GitLab

PiperOrigin-RevId: 352601466

PiperOrigin-RevId: 351619683

PiperOrigin-RevId: 351610384

* 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.

--
321046157  by Andre Araujo:

    Purely Google refactor

--

PiperOrigin-RevId: 326369548

* Added export of delg_model module.

* README update to explain training DELG global features head

* Added guidelines for DELF hyperparameter values

* Fixed typo

* Added mention about remaining training flags.

* Merged commit includes the following changes:
334723489  by Andre Araujo:

    Backpropagate global and attention layers together.

--
334228310  by Andre Araujo:

    Enable scaling of local feature locations to the resized resolution.

--

PiperOrigin-RevId: 334723489

* Merged commit includes the following changes:
347032253  by Andre Araujo:

    Updated local and global_and_local model export scripts for exporting models trained with the autoencoder layer.

--
344312455  by Andre Araujo:

    Implement autoencoder in training pipeline.

--
341116593  by Andre Araujo:

    Reduce the default save_interval, to get more frequent checkpoints.

--
341111808  by Andre Araujo:

    Allow checkpoint restoration in DELF training, to enable resuming of training jobs.

--
340138315  by Andre Araujo:

    DELF training script: make it always save the last checkpoint.

--
338731551  by Andre Araujo:

    Add image_size flag in DELF/G OSS training script.

--
338684879  by Andre Araujo:

    Clean up summaries in DELF/G training script.

    - Previously, the call to tf.summary.record_if() was not working, which led to summaries being recorded at every step, leading to too large events files. This is fixed.
    - Previously, some summaries were computed at iteration k, while others at iteration k+1. Now, we standardize summary computations to always run after backpropagation (which means that summaries are reported for step k+1, referring to the batch k).
    - Added a new summary: number of global steps per second; useful to see how fast training is making progress.

    Also a few other small modifications are included:
    - Improved description of the train.py script.
    - Some small automatic reformattings.

--

PiperOrigin-RevId: 347032253

* Updated README for training with autoencoder

* DELF README update after first review.
Co-authored-by: Andre Araujo <andrearaujo@google.com>

FPN network.

PiperOrigin-RevId: 351255218

for object detection and keypoint estimation tasks.

PiperOrigin-RevId: 350640225

PiperOrigin-RevId: 347837387

* Merged commit includes the following changes:
253126424  by Andre Araujo:

    Scripts to compute metrics for Google Landmarks dataset.

    Also, a small fix to metric in retrieval case: avoids duplicate predicted images.

--
253118971  by Andre Araujo:

    Metrics for Google Landmarks dataset.

--
253106953  by Andre Araujo:

    Library to read files from Google Landmarks challenges.

--
250700636  by Andre Araujo:

    Handle case of aggregation extraction with empty set of input features.

--
250516819  by Andre Araujo:

    Add minimum size for DELF extractor.

--
250435822  by Andre Araujo:

    Add max_image_size/min_image_size for open-source DELF proto / module.

--
250414606  by Andre Araujo:

    Refactor extract_aggregation to allow reuse with different datasets.

--
250356863  by Andre Araujo:

    Remove unnecessary cmd_args variable from boxes_and_features_extraction.

--
249783379  by Andre Araujo:

    Create directory for writing mapping file if it does not exist.

--
249581591  by Andre Araujo:

    Refactor scripts to extract boxes and features from images in Revisited datasets.
    Also, change tf.logging.info --> print for easier logging in open source code.

--
249511821  by Andre Araujo:

    Small change to function for file/directory handling.

--
249289499  by Andre Araujo:

    Internal change.

--

PiperOrigin-RevId: 253126424

* Updating DELF init to adjust to latest changes

* Editing init files for python packages

* Edit D2R dataset reader to work with py3.

PiperOrigin-RevId: 253135576

* DELF package: fix import ordering

* Adding new requirements to setup.py

* Adding init file for training dir

* Merged commit includes the following changes:

FolderOrigin-RevId: /google/src/cloud/andrearaujo/delf_oss/google3/..

* Adding init file for training subdirs

* Working version of DELF training

* Internal change.

PiperOrigin-RevId: 253248648

* Fix variance loading in open-source code.

PiperOrigin-RevId: 260619120

* Separate image re-ranking as a standalone library, and add metric writing to dataset library.

PiperOrigin-RevId: 260998608

* Tool to read written D2R Revisited datasets metrics file. Test is added.

Also adds a unit test for previously-existing SaveMetricsFile function.

PiperOrigin-RevId: 263361410

* Add optional resize factor for feature extraction.

PiperOrigin-RevId: 264437080

* Fix NumPy's new version spacing changes.

PiperOrigin-RevId: 265127245

* Maker image matching function visible, and add support for RANSAC seed.

PiperOrigin-RevId: 277177468

* Avoid matplotlib failure due to missing display backend.

PiperOrigin-RevId: 287316435

* Removes tf.contrib dependency.

PiperOrigin-RevId: 288842237

* Fix tf contrib removal for feature_aggregation_extractor.

PiperOrigin-RevId: 289487669

* Merged commit includes the following changes:
309118395  by Andre Araujo:

    Make DELF open-source code compatible with TF2.

--
309067582  by Andre Araujo:

    Handle image resizing rounding properly for python extraction.

    New behavior is tested with unit tests.

--
308690144  by Andre Araujo:

    Several changes to improve DELF model/training code and make it work in TF 2.1.0:
    - Rename some files for better clarity
    - Using compat.v1 versions of functions
    - Formatting changes
    - Using more appropriate TF function names

--
308689397  by Andre Araujo:

    Internal change.

--
308341315  by Andre Araujo:

    Remove old slim dependency in DELF open-source model.

    This avoids issues with requiring old TF-v1, making it compatible with latest TF.

--
306777559  by Andre Araujo:

    Internal change

--
304505811  by Andre Araujo:

    Raise error during geometric verification if local features have different dimensionalities.

--
301739992  by Andre Araujo:

    Transform some geometric verification constants into arguments, to allow custom matching.

--
301300324  by Andre Araujo:

    Apply name change(experimental_run_v2 -> run) for all callers in Tensorflow.

--
299919057  by Andre Araujo:

    Automated refactoring to make code Python 3 compatible.

--
297953698  by Andre Araujo:

    Explicitly replace "import tensorflow" with "tensorflow.compat.v1" for TF2.x migration

--
297521242  by Andre Araujo:

    Explicitly replace "import tensorflow" with "tensorflow.compat.v1" for TF2.x migration

--
297278247  by Andre Araujo:

    Explicitly replace "import tensorflow" with "tensorflow.compat.v1" for TF2.x migration

--
297270405  by Andre Araujo:

    Explicitly replace "import tensorflow" with "tensorflow.compat.v1" for TF2.x migration

--
297238741  by Andre Araujo:

    Explicitly replace "import tensorflow" with "tensorflow.compat.v1" for TF2.x migration

--
297108605  by Andre Araujo:

    Explicitly replace "import tensorflow" with "tensorflow.compat.v1" for TF2.x migration

--
294676131  by Andre Araujo:

    Add option to resize images to square resolutions without aspect ratio preservation.

--
293849641  by Andre Araujo:

    Internal change.

--
293840896  by Andre Araujo:

    Changing Slim import to tf_slim codebase.

--
293661660  by Andre Araujo:

    Allow the delf training script to read from TFRecords dataset.

--
291755295  by Andre Araujo:

    Internal change.

--
291448508  by Andre Araujo:

    Internal change.

--
291414459  by Andre Araujo:

    Adding train script.

--
291384336  by Andre Araujo:

    Adding model export script and test.

--
291260565  by Andre Araujo:

    Adding placeholder for Google Landmarks dataset.

--
291205548  by Andre Araujo:

    Definition of DELF model using Keras ResNet50 as backbone.

--
289500793  by Andre Araujo:

    Add TFRecord building script for delf.

--

PiperOrigin-RevId: 309118395

* Updating README, dependency versions

* Updating training README

* Fixing init import of export_model

* Fixing init import of export_model_utils

* tkinter in INSTALL_INSTRUCTIONS

* Merged commit includes the following changes:

FolderOrigin-RevId: /google/src/cloud/andrearaujo/delf_oss/google3/..

* INSTALL_INSTRUCTIONS mentioning different cloning options

* Updating required TF version, since 2.1 is not available in pip

* Internal change.

PiperOrigin-RevId: 309136003

* Fix missing string_input_producer and start_queue_runners in TF2.

PiperOrigin-RevId: 309437512

* Handle RANSAC from skimage's latest versions.

PiperOrigin-RevId: 310170897

* DELF 2.1 version: badge and setup.py updated

* Add TF version badge in INSTALL_INSTRUCTIONS and paper badges in README

* Add paper badges in paper instructions

* Add paper badge to landmark detection instructions

* Small update to DELF training README

* Merged commit includes the following changes:
312614961  by Andre Araujo:

    Instructions/code to reproduce DELG paper results.

--
312523414  by Andre Araujo:

    Fix a minor bug when post-process extracted features, format config.delf_global_config.image_scales_ind to a list.

--
312340276  by Andre Araujo:

    Add support for global feature extraction in DELF open-source codebase.

--
311031367  by Andre Araujo:

    Add use_square_images as an option in DELF config. The default value is false. if it is set, then images are resized to square resolution before feature extraction (e.g. Starburst use case. ) Thought for a while, whether to have two constructor of DescriptorToImageTemplate, but in the end, decide to only keep one, may be less confusing.

--
310658638  by Andre Araujo:

    Option for producing local feature-based image match visualization.

--

PiperOrigin-RevId: 312614961

* DELF README update / DELG instructions

* DELF README update

* DELG instructions update

* Merged commit includes the following changes:

PiperOrigin-RevId: 312695597

* Merged commit includes the following changes:
312754894  by Andre Araujo:

    Code edits / instructions to reproduce GLDv2 results.

--

PiperOrigin-RevId: 312754894

* Markdown updates after adding GLDv2 stuff

* Small updates to DELF README

* Clarify that library must be installed before reproducing results

* Merged commit includes the following changes:
319114828  by Andre Araujo:

    Upgrade global feature model exporting to TF2.

--

PiperOrigin-RevId: 319114828

* Properly merging README

* small edits to README

* small edits to README

* small edits to README

* global feature exporting in training README

* Update to DELF README, install instructions

* Centralizing installation instructions

* Small readme update

* Fixing commas

* Mention DELG acceptance into ECCV'20

* Merged commit includes the following changes:
326723075  by Andre Araujo:

    Move image resize utility into utils.py.

--

PiperOrigin-RevId: 326723075

* Adding back matched_images_demo.png

* Merged commit includes the following changes:
327279047  by Andre Araujo:

    Adapt extractor to handle new form of joint local+global extraction.

--
326733524  by Andre Araujo:

    Internal change.

--

PiperOrigin-RevId: 327279047

* Updated DELG instructions after model extraction refactoring

* Updating GLDv2 paper model baseline

* Merged commit includes the following changes:
328982978  by Andre Araujo:

    Updated DELG model training so that the size of the output tensor is unchanged by the GeM pooling layer. Export global model trained with DELG global features.

--
328218938  by Andre Araujo:

    Internal change.

--

PiperOrigin-RevId: 328982978

* Updated training README after recent changes

* Updated training README to fix small typo

* Merged commit includes the following changes:
330022709  by Andre Araujo:

    Export joint local+global TF2 DELG model, and enable such joint extraction.

    Also, rename export_model.py -> export_local_model.py for better clarity.

    To check that the new exporting code is doing the right thing, I compared features extracted from the new exported model against those extracted from models exported with a single modality, using the same checkpoint. They are identical.

    Some other small changes:
    - small automatic reformating
    - small documentation improvements

--

PiperOrigin-RevId: 330022709

* Updated DELG exporting instructions

* Updated DELG exporting instructions: fix small typo

* Adding DELG pre-trained models on GLDv2-clean

* Merged commit includes the following changes:
331625297  by Andre Araujo:

    Internal change.

--
330062115  by Andre Araujo:

    Fix small (non-critical) typo in the DELG extractor.

--

PiperOrigin-RevId: 331625297

* Merged commit includes the following changes:
347479009  by Andre Araujo:

    Fix image size setting for GLD training.

--

PiperOrigin-RevId: 347479009

by default NMS is off.

PiperOrigin-RevId: 347613472

* 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.

--
321046157  by Andre Araujo:

    Purely Google refactor

--

PiperOrigin-RevId: 326369548

* Added export of delg_model module.

* README update to explain training DELG global features head

* Added guidelines for DELF hyperparameter values

* Fixed typo

* Added mention about remaining training flags.

* Merged commit includes the following changes:
334723489  by Andre Araujo:

    Backpropagate global and attention layers together.

--
334228310  by Andre Araujo:

    Enable scaling of local feature locations to the resized resolution.

--

PiperOrigin-RevId: 334723489

* Merged commit includes the following changes:
347032253  by Andre Araujo:

    Updated local and global_and_local model export scripts for exporting models trained with the autoencoder layer.

--
344312455  by Andre Araujo:

    Implement autoencoder in training pipeline.

--
341116593  by Andre Araujo:

    Reduce the default save_interval, to get more frequent checkpoints.

--
341111808  by Andre Araujo:

    Allow checkpoint restoration in DELF training, to enable resuming of training jobs.

--
340138315  by Andre Araujo:

    DELF training script: make it always save the last checkpoint.

--
338731551  by Andre Araujo:

    Add image_size flag in DELF/G OSS training script.

--
338684879  by Andre Araujo:

    Clean up summaries in DELF/G training script.

    - Previously, the call to tf.summary.record_if() was not working, which led to summaries being recorded at every step, leading to too large events files. This is fixed.
    - Previously, some summaries were computed at iteration k, while others at iteration k+1. Now, we standardize summary computations to always run after backpropagation (which means that summaries are reported for step k+1, referring to the batch k).
    - Added a new summary: number of global steps per second; useful to see how fast training is making progress.

    Also a few other small modifications are included:
    - Improved description of the train.py script.
    - Some small automatic reformattings.

--

PiperOrigin-RevId: 347032253
Co-authored-by: Andre Araujo <andrearaujo@google.com>

Context R-CNN Updates: Added capabilities to use multi-headed or multi-layered attention, to place the attention heads pre- or post-second stage feature extraction, and to work with embedded features in the context feature back from pre- or post-second stage feature extraction. Added an option for RPN feature map crops to be piped through to model outputs.

PiperOrigin-RevId: 345777219

DEFAULT_VALUE_OK=setting prefetch batches default to 2 as using -1 can cause memory issues for some models such as context r-cnn that use sequence examples.

PiperOrigin-RevId: 345682268

PiperOrigin-RevId: 345620862

PiperOrigin-RevId: 345586686

PiperOrigin-RevId: 345586199

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