tensorflow / tensorflow/models

EfficientDet D7 vs NasNet Performance

Open
#9,128 0 comments 0 reactions 1 assignee View on GitHub

Nobody has claimed this yet.

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

Description

I use TensorFlow 2.2 and tested all EfficientDet models. It is written on the page that EfficientDet D7 has higher mAP than NasNet as 51.5 > 43. But in testing daha I saw EfficientDet has really lower accuracy then other models. Why NasNet is much higher then EfficientDet while it has lower mAP?
Here results can be seen:
Nas detection:
cars_nas

EfficientDet7 detection:
cars_efd7

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.