TheBlackBox

> Hi, Are your V100 GPUs 32G? Yes, I used V100 GPUs 32G. I checked that no other process occupied the GPUs.

The images I downloaded does not match the label files either. Could anyone give a hit which version of data I should download.

@tangsipeng Yes, I downloaded the version as indicated but found a image size mismatch error. And the classification accuracy curve is also wired.

I also encounter this problem. Need some help, Thanks.

I switched to Detectron 2.0.2 as I remember, which resolved this problem.

I also encountered this problem but have not yet found a solution. I am trying to import the script from other repo and modify it myself.

> My code may not be up to date. I will rerun the experiments and see if it works. Thanks

> @LigZhong If you use another version before this commit, you just need to test the trained model with the script of tools/test.py to get a more precise result Is...

> I know, it's the name of floder I met the same problem, can you explain a little bit more on fixing this? thank you very much.