import torch.nn as nnclass ViT(nn.Module): def __init__(self, img_size, patch_size, num_classes, dim): super().__init__() self.patch_size = patch_size num_patches = (img_size // patch_size) ** 2 patch_dim = 3 * patch_size ** 2 # 输入的通道数，3表示RGB通道 self.class_embed = nn.Parameter(torch.randn(1, 1, dim)) self.patch_embed = nn.Linear(patch_dim, dim) self.pos_embed = nn.Parameter(torch.randn(1, num_patches + 1, dim)) self.cls_token = nn.Parameter(torch.randn(1, 1, dim)) self.transformer = nn.TransformerEncoderLayer(d_model=dim, nhead=8) self.linear = nn.Linear(dim, num_classes) def forward(self, x): batch_size, _, _, _ = x.shape patches = x.unfold(2, self.patch_size, self.patch_size).unfold(3, self.patch_size, self.patch_size) patches = patches.flatten(2).transpose(1, 2) patch_embed = self.patch_embed(patches) pos_embed = self.pos_embed[:, :(patches.size(1) + 1)] cls_tokens = self.cls_token.expand(batch_size, -1, -1) x = torch.cat([cls_tokens, patch_embed], dim=1) x += pos_embed x = self.transformer(x) x = x.mean(dim=1) x = self.linear(x) return x

这段代码是用来定义一个名为ViT的类，其继承自nn.Module。其有四个参数，包括图像尺寸img_size、每个patch的尺寸patch_size、类别数目num_classes和维度dim。在初始化时，代码调用了父类的构造函数，并且将patch_size保存在self.patch_size中。由于图像被切成了多个patch，因此需要计算patch的数目num_patches，以及每个patch的维度patch_dim。