GitLab

PiperOrigin-RevId: 325797820

Fixed a long-standing bug where the released VGGish model used
post-activation embedding output while the released embeddings
were pre-activation. There are still discrepancies due to
other reasons: differences in choice of YouTube transcode,
repeated resamplings with different resamplers, slight differences
in feature computation, etc.

* Made VGGish and YAMNet work in TF2 without disabling TF2 behavior.

Allowed TF2 behavior and allowed passing in a features tensor into the
VGGish model definition. Both of these changes are needed for making
TF-Hub exports of these models. Lifted constraints on TF versions since
tf_slim has been updated to work with TF 2.

* Responded to DAn's comments in https://github.com/tensorflow/models/pull/9077

* Fixed typo in comment.

PiperOrigin-RevId: 325621239

PiperOrigin-RevId: 325536056

PiperOrigin-RevId: 325470519

This is the likely reason for jobs that take forever.

PiperOrigin-RevId: 325275789

rpn_features for rfcn at second stage only have 1 level.

1. fix boxlist concatenate
2. fix input for crop and resize fn
3. TODO: need to check if the crop and resize fn used correctly

format:

1. Change rpn_features_to_crop into a list
2. change rpn_box_predictor_features into a list