pytorch_simple_CenterNet_45 icon indicating copy to clipboard operation
pytorch_simple_CenterNet_45 copied to clipboard

Published 20 hours ago • verified publisher icon zzzxxxttt

Result Extraction

Open JiaLim98 opened this issue 4 years ago • 9 comments

Hi @zzzxxxttt,

Thank you for your amazing work. I have completed my training and testing. However, I require two more results for documentation purposes.

  1. Precision-Recall Curve: May I know which python file is the repo using? This is because I found two cocoeval.py after finish compiling PythonAPI, under the two paths stated below. I have tried modifying both but can't seem to work (looks like the test.py is not using both) . Can you let me know how can I extract the 101 datapoints for PR curve?
    • \lib\cocoapi\PythonAPI\build\lib.linux-x86_64-3.6\pycocotools, and
    • \lib\cocoapi\PythonAPI\pycocotools
  2. [email protected] by classes. I can't seem to find the line of code that gives me this. Can you let me know how? I got the overall coco results already, I just need the results by classes.

Hope to hear from you soon. Thank you.

Cheers, JiaLim98

JiaLim98 avatar Oct 08 '20 06:10 JiaLim98

For the pr curve, this issue may help, and detectron2 generates class-wise mAP during evaluation, you can check the implementation of it.

zzzxxxttt avatar Oct 09 '20 07:10 zzzxxxttt

Thanks for the reply.

For anyone who wants to output class-wise mAP, this is the most straightforward way I found. The mAP for entire model is calculated from the average of APs for each classes. I have found the code for exporting the class-wise mAP from cocoeval.py in Pycocotools here from line 458 to line 464.

JiaLim98 avatar Oct 14 '20 06:10 JiaLim98

Jialim，I am very happy that you have completed the training and testing work, may I know your final accuracy? I am trying to train this net in my datasets, but I still not complete it.

yangyang117 avatar Dec 24 '20 00:12 yangyang117

Hi @yangyang117,

My final accuracy (without finetuning) are: [email protected] = 92.02% and [email protected]:0.05:0.95 = 40.60% Hope it helps.

JiaLim98 avatar Dec 24 '20 01:12 JiaLim98

Thanks for your answering, is this for your own datasets or public datasets?

yangyang117 avatar Dec 24 '20 01:12 yangyang117

It is an open-sourced PCB defects dataset.

JiaLim98 avatar Dec 24 '20 01:12 JiaLim98

Thank you, it's very helpful.

yangyang117 avatar Dec 24 '20 02:12 yangyang117

它是开源的PCB缺陷数据集。

您好，麻烦问一下 自己的数据集 遇到这个问题 No such file or directory: './data/voc/VOCdevkit/VOC2007/annotations_cache'该如何处理

18342960922 avatar Mar 06 '21 09:03 18342960922

您可以检查文件目录是否确实存在. 对于第一次训练，这个问题不应该存在.

JiaLim98 avatar Mar 08 '21 03:03 JiaLim98