error

[DaBaiTuuu]

when run the anomaly/train.py ,i modified the cfg.TRAIN.batch_size_per_gpu from 2 to 1 and raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size))
ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1, 1])
how to figure it out/