tensorflow / tensorflow/models

Unable to reproduce same mAP with kitti pretrained tf1 model on Kitti dataset

Open
#10,376 3 comments 0 reactions 3 assignees View on GitHub

@pkulzc is already working on this.

Since Nov 18, 2021.

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

Description

  • I am using the TensorFlow 1.14
  • 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/...

Downloaded Kitti pretrained model from
http://download.tensorflow.org/models/object_detection/faster_rcnn_resnet101_kitti_2018_01_28.tar.gz

2. Describe the bug

When evaluation is run on test set of Kitti dataset, mAP for IoU=0.5 is 39%, instead of 87%..

3. Expected behavior

Should achieve mAP atleast near to 80%.

4. System information

  • OS Platform and Distribution : Linux Ubuntu 20.04
  • TensorFlow installed from pip
  • TensorFlow version : 1.14
  • Python version: 3.7
  • CUDA/cuDNN version: not installed
  • GPU model and memory: not available

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.