tensorflow / tensorflow/models

Pre-trained Object Detection models don't have any variables to export in the variables folder for TF2.x usage

Open
#8,179 4 comments 1 reaction 3 assignees View on GitHub

@pkulzc is already working on this.

Since May 21, 2020.

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

Description

System information

  • Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No
  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04
  • Mobile device (e.g., Pixel 4, Samsung Galaxy 10) if the issue happens on mobile device:
  • TensorFlow installed from (source or binary): binary
  • TensorFlow version (use command below): 2.1
  • Python version: 3.7
  • Bazel version (if compiling from source):
  • GCC/Compiler version (if compiling from source):
  • CUDA/cuDNN version: 7.6.5
  • GPU model and memory: Tesla T4

Please provide the entire URL of the model you are using?

https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md
Describe the current behavior
Related issue: https://github.com/tensorflow/tensorrt/issues/178
TF2.x looks for variables from the variables folder to restore the model but this folder is empty in the pretrained models available for download. I have tried converting from the checkpoint given but it just creates an empty frozen graph.
Describe the expected behavior
A saved_model file + a variables folder should be created when using this.
Code to reproduce the issue

Look at related issue
Other info / logs

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.