应该为所有 1000 类 或没有 类 定义权重张量，但得到形状的权重张量：[5]
Weight tensor should be defined either for all 1000 classes or no classes but got weight tensor of shape: [5]
我正在尝试将 VGG16 用于 ** 5 类 数据集**。
我已经添加了 5 个新层来将 logit 的输出调整为 5.
model = models.vgg16(pretrained=True) #下载在Imagenet数据集上预训练的vgg16模型。
#Replace the Final layer of pretrained vgg16 with 5 new layers.
model.fc = nn.Sequential(nn.Linear(1000,512),
nn.ReLU(inplace=True),
nn.Linear(512,256),
nn.ReLU(inplace=True),
nn.Linear(256,128),
nn.ReLU(inplace=True),
nn.Linear(128,64),
nn.ReLU(inplace=True),
nn.Linear(64,5),
)
而我的损失函数如下
loss_fn = nn.CrossEntropyLoss(weight=class_weights) #CrossEntropyLoss with class_weights.
其中 class_weights 是这样定义的
from sklearn.utils import class_weight #For calculating weights for each class.
class_weights = class_weight.compute_class_weight(class_weight='balanced',classes=np.array([0,1,2,3,4]),y=train_df['level'].values)
class_weights = torch.tensor(class_weights,dtype=torch.float).to(device)
print(class_weights) #Prints the calculated weights for the classes.
输出：张量([0.2556, 4.6000, 1.5333, 9.2000, 9.2000], device='cuda:0')
在第一个纪元之后，我得到了下面给出的错误。
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
Input In [15], in <cell line: 5>()
3 nb_epochs = 3
4 #Call the optimize function.
----> 5 train_losses, valid_losses = optimize(train_dataloader,valid_dataloader,model,loss_fn,optimizer,nb_epochs)
Input In [14], in optimize(train_dataloader, valid_dataloader, model, loss_fn, optimizer, nb_epochs)
21 print(f'\nEpoch {epoch+1}/{nb_epochs}')
22 print('-------------------------------')
---> 23 train_loss = train(train_dataloader,model,loss_fn,optimizer, epoch) #Calls the train function.
24 train_losses.append(train_loss)
25 valid_loss = validate(valid_dataloader,model,loss_fn) #Calls the validate function.
Input In [12], in train(dataloader, model, loss_fn, optimizer, epoch)
24 for batch,(x,y) in enumerate(dataloader): #Iterates through the batches.
26 output = model(x.to(device)) #model's predictions.
---> 27 loss = loss_fn(output,y.to(device)) #loss calculation.
29 running_loss += loss.item()
31 total += y.size(0)
File ~/anaconda3/envs/Ammar/lib/python3.9/site-packages/torch/nn/modules/module.py:1113, in Module._call_impl(self, *input, **kwargs)
1109 # If we don't have any hooks, we want to skip the rest of the logic in
1110 # this function, and just call forward.
1111 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1112 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1113 return forward_call(*input, **kwargs)
1114 # Do not call functions when jit is used
1115 full_backward_hooks, non_full_backward_hooks = [], []
File ~/anaconda3/envs/Ammar/lib/python3.9/site-packages/torch/nn/modules/loss.py:1163, in CrossEntropyLoss.forward(self, input, target)
1162 def forward(self, input: Tensor, target: Tensor) -> Tensor:
-> 1163 return F.cross_entropy(input, target, weight=self.weight,
1164 ignore_index=self.ignore_index, reduction=self.reduction,
1165 label_smoothing=self.label_smoothing)
File ~/anaconda3/envs/Ammar/lib/python3.9/site-packages/torch/nn/functional.py:2961, in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
2959 if size_average is not None or reduce is not None:
2960 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2961 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: weight tensor should be defined either for all 1000 classes or no classes but got weight tensor of shape: [5]
抱歉，我的声望不够50，无法直接发表评论。根据错误消息，您最终得到 1000 个输出，但您只定义了五个权重。所以可以尝试输出模型，看看模型最后一层的输出是不是5，有可能是model.fc不行
我遇到了和你一样的问题。我首先更改最终分类器层的大小（我从 here 复制了代码）：
model = models.mobilenet_v2(pretrained=True)
last_item_index = len(model.classifier) - 1
old_fc = model.classifier.__getitem__(last_item_index )
new_fc = nn.Linear(in_features=old_fc.in_features,
out_features= 129, bias=True)
model.classifier.__setitem__(last_item_index , new_fc)
更改后，我使用以下代码打印了模型架构：
from torchsummary import summary
summary(model, (3, 224, 224))
它正在运行（我的数据集中 类 的数量是 129）：
(classifier): Sequential(
(0): Dropout(p=0.2, inplace=False)
(1): Linear(in_features=1280, out_features=129, bias=True)
)
我正在尝试将 VGG16 用于 ** 5 类 数据集**。 我已经添加了 5 个新层来将 logit 的输出调整为 5.
model = models.vgg16(pretrained=True) #下载在Imagenet数据集上预训练的vgg16模型。
#Replace the Final layer of pretrained vgg16 with 5 new layers.
model.fc = nn.Sequential(nn.Linear(1000,512),
nn.ReLU(inplace=True),
nn.Linear(512,256),
nn.ReLU(inplace=True),
nn.Linear(256,128),
nn.ReLU(inplace=True),
nn.Linear(128,64),
nn.ReLU(inplace=True),
nn.Linear(64,5),
)
而我的损失函数如下
loss_fn = nn.CrossEntropyLoss(weight=class_weights) #CrossEntropyLoss with class_weights.
其中 class_weights 是这样定义的
from sklearn.utils import class_weight #For calculating weights for each class.
class_weights = class_weight.compute_class_weight(class_weight='balanced',classes=np.array([0,1,2,3,4]),y=train_df['level'].values)
class_weights = torch.tensor(class_weights,dtype=torch.float).to(device)
print(class_weights) #Prints the calculated weights for the classes.
输出：张量([0.2556, 4.6000, 1.5333, 9.2000, 9.2000], device='cuda:0')
在第一个纪元之后，我得到了下面给出的错误。
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
Input In [15], in <cell line: 5>()
3 nb_epochs = 3
4 #Call the optimize function.
----> 5 train_losses, valid_losses = optimize(train_dataloader,valid_dataloader,model,loss_fn,optimizer,nb_epochs)
Input In [14], in optimize(train_dataloader, valid_dataloader, model, loss_fn, optimizer, nb_epochs)
21 print(f'\nEpoch {epoch+1}/{nb_epochs}')
22 print('-------------------------------')
---> 23 train_loss = train(train_dataloader,model,loss_fn,optimizer, epoch) #Calls the train function.
24 train_losses.append(train_loss)
25 valid_loss = validate(valid_dataloader,model,loss_fn) #Calls the validate function.
Input In [12], in train(dataloader, model, loss_fn, optimizer, epoch)
24 for batch,(x,y) in enumerate(dataloader): #Iterates through the batches.
26 output = model(x.to(device)) #model's predictions.
---> 27 loss = loss_fn(output,y.to(device)) #loss calculation.
29 running_loss += loss.item()
31 total += y.size(0)
File ~/anaconda3/envs/Ammar/lib/python3.9/site-packages/torch/nn/modules/module.py:1113, in Module._call_impl(self, *input, **kwargs)
1109 # If we don't have any hooks, we want to skip the rest of the logic in
1110 # this function, and just call forward.
1111 if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
1112 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1113 return forward_call(*input, **kwargs)
1114 # Do not call functions when jit is used
1115 full_backward_hooks, non_full_backward_hooks = [], []
File ~/anaconda3/envs/Ammar/lib/python3.9/site-packages/torch/nn/modules/loss.py:1163, in CrossEntropyLoss.forward(self, input, target)
1162 def forward(self, input: Tensor, target: Tensor) -> Tensor:
-> 1163 return F.cross_entropy(input, target, weight=self.weight,
1164 ignore_index=self.ignore_index, reduction=self.reduction,
1165 label_smoothing=self.label_smoothing)
File ~/anaconda3/envs/Ammar/lib/python3.9/site-packages/torch/nn/functional.py:2961, in cross_entropy(input, target, weight, size_average, ignore_index, reduce, reduction, label_smoothing)
2959 if size_average is not None or reduce is not None:
2960 reduction = _Reduction.legacy_get_string(size_average, reduce)
-> 2961 return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: weight tensor should be defined either for all 1000 classes or no classes but got weight tensor of shape: [5]
抱歉，我的声望不够50，无法直接发表评论。根据错误消息，您最终得到 1000 个输出，但您只定义了五个权重。所以可以尝试输出模型，看看模型最后一层的输出是不是5，有可能是model.fc不行
我遇到了和你一样的问题。我首先更改最终分类器层的大小（我从 here 复制了代码）：
model = models.mobilenet_v2(pretrained=True)
last_item_index = len(model.classifier) - 1
old_fc = model.classifier.__getitem__(last_item_index )
new_fc = nn.Linear(in_features=old_fc.in_features,
out_features= 129, bias=True)
model.classifier.__setitem__(last_item_index , new_fc)
更改后，我使用以下代码打印了模型架构：
from torchsummary import summary
summary(model, (3, 224, 224))
它正在运行（我的数据集中 类 的数量是 129）：
(classifier): Sequential(
(0): Dropout(p=0.2, inplace=False)
(1): Linear(in_features=1280, out_features=129, bias=True)
)