GitLab

Updating Context R-CNN dataset tools to fix a bug in context feature bank building logic when the number of context examples in the time horizon is greater than the specified maximum, and adding capabilities to track and save the number of embeddings stored per image.

PiperOrigin-RevId: 345548385

added a new operating mode for single-instance prediction.

1) Refactored the _postprocess_keypoints_for_class_and_image function such that
it can be reused by single/multi class keypoint tasks.
2) Removed the "mod" operator to make the model compatible with WASM.

PiperOrigin-RevId: 345468250

Avoid  explicit tf.unstack in `convert_strided_predictions_to_normalized_boxes`. This enables exporting a saved model with dynamic batch size.

PiperOrigin-RevId: 345055072

PiperOrigin-RevId: 344743049

PiperOrigin-RevId: 344310944

Fix the score_converter issue, which should apply on the dimension of num_class_slots per anchor separately, not on all anchors per location together (e.g. think of softmax).

PiperOrigin-RevId: 344143469

PiperOrigin-RevId: 343920343

PiperOrigin-RevId: 343491021

PiperOrigin-RevId: 343342628

Modify adjust_gamma method to only adjust rgb channels (or a single grayscale channel), and to call tf.image.adjust_gamma on an image with values between 0 and 1.

PiperOrigin-RevId: 342911345

PiperOrigin-RevId: 342373365

PiperOrigin-RevId: 341573525

PiperOrigin-RevId: 341188685

Make label_id_offset an argument so it can be turned off when eval_util.result_dict_for_batched_example is applied on the outputs of an exported SavedModel. Exported saved models already apply label offset.

PiperOrigin-RevId: 341176846

Run inference under distribution strategy, gather outputs locally and evaluate the results with coco tools on cpu.

PiperOrigin-RevId: 341162083

* Rename sequence_projection to seq_flow_lite

* Rename sequence_projection to seq_flow_lite

PiperOrigin-RevId: 340366780

Fixes two bugs when handling verified_neg_classes and not_exhaustive_classes fields for LVIS evaluation:
(1) Before, if one of these fields was empty, the input pipeline would default to an all-ones representation; this CL turns out off this behavior for the LVIS-specific classes.
(2) Labels are now 1-indexed coming out of the _prepare_groundtruth_for_eval function in model_lib (as they should be).

PiperOrigin-RevId: 340357845

Plumb LVIS specific fields (e.g. `neg_category_ids`, `not_exhaustive_category_ids`) through input pipelines.

PiperOrigin-RevId: 339614575

PiperOrigin-RevId: 339190667

PiperOrigin-RevId: 339071313

Fix a bug of slicing boxes in _postprocess_keypoints_for_class_and_image and switch to use python assert in _get_shape.

PiperOrigin-RevId: 338693370

PiperOrigin-RevId: 338526646

PiperOrigin-RevId: 338383183

PiperOrigin-RevId: 338221628

Added few keypoint postprocessing functions to handle the one-class bounding box/keypoint use case such that the model can be converted to tf.lite format and run on CPU/GPU.

PiperOrigin-RevId: 338078454

causes different behaviors with NaNs in reduce_min/argmin functions. Replaced
the NaN values by Infs in one of the tensor to fix it.

PiperOrigin-RevId: 338069303

PiperOrigin-RevId: 338066485

Old link (http://host.robots.ox.ac.uk/pascal/VOC/voc2012/) is not available. So need to update the location of the dataset. (#9395)

PiperOrigin-RevId: 337134017

PiperOrigin-RevId: 336321500

When InputReader.sample_from_datasets_weights is set, we apply these to sample individual input files.

PiperOrigin-RevId: 336128228

PiperOrigin-RevId: 336097508

PiperOrigin-RevId: 336090589

* Merged commit includes the following changes:
326369548  by Andre Araujo:

    Fix import issues.

--
326159826  by Andre Araujo:

    Changed the implementation of the cosine weights from Keras layer to tf.Variable to manually control for L2 normalization.

--
326139082  by Andre Araujo:

    Support local feature matching using ratio test.

    To allow for easily choosing which matching type to use, we rename a flag/argument and modify all related files to avoid breakages.

    Also include a small change when computing nearest neighbors for geometric matching, to parallelize computation, which saves a little bit of time during execution (argument "n_jobs=-1").

--
326119848  by Andre Araujo:

    Option to measure DELG latency taking binarization into account.

--
324316608  by Andre Araujo:

    DELG global features training.

--
323693131  by Andre Araujo:

    PY3 conversion for delf public lib.

--
3210...

PiperOrigin-RevId: 335521712

PiperOrigin-RevId: 335067840