search

uber-research / UPSNet

UPSNet: A Unified Panoptic Segmentation Network
Other
649 stars 120 forks source link

batch_size per gpu is limited to 1 #134

Open ginobilinie opened 4 years ago

ginobilinie commented 4 years ago

I have tried to use this copy of code, however, I found the batch_size per GPU is limited 1. It is limited by the following codes in base_dataset.py:

        elif key == 'roidb':
            assert len(batch) == 1
            blob.update({'roidb': batch[0]['roidb']})

I'm asking how I can remove the limit.

Thanks.