我试图通过预训练（自监督学习）模型来进行迁移学习，该模型在未标记数据上对旋转（0、90、180 和 270 度：4 个标签）进行训练。以下是模型代码：
class RotNet1(nn.Module): def __init__(self): keep_prob = 0.9 super(RotNet1, self).__init__() self.layer1 = nn.Sequential(nn.Conv2d(in_channels = 3, out_channels = 80, kernel_size = 7, stride = 1, padding = 0), nn.ReLU(), nn.MaxPool2d(kernel_size = 2, stride = 2, padding = 1), nn.Dropout(p=1 - keep_prob) ) self.bn1 = nn.BatchNorm2d(num_features = 80) self.dropout1 = nn.Dropout2d(p=0.02) self.layer2 = nn.Sequential(nn.Conv2d(in_channels = 80, out_channels = 128, kernel_size = 3, stride = 1, padding = 1), nn.ReLU(), nn.MaxPool2d(kernel_size = 2, stride = 2, padding = 1), nn.Dropout(p=1 - keep_prob) ) self.bn2 = nn.BatchNorm2d(num_features = 128) self.layer3 = nn.Sequential(nn.Conv2d(in_channels = 128, out_channels = 256, kernel_size = 3, stride = 1, padding = 0), nn.ReLU(), nn.MaxPool2d(kernel_size = 2, stride = 2, padding = 1), nn.Dropout(p=1 - keep_prob) ) self.bn3 = nn.BatchNorm2d(num_features = 256) self.layer4 = nn.Sequential(nn.Conv2d(in_channels = 256, out_channels = 512, kernel_size = 3, stride = 1, padding = 0), nn.ReLU(), nn.MaxPool2d(kernel_size = 2, stride = 2, padding = 1), nn.Dropout(p=1 - keep_prob) ) self.bn4 = nn.BatchNorm2d(num_features = 512) self.layer5 = nn.Sequential(nn.Conv2d(in_channels = 512, out_channels = 512, kernel_size = 3, stride = 1, padding = 0), nn.ReLU(), nn.MaxPool2d(kernel_size = 2, stride = 2, padding = 1), nn.Dropout(p=1 - keep_prob) ) self.bn5 = nn.BatchNorm2d(num_features = 512) self.drop_out = nn.Dropout() self.fc1 = nn.Linear(512* 2 * 2, 200) self.fc2 = nn.Linear(200, 4) #self.fc3 = nn.Linear(200, 100) def forward(self, input): out = self.layer1(input) out = self.bn1(out) out = self.dropout1(out) out = self.layer2(out) out = self.bn2(out) out = self.layer3(out) out = self.bn3(out) out = self.layer4(out) out = self.bn4(out) out = self.layer5(out) out = self.bn5(out) out = out.reshape(out.size(0), -1) out = self.drop_out(out) out = self.fc1(out) out = self.fc2(out) #out = self.fc3(out) return out我用这4个标签训练了这个模型，并将模型命名为model_ssl。然后我复制了这个模型，并将最后一个全连接层的数量从4改为200（这是标记的训练和验证集中标签的数量，其中示例数量受到限制）：
model_a = copy.copy(model_ssl)#model_a.classifiernum_classes = 200model_a.fc2 = nn.Linear(256,num_classes).cuda()model_a.to(device)loss_fn = torch.nn.CrossEntropyLoss()n_epochs_a = 20learning_rate_a = 0.01alpha_a = 1e-5momentum_a = 0.9optimizer = torch.optim.SGD(model_a.parameters(), momentum = momentum_a, nesterov=True, weight_decay = alpha_a, lr=learning_rate_a)train_losses_a, val_losses_a, train_acc_a, val_acc_a = train(model_a, train_dataloader_sl, val_dataloader_sl, optimizer, n_epochs_a, loss_fn)这是错误消息：
---------------------------------------------------------------------------RuntimeError Traceback (most recent call last)<ipython-input-27-f6f362ba8c53> in <module>() 15 optimizer, 16 n_epochs_a,---> 17 loss_fn)6 frames<ipython-input-23-df58f17c5135> in train(model, train_dataloader, val_dataloader, optimizer, n_epochs, loss_function) 57 for epoch in range(n_epochs): 58 model.train()---> 59 train_loss, train_accuracy = train_epoch(model, train_dataloader, optimizer, loss_fn) 60 model.eval() 61 val_loss, val_accuracy = evaluate(model, val_dataloader, loss_fn)<ipython-input-23-df58f17c5135> in train_epoch(model, train_dataloader, optimizer, loss_fn) 10 labels = labels.to(device=device, dtype=torch.int64) 11 # Run predictions---> 12 output = model(images) 13 # Set gradients to zero 14 optimizer.zero_grad()/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs) 548 result = self._slow_forward(*input, **kwargs) 549 else:--> 550 result = self.forward(*input, **kwargs) 551 for hook in self._forward_hooks.values(): 552 hook_result = hook(self, input, result)<ipython-input-11-2cd851b6d8e4> in forward(self, input) 85 out = self.drop_out(out) 86 out = self.fc1(out)---> 87 out = self.fc2(out) 88 #out = self.fc3(out) 89 return out/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs) 548 result = self._slow_forward(*input, **kwargs) 549 else:--> 550 result = self.forward(*input, **kwargs) 551 for hook in self._forward_hooks.values(): 552 hook_result = hook(self, input, result)/usr/local/lib/python3.6/dist-packages/torch/nn/modules/linear.py in forward(self, input) 85 86 def forward(self, input):---> 87 return F.linear(input, self.weight, self.bias) 88 89 def extra_repr(self):/usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in linear(input, weight, bias) 1608 if input.dim() == 2 and bias is not None: 1609 # fused op is marginally faster-> 1610 ret = torch.addmm(bias, input, weight.t()) 1611 else: 1612 output = input.matmul(weight.t())RuntimeError: size mismatch, m1: [256 x 200], m2: [256 x 200] at /pytorch/aten/src/THC/generic/THCTensorMathBlas.cu:283矩阵m1和m2的大小似乎是匹配的，但仍然出现了这个错误消息。我应该怎么做？
回答：
fc1的输出形状为200，因此fc2的输入大小应该是200而不是256，num_classes和256应该交换位置：
num_classes = 200model_a.fc2 = nn.Linear(num_classes, 256).cuda()