-
Notifications
You must be signed in to change notification settings - Fork 40
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
Prediction score threshhold stability #2
Comments
I changed the score threshold (0.78->0.6) and now it reaches 85 AP11 as below bbox AP:97.9524, 89.7096, 89.3596 |
Thanks for letting me know. |
I got similar results with hailanyi, I don’t know if some of the given config parameters are not optimal, such as COORD_TYPE. Besides, I want to know the details of the model implementation, but there are many functions in occ_target that I don’t understand. If you have time, can you provide some code comments? thanks! |
I also try to reproduce the performance claimed in paper, but it's not as good as claimed number. |
Hello, do you reproduce the performance claimed in paper? I cannot reproduce such performance in the val set and test set |
Hi I use this code base to produce the results, however seems the threshold on my machine may not be the same for everyone. I also observe the number of gpus used in training will somehow impact the final results, not sure if it causes the problem |
Thanks for your reply, I will try four GPUs. By the way, when submitting the test results, how many epoches do you adopt? 40? |
Hi!
Thanks for sharing the code. With out any code changes, I only got 79 AP11 on val set as below. It is weird, because the paper can go up to 86 AP11. Is there a trained model, or could you give me some advice for training @Xharlie ?
Car AP@0.70, 0.70, 0.70:
bbox AP:90.7842, 89.7048, 89.3668
bev AP:90.3260, 88.2499, 88.1178
3d AP:89.5578, 79.5970, 78.9717
aos AP:42.11, 40.24, 40.12
Car AP_R40@0.70, 0.70, 0.70:
bbox AP:96.9146, 93.4603, 90.9702
bev AP:93.9134, 89.9003, 87.4430
3d AP:92.9308, 84.1075, 81.5648
aos AP:44.93, 41.93, 40.84
The text was updated successfully, but these errors were encountered: