DonMuv

File "/disk/sdc/shejiao/Pytorch-UNet-master/evaluate.py", line 19, in evaluate mask_true = F.one_hot(mask_true, net.n_classes).permute(0, 3, 1, 2).float() RuntimeError: number of dims don't match in permute

1

File "/disk/sdc/shejiao/Pytorch-UNet-master/evaluate.py", line 19, in evaluate mask_true = F.one_hot(mask_true, net.n_classes).permute(0, 3, 1, 2).float() RuntimeError: number of dims don't match in permute

为什么Teacher模型是1G大小，Student也是1G大小，这个蒸馏的意义在哪里

DKD可否用于其他领域

1

DKD看起来是对全连接层输出的logits进行蒸馏的，请问是否可以应用在没有全连接层的网络中，但看起来需要通道对齐操作是吗

Given input size: (64x240x320). Calculated output size: (64x0x1). Output size is too small

1

Hi, There is a error when i use the repvggplus: File "/home/donmuv/Patch-NetVLAD/repvggplus.py", line 65, in forward out = self.post_se(self.nonlinearity(out)) File "/home/donmuv/anaconda3/envs/NetVlad/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl result = self.forward(*input, **kwargs) File...