69443f741e69f9f52cb6bc2940b4d4ae3b7)

--
238123936  by rathodv:

    Add num_matched_groundtruth summary to target assigner in SSD.

--
238103345  by ronnyvotel:

    Raising error if input file pattern does not match any files.
    Also printing the number of evaluation images for coco metrics.

--
238044081  by Zhichao Lu:

    Fix docstring to state the correct dimensionality of `class_predictions_with_background`.

--
237920279  by Zhichao Lu:

    [XLA] Rework debug flags for dumping HLO.

    The following flags (usually passed via the XLA_FLAGS envvar) are removed:

      xla_dump_computations_to
      xla_dump_executions_to
      xla_dump_ir_to
      xla_dump_optimized_hlo_proto_to
      xla_dump_per_pass_hlo_proto_to
      xla_dump_unoptimized_hlo_proto_to
      xla_generate_hlo_graph
      xla_generate_hlo_text_to
      xla_hlo_dump_as_html
      xla_hlo_graph_path
      xla_log_hlo_text

    The following new flags are added:

      xla_dump_to
      xla_dump_hlo_module_re
      xla_dump_hlo_pass_re
      xla_dump_hlo_as_text
      xla_dump_hlo_as_proto
      xla_dump_hlo_as_dot
      xla_dump_hlo_as_url
      xla_dump_hlo_as_html
      xla_dump_ir
      xla_dump_hlo_snapshots

    The default is not to dump anything at all, but as soon as some dumping flag is
    specified, we enable the following defaults (most of which can be overridden).

     * dump to stdout (overridden by --xla_dump_to)
     * dump HLO modules at the very beginning and end of the optimization pipeline
     * don't dump between any HLO passes (overridden by --xla_dump_hlo_pass_re)
     * dump all HLO modules (overridden by --xla_dump_hlo_module_re)
     * dump in textual format (overridden by
       --xla_dump_hlo_as_{text,proto,dot,url,html}).

    For example, to dump optimized and unoptimized HLO text and protos to /tmp/foo,
    pass

      --xla_dump_to=/tmp/foo --xla_dump_hlo_as_text --xla_dump_hlo_as_proto

    For details on these flags' meanings, see xla.proto.

    The intent of this change is to make dumping both simpler to use and more
    powerful.

    For example:

     * Previously there was no way to dump the HLO module during the pass pipeline
       in HLO text format; the only option was --dump_per_pass_hlo_proto_to, which
       dumped in proto format.

       Now this is --xla_dump_pass_re=.* --xla_dump_hlo_as_text.  (In fact, the
       second flag is not necessary in this case, as dumping as text is the
       default.)

     * Previously there was no way to dump HLO as a graph before and after
       compilation; the only option was --xla_generate_hlo_graph, which would dump
       before/after every pass.

       Now this is --xla_dump_hlo_as_{dot,url,html} (depending on what format you
       want the graph in).

     * Previously, there was no coordination between the filenames written by the
       various flags, so info about one module might be dumped with various
       filename prefixes.  Now the filenames are consistent and all dumps from a
       particular module are next to each other.

    If you only specify some of these flags, we try to figure out what you wanted.
    For example:

     * --xla_dump_to implies --xla_dump_hlo_as_text unless you specify some
       other --xla_dump_as_* flag.

     * --xla_dump_hlo_as_text or --xla_dump_ir implies dumping to stdout unless you
       specify a different --xla_dump_to directory.  You can explicitly dump to
       stdout with --xla_dump_to=-.

    As part of this change, I simplified the debugging code in the HLO passes for
    dumping HLO modules.  Previously, many tests explicitly VLOG'ed the HLO module
    before, after, and sometimes during the pass.  I removed these VLOGs.  If you
    want dumps before/during/after an HLO pass, use --xla_dump_pass_re=<pass_name>.

--
237510043  by lzc:

    Internal Change.

--
237469515  by Zhichao Lu:

    Parameterize model_builder.build in inputs.py.

--
237293511  by rathodv:

    Remove multiclass_scores from tensor_dict in transform_data_fn always.

--
237260333  by ronnyvotel:

    Updating faster_rcnn_meta_arch to define prediction dictionary fields that are batched.

--

PiperOrigin-RevId: 247226201

The evaluation crashes in python3 if iteritems() is used instead of items()

* 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:
207771702  by Zhichao Lu:

    Refactoring evaluation utilities so that it is easier to introduce new DetectionEvaluators with eval_metric_ops.

--
207758641  by Zhichao Lu:

    Require tensorflow version 1.9+ for running object detection API.

--
207641470  by Zhichao Lu:

    Clip `num_groundtruth_boxes` in pad_input_data_to_static_shapes() to `max_num_boxes`. This prevents a scenario where tensors are sliced to an invalid range in model_lib.unstack_batch().

--
207621728  by Zhichao Lu:

    This CL adds a FreezableBatchNorm that inherits from the Keras BatchNormalization layer, but supports freezing the `training` parameter at construction time instead of having to do it in the `call` method.

    It also adds a method to the `KerasLayerHyperparams` class that will build an appropriate FreezableBatchNorm layer according to the hyperparameter configuration. If batch_norm is disabled, this method returns and Identity layer.

    These will be used to simplify the conversion to Keras APIs.

--
207610524  by Zhichao Lu:

    Update anchor generators and box predictors for python3 compatibility.

--
207585122  by Zhichao Lu:

    Refactoring convolutional box predictor into separate prediction heads.

--
207549305  by Zhichao Lu:

    Pass all 1s for batch weights if nothing is specified in GT.

--
207336575  by Zhichao Lu:

    Move the new argument 'target_assigner_instance' to the end of the list of arguments to the ssd_meta_arch constructor for backwards compatibility.

--
207327862  by Zhichao Lu:

    Enable support for float output in quantized custom op for postprocessing in SSD Mobilenet model.

--
207323154  by Zhichao Lu:

    Bug fix: change dict.iteritems() to dict.items()

--
207301109  by Zhichao Lu:

    Integrating expected_classification_loss_under_sampling op as an option in the ssd_meta_arch

--
207286221  by Zhichao Lu:

    Adding an option to weight regression loss with foreground scores from the ground truth labels.

--
207231739  by Zhichao Lu:

    Explicitly mentioning the argument names when calling the batch target assigner.

--
207206356  by Zhichao Lu:

    Add include_trainable_variables field to train config to better handle trainable variables.

--
207135930  by Zhichao Lu:

    Internal change.

--
206862541  by Zhichao Lu:

    Do not unpad the outputs from batch_non_max_suppression before sampling.

    Since BalancedPositiveNegativeSampler takes an indicator for valid positions to sample from we can pass the output from NMS directly into Sampler.

--

PiperOrigin-RevId: 207771702

* Remove unused doc.

196161788  by Zhichao Lu:

    Add eval_on_train_steps parameter.

    Since the number of samples in train dataset is usually different to the number of samples in the eval dataset.

--
196151742  by Zhichao Lu:

    Add an optional random sampling process for SSD meta arch and update mean stddev coder to use default std dev when corresponding tensor is not added to boxlist field.

--
196148940  by Zhichao Lu:

    Release ssdlite mobilenet v2 coco trained model.

--
196058528  by Zhichao Lu:

    Apply FPN feature map generation before we add additional layers on top of resnet feature extractor.

--
195818367  by Zhichao Lu:

    Add support for exporting detection keypoints.

--
195745420  by Zhichao Lu:

    Introduce include_metrics_per_category option to Object Detection eval_config.

--
195734733  by Zhichao Lu:

    Rename SSDLite config to be more explicit.

--
195717383  by Zhichao Lu:

    Add quantized training to object_detection.

--
195683542  by...

* Adding option for one_box_for_all_classes to the box_predictor

PiperOrigin-RevId: 192813444

* Extend to accept different ratios of conv channels.

PiperOrigin-RevId: 192837477

* Remove inaccurate caveat from proto file.

PiperOrigin-RevId: 192850747

* Add option to set dropout for classification net in weight shared box predictor.

PiperOrigin-RevId: 192922089

* fix flakiness in testSSDRandomCropWithMultiClassScores due to randomness.

PiperOrigin-RevId: 193067658

* Post-process now works again in train mode.

PiperOrigin-RevId: 193087707

* Adding support for reading in logits as groundtruth labels and applying an optional temperature (scaling) before softmax in support of distillation.

PiperOrigin-RevId: 193119411

* Add a util function to visualize value histogram as a tf.summary.image.

PiperOrigin-RevId: 193137342

* Do not add batch norm parameters to final conv2d ops that predict boxes encodings and class scores in weight shared conv box predictor.

This allows us to set proper bias and force initial predictions to be background when using focal loss.

PiperOrigin-RevId: 193204364

* Make sure the final layers are also resized proportional to conv_depth_ratio.

PiperOrigin-RevId: 193228972

* Remove deprecated batch_norm_trainable field from ssd mobilenet v2 config

PiperOrigin-RevId: 193244778

* Updating coco evaluation metrics to allow for a batch of image info, rather than a single image.

PiperOrigin-RevId: 193382651

* Update protobuf requirements to 3+ in installation docs.

PiperOrigin-RevId: 193409179

* Add support for training keypoints.

PiperOrigin-RevId: 193576336

* Fix data augmentation functions.

PiperOrigin-RevId: 193737238

* Read the default batch size from config file.

PiperOrigin-RevId: 193959861

* Fixing a bug in the coco evaluator.

PiperOrigin-RevId: 193974479

* num_gt_boxes_per_image and num_det_boxes_per_image value incorrect.
Should be not the expand dim.

PiperOrigin-RevId: 194122420

* Add option to evaluate any checkpoint (without requiring write access to that directory and overwriting any existing logs there).

PiperOrigin-RevId: 194292198

* PiperOrigin-RevId: 190346687

* - Expose slim arg_scope function to compute keys to enable tessting.
- Add is_training=None option to mobinenet arg_scopes. This allows the users to set is_training from an outer scope.

PiperOrigin-RevId: 190997959

* Add an option to not set slim arg_scope for batch_norm is_training parameter. This enables users to set the is_training parameter from an outer scope.

PiperOrigin-RevId: 191611934

* PiperOrigin-RevId: 191955231

* PiperOrigin-RevId: 193254125

* PiperOrigin-RevId: 193371562

* PiperOrigin-RevId: 194085628

* Force cast of num_classes to integer

PiperOrigin-RevId: 188335318

* Updating config util to allow overwriting of cosine decay learning rates.

PiperOrigin-RevId: 188338852

* Make box_list_ops.py and box_list_ops_test.py work with C API enabled.

The C API has improved shape inference over the original Python
code. This causes some previously-working conds to fail. Switching to smart_cond fixes this.

Another effect of the improved shape inference is that one of the
failures tested gets caught earlier, so I modified the test to reflect
this.

PiperOrigin-RevId: 188409792

* Fix parallel event file writing issue.

Without this change, the event files might get corrupted when multiple evaluations are run in parallel.

PiperOrigin-RevId: 188502560

* Deprecating the boolean flag of from_detection_checkpoint.

Replace with a string field fine_tune_checkpoint_type to train_config to provide extensibility. The fine_tune_checkpoint_type can currently take value of `detection`, `classification`, or others when the restore_map is overwritten.

PiperOrigin-RevId: 188518685

* Automated g4 rollback of changelist 188502560

PiperOrigin-RevId: 188519969

* Introducing eval metrics specs for Coco Mask metrics. This allows metrics to be computed in tensorflow using the tf.learn Estimator.

PiperOrigin-RevId: 188528485

* Minor fix to make object_detection/metrics/coco_evaluation.py python3 compatible.

PiperOrigin-RevId: 188550683

* Updating eval_util to handle eval_metric_ops from multiple `DetectionEvaluator`s.

PiperOrigin-RevId: 188560474

* Allow tensor input for new_height and new_width for resize_image.

PiperOrigin-RevId: 188561908

* Fix typo in fine_tune_checkpoint_type name in trainer.

PiperOrigin-RevId: 188799033

* Adding mobilenet feature extractor to object detection.

PiperOrigin-RevId: 188916897

* Allow label maps to optionally contain an explicit background class with id zero.

PiperOrigin-RevId: 188951089

* Fix boundary conditions in random_pad_to_aspect_ratio to ensure that min_scale is always less than max_scale.

PiperOrigin-RevId: 189026868

* Fallback on from_detection_checkpoint option if fine_tune_checkpoint_type isn't set.

PiperOrigin-RevId: 189052833

* Add proper names for learning rate schedules so we don't see cryptic names on tensorboard.

PiperOrigin-RevId: 189069837

* Enforcing that all datasets are batched (and then unbatched in the model) with batch_size >= 1.

PiperOrigin-RevId: 189117178

* Adding regularization to total loss returned from DetectionModel.loss().

PiperOrigin-RevId: 189189123

* Standardize the names of loss scalars (for SSD, Faster R-CNN and R-FCN) in both training and eval so they can be compared on tensorboard.

Log localization and classification losses in evaluation.

PiperOrigin-RevId: 189189940

* Remove negative test from box list ops test.

PiperOrigin-RevId: 189229327

* Add an option to warmup learning rate in manual stepping schedule.

PiperOrigin-RevId: 189361039

* Replace tf.contrib.slim.tfexample_decoder.LookupTensor with object_detection.data_decoders.tf_example_decoder.LookupTensor.

PiperOrigin-RevId: 189388556

* Force regularization summary variables under specific family names.

PiperOrigin-RevId: 189393190

* Automated g4 rollback of changelist 188619139

PiperOrigin-RevId: 189396001

* Remove step 0 schedule since we do a hard check for it after cl/189361039

PiperOrigin-RevId: 189396697

* PiperOrigin-RevId: 189040463

* PiperOrigin-RevId: 189059229

* PiperOrigin-RevId: 189214402

* Force regularization summary variables under specific family names.

PiperOrigin-RevId: 189393190

* Automated g4 rollback of changelist 188619139

PiperOrigin-RevId: 189396001

* Make slim python3 compatible.

* Monir fixes.

* Add TargetAssignment summaries in a separate family.

PiperOrigin-RevId: 189407487

* 1. Setting `family` keyword arg prepends the summary names twice with the same name. Directly adding family suffix to the name gets rid of this problem.
2. Make sure the eval losses have the same name.

PiperOrigin-RevId: 189434618

* Minor fixes to make object detection tf 1.4 compatible.

PiperOrigin-RevId: 189437519

* Call the base of mobilenet_v1 feature extractor under the right arg scope and set batchnorm is_training based on the value passed in the constructor.

PiperOrigin-RevId: 189460890

* Automated g4 rollback of changelist 188409792

PiperOrigin-RevId: 189463882

* Update object detection syncing.

PiperOrigin-RevId: 189601955

* Add an option to warmup learning rate, hold it constant for a certain number of steps and cosine decay it.

PiperOrigin-RevId: 189606169

* Let the proposal feature extractor function in faster_rcnn meta architectures return the activations (end_points).

PiperOrigin-RevId: 189619301

* Fixed bug which caused masks to be mostly zeros (caused by detection_boxes being in absolute coordinates if scale_to_absolute=True.

PiperOrigin-RevId: 189641294

* Open sourcing Mobilenetv2 + SSDLite.

PiperOrigin-RevId: 189654520

* Remove unused files.

PiperOrigin-RevId: 187527188

185215255  by Zhichao Lu:

    Stop populating image/object/class/text field when generating COCO tf record.

--
185213306  by Zhichao Lu:

    Use the params batch size and not the one from train_config in input_fn

--
185209081  by Zhichao Lu:

    Handle the case when there are no ground-truth masks for an image.

--
185195531  by Zhichao Lu:

    Remove unstack and stack operations on features from third_party/object_detection/model.py.

--
185195017  by Zhichao Lu:

    Matrix multiplication based gather op implementation.

--
185187744  by Zhichao Lu:

    Fix eval_util minor issue.

--
185098733  by Zhichao Lu:

    Internal change

185076656  by Zhichao Lu:

    Increment the amount of boxes for coco17.

--
185074199  by Zhichao Lu:

    Add config for SSD Resnet50 v1 with FPN.

--
185060199  by Zhichao Lu:

    Fix a bug in clear_detections.
    This method set detection_keys to an empty dictionary instead of an empty set. I've refactored so that this ...

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 s...