BranStarkkk
BranStarkkk
> Hi, `if_amp = False `doesn't work for me. I also tried using a small learning rate, but the problem still exists. Does anyone know how to handle it? I...
> > > Hi, `if_amp = False `doesn't work for me. I also tried using a small learning rate, but the problem still exists. Does anyone know how to handle...
第二个带“ft”的是微调过的，第一个性能相对差一些
> 我想请问一些，这个训练连权重是在哪里下载的呀 hugging face搜vim
已解决，方法为加载完预训练权重文件之后修改首层的参数： self.model = VisionMamba(pretrained=pretrained, patch_size=16, channels=3) # pretrained=True self.model.patch_embed.proj = nn.Conv2d(channels, 192, kernel_size=(patch_size, patch_size), stride=(8, 8)) # channels=4, patch_size为自己模型设置的batch_size self.model.head = nn.Identity()