-
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
Cannot reproduce result for coco #13
Comments
We use the provided scripts to run all the experiments. Could you provide the training log to help us find the problem? |
Thanks for reply. The log is below. From the log, I used the same config you provided with changing the data path and pre-trained path to my location. |
We use mmdet==2.10.0 in our experiments, and there may some difference in later version. We will find this out and update our code soon. |
你好,我也遇见了这个问题,尝试多次,确定是环境的问题,重新配置环境就可以啦, |
Following readme construction, I only got AP 0.065 after training on Seed 1 Percent 1 Coco standard while 25.81 ± 0.28 (+16.76) is claimed in the paper. Here's my setting:
Dataset:
percent 1 seed 1 Coco standard
Pretrained baseline:
I use the train_gpu2.sh modification and only got AP 0.0030 less than 1%. I trained twice and AP 0.003 is repeatable.
Training:
I use train_gpu8.sh without modification and only got AP 0.065 less than 10%
My guess is that the pretrained baseline performs low. Could you share your model and log of pretrained baseline and semi-supevised training to help use reproduce results?
The text was updated successfully, but these errors were encountered: