search

junfu1115 / DANet

Dual Attention Network for Scene Segmentation (CVPR2019)
MIT License
2.41k stars 483 forks source link

ValueError: operands could not be broadcast together with shapes (1,1024,2048) (1024,2048,4) #141

Open tangyipeng100 opened 3 years ago

tangyipeng100 commented 3 years ago

I used the command CUDA_VISIBLE_DEVICES=0,1,2,3 python test.py --dataset citys --model danet --backbone resnet101 --resume models/DANet101.pth.tar --eval --base-size 2048 --crop-size 768 --workers 1 --multi-grid --multi-dilation 4 8 16 --os 8 --aux --no-deepstem But I got a lot of ValueError like the title shows. And I got very low results: pixAcc: 0.1265, mIoU: 0.0180

I referred to https://github.com/junfu1115/DANet/issues/12 and https://github.com/junfu1115/DANet/issues/120 to process Cityscapes and generated train_fine.txt,val_fine.txt,test_fine.txt. What`s wrong with me? Thanks.