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
Lower results when evaluating released BEVDet checkpoint #41
Comments
@Divadi you train this with 4 gpus, total 8x4=32 batch size and lr=1e-4? |
This is without re-training; I just loaded & evaluated the released checkpoint. I'm running a separate training job with 4 gpus, 16x4=64 batch size, original lr, but it has not completed yet. |
Hmm... When I load your pkl and compare it with mine:
The first file path itself is different; the predictions are different as well. Is what you sent me the first sample as loaded by the pipeline? |
I set the workers_per_gpu=0 |
emm, I apologize for my mistaken 'test.pkl' for 'check.pkl' and 'img_feats' for 'img_metas' |
I will check the pkl & zip further when I get home. The results of training myself are as follows:
|
@Divadi mAVE and mAAE is a bit low. Some 'abnormal' examples (I think the others will not report their result when it is seem ok- - ) can be found in issue#21. |
may be epoch18 is better…… |
@HuangJunJie2017 Updated results:
Thank you for your help! |
@Divadi nice job! thank you so much for your information! |
Hello, I have tried to evaluate released BEVDet checkpoint as-is on my setup, but I get
which is lower than the expected 30.8/40.4 mAP/NDS.
I am using A6000 GPUs, torch 1.10.1, cudatoolkit 11.3. Do you know what might be the issue?
I find that I have the exact same numbers as #15 @BoLang615, but I believe I am using the latest version. I would appreciate any pointers for this.
Thank you!
The text was updated successfully, but these errors were encountered: