Open Luo-Z13 opened 1 year ago
You maybe use your own images with incorrect input sizes.
Thank you for your quick reply, so where should I change the input size of dataloader? Is it in ./base/loveda.py?
------------------ 原始邮件 ------------------ 发件人: "Junjue-Wang/LoveDA" @.>; 发送时间: 2022年11月15日(星期二) 下午3:39 @.>; @.**@.>; 主题: Re: [Junjue-Wang/LoveDA] Predict.py Problem (Issue #53)
You maybe use your own images with incorrect input sizes.
— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>
Yes. I can try it.
I download pretrained weight and use predict.py to test some images, but meet this bug, what's the problem of the fuse_layers?
File "test4/Road/LoveDA-master/Semantic_Segmentation/module/baseline/base_hrnet/_hrnet.py", line 394, in forward y = y + self.fuse_layers[i][j](x[j]) RuntimeError: The size of tensor a (500) must match the size of tensor b (504) at non-singleton dimension 3