GitLab

* Merged commit includes the following changes:
202804536  by Zhichao Lu:

    Return tf.data.Dataset from input_fn that goes into the estimator and use PER_HOST_V2 option for tpu input pipeline config.

    This change shaves off 100ms per step resulting in 25 minutes of total reduced training time for ssd mobilenet v1 (15k steps to convergence).

--
202769340  by Zhichao Lu:

    Adding as_matrix() transformation for image-level labels.

--
202768721  by Zhichao Lu:

    Challenge evaluation protocol modification: adding labelmaps creation.

--
202750966  by Zhichao Lu:

    Add the explicit names to two output nodes.

--
202732783  by Zhichao Lu:

    Enforcing that batch size is 1 for evaluation, and no original images are retained during evaluation when use_tpu=False (to avoid dynamic shapes).

--
202425430  by Zhichao Lu:

    Refactor input pipeline to improve performance.

--
202406389  by Zhichao Lu:

    Only check the validity of `warmup_learning_rate` if it will be used.

--
202330450  by Zhichao Lu:

    Adding the description of the flag input_image_label_annotations_csv to add
      image-level labels to tf.Example.

--
202029012  by Zhichao Lu:

    Enabling displaying relationship name in the final metrics output.

--
202024010  by Zhichao Lu:

    Update to the public README.

--
201999677  by Zhichao Lu:

    Fixing the way negative labels are handled in VRD evaluation.

--
201962313  by Zhichao Lu:

    Fix a bug in resize_to_range.

--
201808488  by Zhichao Lu:

    Update ssd_inception_v2_pets.config to use right filename of pets dataset tf records.

--
201779225  by Zhichao Lu:

    Update object detection API installation doc

--
201766518  by Zhichao Lu:

    Add shell script to create pycocotools package for CMLE.

--
201722377  by Zhichao Lu:

    Removes verified_labels field and uses groundtruth_image_classes field instead.

--
201616819  by Zhichao Lu:

    Disable eval_on_tpu since eval_metrics is not setup to execute on TPU.
    Do not use run_config.task_type to switch tpu mode for EVAL,
    since that won't work in unit test.
    Expand unit test to verify that the same instantiation of the Estimator can independently disable eval on TPU whereas training is enabled on TPU.

--
201524716  by Zhichao Lu:

    Disable export model to TPU, inference is not compatible with TPU.
    Add GOOGLE_INTERNAL support in object detection copy.bara.sky

--
201453347  by Zhichao Lu:

    Fixing bug when evaluating the quantized model.

--
200795826  by Zhichao Lu:

    Fixing parsing bug: image-level labels are parsed as tuples instead of numpy
    array.

--
200746134  by Zhichao Lu:

    Adding image_class_text and image_class_label fields into tf_example_decoder.py

--
200743003  by Zhichao Lu:

    Changes to model_main.py and model_tpu_main to enable training and continuous eval.

--
200736324  by Zhichao Lu:

    Replace deprecated squeeze_dims argument.

--
200730072  by Zhichao Lu:

    Make detections only during predict and eval mode while creating model function

--
200729699  by Zhichao Lu:

    Minor correction to internal documentation (definition of Huber loss)

--
200727142  by Zhichao Lu:

    Add command line parsing as a set of flags using argparse and add header to the
    resulting file.

--
200726169  by Zhichao Lu:

    A tutorial on running evaluation for the Open Images Challenge 2018.

--
200665093  by Zhichao Lu:

    Cleanup on variables_helper_test.py.

--
200652145  by Zhichao Lu:

    Add an option to write (non-frozen) graph when exporting inference graph.

--
200573810  by Zhichao Lu:

    Update ssd_mobilenet_v1_coco and ssd_inception_v2_coco download links to point to a newer version.

--
200498014  by Zhichao Lu:

    Add test for groundtruth mask resizing.

--
200453245  by Zhichao Lu:

    Cleaning up exporting_models.md along with exporting scripts

--
200311747  by Zhichao Lu:

    Resize groundtruth mask to match the size of the original image.

--
200287269  by Zhichao Lu:

    Having a option to use custom MatMul based crop_and_resize op as an alternate to the TF op in Faster-RCNN

--
200127859  by Zhichao Lu:

    Updating the instructions to run locally with new binary. Also updating pets configs since file path naming has changed.

--
200127044  by Zhichao Lu:

    A simpler evaluation util to compute Open Images Challenge
    2018 metric (object detection track).

--
200124019  by Zhichao Lu:

    Freshening up configuring_jobs.md

--
200086825  by Zhichao Lu:

    Make merge_multiple_label_boxes work for ssd model.

--
199843258  by Zhichao Lu:

    Allows inconsistent feature channels to be compatible with WeightSharedConvolutionalBoxPredictor.

--
199676082  by Zhichao Lu:

    Enable an override for `InputReader.shuffle` for object detection pipelines.

--
199599212  by Zhichao Lu:

    Markdown fixes.

--
199535432  by Zhichao Lu:

    Pass num_additional_channels to tf.example decoder in predict_input_fn.

--
199399439  by Zhichao Lu:

    Adding `num_additional_channels` field to specify how many additional channels to use in the model.

--

PiperOrigin-RevId: 202804536

* Add original model builder and docs back.

Fix the Bug that evaluator don't load the min max values of fake_quantize op from lastest checkpoint

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

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...

195269567  by Zhichao Lu:

    Removing image summaries during train mode.

--
195147413  by Zhichao Lu:

    SSDLite config for mobilenet v2.

--
194883585  by Zhichao Lu:

    Simplify TPU compatible nearest neighbor upsampling using reshape and broadcasting.

--
194851009  by Zhichao Lu:

    Include ava v2.1 detection models in model zoo.

--
194292198  by Zhichao Lu:

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

--
194122420  by Zhichao Lu:

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

--
193974479  by Zhichao Lu:

    Fixing a bug in the coco evaluator.

--
193959861  by Zhichao Lu:

    Read the default batch size from config file.

--
193737238  by Zhichao Lu:

    Fix data augmentation functions.

--
193576336  by Zhichao Lu:

    Add support for training keypoints.

--
193409179  by Zhichao Lu:

    Update protobuf requirements to 3+ in installation docs.

--
193382651  by Zhichao Lu:

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

--
193244778  by Zhichao Lu:

    Remove deprecated batch_norm_trainable field from ssd mobilenet v2 config

--
193228972  by Zhichao Lu:

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

--
193204364  by Zhichao Lu:

    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.

--
193137342  by Zhichao Lu:

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

--
193119411  by Zhichao Lu:

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

--
193087707  by Zhichao Lu:

    Post-process now works again in train mode.

--
193067658  by Zhichao Lu:

    fix flakiness in testSSDRandomCropWithMultiClassScores due to randomness.

--
192922089  by Zhichao Lu:

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

--
192850747  by Zhichao Lu:

    Remove inaccurate caveat from proto file.

--
192837477  by Zhichao Lu:

    Extend to accept different ratios of conv channels.

--
192813444  by Zhichao Lu:

    Adding option for one_box_for_all_classes to the box_predictor

--
192624207  by Zhichao Lu:

    Update to trainer to allow for reading multiclass scores

--
192583425  by Zhichao Lu:

    Contains implementation of Visual Relations Detection evaluation metric (per
    image evaluation).

--
192529600  by Zhichao Lu:

    Modify the ssd meta arch to allow the option of not adding an implicit background class.

--
192512429  by Zhichao Lu:

    Refactor model_tpu_main.py files and move continuous eval loop into model_lib.py

--
192494267  by Zhichao Lu:

    Update create_pascal_tf_record.py and create_pet_tf_record.py

--
192485456  by Zhichao Lu:

    Enforcing that all eval metric ops have valid python strings.

--
192472546  by Zhichao Lu:

    Set regularize_depthwise to true in mobilenet_v1_argscope.

--
192421843  by Zhichao Lu:

    Refactoring of Mask-RCNN to put all mask prediction code in third stage.

--
192320460  by Zhichao Lu:

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

--
192226678  by Zhichao Lu:

    Access TPUEstimator and CrossShardOptimizer from tf namesspace.

--
192195514  by Zhichao Lu:

    Fix test that was flaky due to randomness

--
192166224  by Zhichao Lu:

    Minor fixes to match git repo.

--
192147130  by Zhichao Lu:

    use shape utils for assertion in feature extractor.

--
192132440  by Zhichao Lu:

    Class agnostic masks for mask_rcnn

--
192006190  by Zhichao Lu:

    Add learning rate summary in EVAL mode in model.py

--
192004845  by Zhichao Lu:

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

--
191957195  by Zhichao Lu:

    Add classification_loss and localiztion_loss metrics for TPU jobs.

--
191932855  by Zhichao Lu:

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

--
191787921  by Zhichao Lu:

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

--
191743097  by Zhichao Lu:

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

--
191668425  by Zhichao Lu:

    Internal change.

--
191649512  by Zhichao Lu:

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

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

--
191620303  by Zhichao Lu:

    Modifications to the preprocessor to support multiclass scores

--

PiperOrigin-RevId: 195269567

* 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

PiperOrigin-RevId: 192624207

image evaluation).

PiperOrigin-RevId: 192583425

PiperOrigin-RevId: 192529600

PiperOrigin-RevId: 192512429

PiperOrigin-RevId: 192494267

PiperOrigin-RevId: 192485456

PiperOrigin-RevId: 192472546

PiperOrigin-RevId: 192421843

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

PiperOrigin-RevId: 192320460

PiperOrigin-RevId: 192226678

PiperOrigin-RevId: 192195514

PiperOrigin-RevId: 192166224

PiperOrigin-RevId: 192147130

PiperOrigin-RevId: 192132440

PiperOrigin-RevId: 192006190

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

PiperOrigin-RevId: 192004845

PiperOrigin-RevId: 191957195

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

PiperOrigin-RevId: 191932855

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

PiperOrigin-RevId: 191787921

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

PiperOrigin-RevId: 191743097

PiperOrigin-RevId: 191668425

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

191649512  by Zhichao Lu:

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

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

--
191620303  by Zhichao Lu:

    Modifications to the preprocessor to support multiclass scores

--
191610773  by Zhichao Lu:

    Adding multiclass_scores to InputDataFields and adding padding for multiclass_scores.

--
191595011  by Zhichao Lu:

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

--
191449408  by Zhichao Lu:

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

--
191437008  by Zhichao Lu:

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

--
191385254  by Zhichao Lu:

    Add config rewrite flag to eval.py

--
191382500  by Zhichao Lu:

    Fix bug for config_util.

--

PiperOrigin-RevId: 191649512

PiperOrigin-RevId: 191377056

PiperOrigin-RevId: 191369912

PiperOrigin-RevId: 191358138