When I run the Base_OC_Module at a certain iteration, it will stop.

[yu-changqian]

Pytorch version: 0.4.1
GPU benchmark: 8 x 1080 Ti
CUDA version: 9.0

Experiment config:
batch size: 16
num workers: 16
input size: 480x480

When I use the Base_OC_Module on the ADE20K dataset, my experiment will stop at a certain iteration without other notion output. And the utilization rate of GPU will drop to 0. Did you have the similar experience?

[PkuRainBow]

Sorry, I think it can be a bug of inplace-abn. Please refer to mapillary/inplace_abn#58.

We use 4 x P100 for all the experiments.

[yu-changqian]

Yes. When I use 4 x 1080Ti, all of it becomes normal. This should be a bug of inplace-abn. Thank you.

[KeyKy]

I get the same problem and it only work for 4 gpus.