-
Notifications
You must be signed in to change notification settings - Fork 28
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
如何对测试结果评估 #1
Comments
感谢您的称赞 ! PR曲线的绘制我需要花些时间研究一下, 应该是要改源码才能实现 另外您测速完的pkl档案有包含什么内容吗? 我手边还没有data可以看 |
@Charcy-yang 您好 我已经加您QQ了 |
同问,谢谢! |
如果是coco dataset的话,初步了解mmdetection使用的是pycocotools这个包实践评测的, 因为我目前只有VOC的数据集,我会找时间研究一下COCO的 ! |
感谢回复,想问的就是VOC的 |
将以下的档案放置到mmdetection的指定目录 put mean_ap_visualize.py under mmdetection/mmdet/core/evaluation/ 依照以下的步骤执行,
注意最终图会生成在mmdetection的主目录下 |
@Stephenfang51 请问如何才能生成.pkl文档呢?我训练完只有.json文件和.pth文件,跪求大神指导一下,还有如何导出json文件里面的loss值、precision值和recall值呢? |
@Stephenfang51 您好,我生成了pkl文件,按您的教程运行 python tools/voc_eval_visualize.py result.pkl ./configs/faster_rcnn_r101_fpn_1x.py 出现ModuleNotFoundError: No module named 'mmdet.core.evaluation.mean_ap_visualize',我明明已经把mean_ap_visualize.py这个文件放到mmdet/core/evaluation/目录下了,还是出现这样的错误。恳请大神指点一二。 |
(mede) ii@ii-Legion-Y7000P-2019:~/mmdetection$ python tools/voc_eval_visualize.py result.pkl ./configs/faster_rcnn_r101_fpn_1x_coco.py |
I encountered the same problem, did you solve it and how did you solve it |
您好,您这写的很好,我已验证可以运行。
可以请教对测试结果如何评估,我测试出来只有AP 值,请问如何绘制PR 曲线呢?谢谢您
The text was updated successfully, but these errors were encountered: