tensorflow / tensorflow/models

How to set up pipeline.config file with one class to train on mobilenet v3 large? and also how to set fine tune checkpoint?

Open
#7,910 5 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Jun 19, 2020.

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

Description

I have to set class of one in pipeline.config,i changed the number of classes to 1 and i started training its showing an error
InvalidArgumentError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a mismatch between the current graph and the graph from the checkpoint. Please ensure that you have not altered the graph expected based on the checkpoint. Original error:

Assign requires shapes of both tensors to match. lhs shape= [1,1,256,12] rhs shape= [1,1,256,546]
[[node save/Assign_86 (defined at /home/drive/Downloads/models-master/research/object_detection/legacy/trainer.py:378) @bmabey @alextp @moonboots @ewilderj @jtoy @tensorflowbutler

And also how to set fine tune checkpoint ?

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.