GitLab

PiperOrigin-RevId: 379828181

PiperOrigin-RevId: 379817535

1) Added the score-to-scaled-distance ranking method.
2) Added the gaussian-weighted ranking method.
3) Added the hyperparameter used in the rescoring function.

PiperOrigin-RevId: 379646603

1. Make api_template always use third_party/py/keras (or keras PIP package in OSS).
2. API tests are updated to ignore tensorflow/python/keras end points.
3. All Keras-related code will be removed in a follow up change. Keras-specific APIs are tracked in google3/third_party/py/keras/api/golden/
4. There are a few APIs (optimizer/initializer) that are exposed as both tf and keras APIs. Their pbtxt are updated to reflect the latest class path change.

Once this change is submitted, the current code in tensorflow/python/keras will become a stale copy, and will be removed soon. No more changes should be made to tensorflow/python/keras.

PiperOrigin-RevId: 379353790

PiperOrigin-RevId: 378977617

378492389  by Andre Araujo:

    Internal change

--
369671840  by Andre Araujo:

    Cleanup after recent PRs in DELF github repo.

--
360692342  by Andre Araujo:

    Replace direct TF app import with absl::app.
    (1) TF::app is deprecated
    (2) direct TF import is discouraged. go/gpylint-faq#g-direct-tensorflow-import

--
359157762  by Andre Araujo:

    Internal change

--

PiperOrigin-RevId: 378492389
Co-authored-by: Andre Araujo <andrearaujo@google.com>

* Fix attention application in DELG

* Adding DELG unit tests

* Formatting for review

* Formatting for review

* Formatting for review

Add notebook and update ODT TFLite conversion doc to show how to make the model compatible with TFLite Task Library.

PiperOrigin-RevId: 378313314

The original Colab by malcolmslaney didn't work with the current VGGish/tensorflow.  Changed the link to an updated version.

region for the keypoint heatmap if the instance's keypoint visibility is 0.

PiperOrigin-RevId: 378183175

PiperOrigin-RevId: 378154667

PiperOrigin-RevId: 377511299

Adding head customization parameters to `ObjectDetection` and `MaskEstimation` CenterNet proto messages.

PiperOrigin-RevId: 377280733

PiperOrigin-RevId: 377208217

PiperOrigin-RevId: 377187393

PiperOrigin-RevId: 377104676

PiperOrigin-RevId: 377103499

PiperOrigin-RevId: 377096964

PiperOrigin-RevId: 374891049

PiperOrigin-RevId: 374301186

PiperOrigin-RevId: 373140072

Update the logo path.

PiperOrigin-RevId: 373010443

PiperOrigin-RevId: 372953929

PiperOrigin-RevId: 372579796

PiperOrigin-RevId: 372426423

interpolation method is configurable.

PiperOrigin-RevId: 372198977

PiperOrigin-RevId: 371929331

for the object center head parameters in CenterNet.

PiperOrigin-RevId: 371783912

PiperOrigin-RevId: 371037598

Fix explicit padding when pool residuals are used. Match the pool residual convolution to the depthwise convolution to ensure the output tensors of both are of the same size.

PiperOrigin-RevId: 370971019

PiperOrigin-RevId: 370903487

PiperOrigin-RevId: 370720011

PiperOrigin-RevId: 370575507

CenterNetMetaArch. It is to make sure the model can be post-quantizable and
doesn't generate calibration errors during quantization.

PiperOrigin-RevId: 370528566

PiperOrigin-RevId: 370255238

* 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:

    ...

logic doesn't depend on the per_keypoint_offset value and use
get_batch_predictions_from_indices to be consistent with other prediction
heads.

PiperOrigin-RevId: 369925004

PiperOrigin-RevId: 369749466