tensorflow / tensorflow/models

No effect of 'freeze_variables' in TensorFlow Objection API when using Tensorflow 2

Open
#9,548 2 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Dec 11, 2020.

models:research:odapi type:bug
Dominant language
Python
Stars
77.7k
Forks
44.8k
PR merge metrics
No merged PRs in 30d

Description

Prerequisites

Please answer the following questions for yourself before submitting an issue.

  • [Y] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
  • [Y] I am reporting the issue to the correct repository. (Model Garden official or research directory)
  • [Y] I checked to make sure that this issue has not already been filed.

1. The entire URL of the file you are using

https://github.com/tensorflow/models/tree/master/research/...

2. Describe the bug

The 'freeze_variables' parameter in
https://github.com/tensorflow/models/blob/master/research/object_detection/protos/train.proto

does not seem to have any effect when using TensorFlow 2. When setting 'freeze_variables' to '.*', which should freeze all variables, the model variables still show up in detection_model.trainable_variables when performing gradient calculation in https://github.com/tensorflow/models/blob/master/research/object_detection/model_lib_v2.py

It seems like 'freeze_variables' is only used in the old tf1 code https://github.com/tensorflow/models/blob/master/research/object_detection/model_lib.py

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.