-
Notifications
You must be signed in to change notification settings - Fork 14
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
Do you have nms process during testing the results? #4
Comments
Post-processing is essential for current detection scheme, however traditional nms is not the only choice, especially when dealing with enormous detection bboxes which is quite resource-consuming. We propose large batch nms to solve the resource-consuming problem. Further more, our experiments find out that nmw can achieve better performance in this task. You can find the config of post-processing here and code can be found here. Hope this is helpful. |
Another quesion.If you have used the nmw during testing the result,why I got a lot of proposals which some of them have exactly the same start and end boundaries?For example, "video_test_0000026 207.88 207.88 1 0.022431798" Just look at the second and third item in this sequence,these two items are the boudaries the code provide.I divided the two items by 25 for 25 fps. |
It looks like a normal fp to me, with score of 0.02, it's not a serious problem. It's just test process, we don't need to further filter the results. By the way, to generate the results file, we provide '--eval-options' in test.py, only by providing the parameter of 'jsonfile_prefix', a formatted result file will be generated with time boundary. |
代码您跑通了吗,.cpp文件您是怎样编译的呢? |
I use test.py to get the result of [email protected], but I can not find the nms process which is necessary for evaluating the result.
The text was updated successfully, but these errors were encountered: