MeinhardMark

Did you solve this?

I think I may have the same problem here: ``` 2023-05-22 21:05:02,540 maskrcnn_benchmark INFO: Start evaluation on VG_stanford_filtered_with_attribute_val dataset(5000 images). 0%| | 0/2501 [14:57

similar situation when I'm trying to finetune on my own dataset. GPU memory usage had been slowly increasing and in the middle it went OOM.

Same situation here. Not only during evaluation, but also during the training process. Did you solve your problem?