shayebuhuiya

在VOC2012上跑这份代码会有两个问题： 1. 图片格式不对，这个我通过改变dataset类加载segimage的文件名解决了； 2. 训练的时候会出现 C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\NLLLoss2d.cu:106: block: [1,0,0], thread: [94,0,0] Assertion `t >= 0 && t < n_classes` failed. Traceback (most recent call last): File "D:\code\python\Unet\train.py", line 37, in train_loss.backward()...