tensorflow / tensorflow/models

How can I evaluate a pre-trained model?

Open
#8,685 1 comment 1 reaction 3 assignees View on GitHub

@pkulzc is already working on this.

Since Jun 17, 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 a group of images with ground truth detection boxes and I want to simply run them through a pre-trained model from the Model Zoo and get the, say, precision/recall/mAP between the ground truth boxes and predicted detections.

The solutions I've seen, in using eval.py or model_main.py all require pipeline_config files that I never configured since I'm not training the model. Is there maybe a workaround where I can specify my testing images somewhere in the pipeline_config to evaluate but not have them used in training?

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.