search

ByChelsea / CMOS

[CVPR 2023] Better “CMOS” Produces Clearer Images: Learning Space-Variant Blur Estimation for Blind Image Super-Resolution
9 stars 0 forks source link

Step3 出错 #1

Open yayinliqing opened 8 months ago

yayinliqing commented 8 months ago 
当我运行python train.py --opt options/train/NYUv2_BSR/train_stage3.yml时报错

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, 144, 1, 1])

ByChelsea commented 7 months ago

Could you provide more detailed error information? The information provided is too limited for me to determine where the problem lies.