J.yang
Results
2
comments of
J.yang
In External-Attention-pytorch/model/backbone/MobileViT.py,line134,you can change it. `nn.Conv2d(inp, hidden_dim, kernel_size=1, stride=self.stride, bias=False),`
看起来像是你的输入数据的问题,你可以先定义一个随机数,然后调试一下,观察每一层的输出结果是否正确。 `input = torch.randn(1, 3, 256, 256)`