我是PyTorch的新手。
我已经实现了一个自定义模型(基于一篇研究论文)，当我试图训练它时，我得到了这个错误。
element 0 of tensors does not require grad and does not have a grad_fn
下面是我的模型代码:
class Classification(tnn.Module):
def __init__(self, n_classes=7):
super(Classification, self).__init__()
self.feature_extractor1 = VGG16FeatureExtactor() # tnn.Module
self.feature_extractor2 = VGG16FeatureExtactor() # tnn.Module
self.conv = conv_layer_relu(chann_in=512, chann_out=512, k_size=1, p_size=0) # tnn.Sequential
self.attn1 = AttentionBlock1() # tnn.Module
self.attn2 = AttentionBlock2() # tnn.Module
# FC layers
self.linear1 = vggFCLayer(512, 256) # tnn.Sequential
self.linear2 = vggFCLayer(256, 128) # tnn.Sequential
# Final layer
self.final = tnn.Linear(128, n_classes)
def forward(self, x, x_lbp):
features1 = self.feature_extractor1(x)
features2 = self.feature_extractor2(x_lbp)
f3 = torch.add(features1, features2)
# Apply attention block1 to features1
attn1 = self.attn1(features1)
# Create mask using Attention Block 2
attn2 = self.attn2(features2)
mask = attn1 * attn2
add = f3 + mask
out = self.conv(add)
out = out.view(out.size(0), -1)
out = self.linear1(out)
out = self.linear2(out)
out = self.final(out)
return out
下面是我的培训代码:
criterion = nn.CrossEntropyLoss(weight=weights)
optimizer = optim.SGD(model.parameters(), lr=lr,momentum=0.9, nesterov=True)
scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, 'min')
def train(self, epoch, trainloader):
self.model.train()
for batch_idx, (inputs, targets) in enumerate(trainloader):
lbp = lbp_transform(inputs)
self.optimizer.zero_grad()
with torch.no_grad():
outputs = self.model(inputs, lbp)
loss = self.criterion(outputs, targets)
loss.backward()
self.scheduler.step(loss)
utils.clip_gradient(self.optimizer, 0.1)
self.optimizer.step()
下面是完整的错误堆栈跟踪:
RuntimeError Traceback (most recent call last)
<ipython-input-17-b4e6536e5301> in <module>()
1 modelTraining = train_vggwithattention.ModelTraining(model = model , criterion=criterion,optimizer=optimizer, scheduler=scheduler, use_cuda=True)
2 for epoch in range(start_epoch, num_epochs):
----> 3 modelTraining.train(epoch=epoch, trainloader=trainloader)
4 # PublicTest(epoch)
5 # writer.flush()
2 frames
/content/train_vggwithattention.py in train(self, epoch, trainloader)
45 loss = self.criterion(outputs, targets)
46 # loss.requires_grad = True
---> 47 loss.backward()
48 for name, param in self.model.named_parameters():
49 print(name, param.grad)
/usr/local/lib/python3.7/dist-packages/torch/_tensor.py in backward(self, gradient, retain_graph, create_graph, inputs)
253 create_graph=create_graph,
254 inputs=inputs)
--> 255 torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
256
257 def register_hook(self, hook):
/usr/local/lib/python3.7/dist-packages/torch/autograd/__init__.py in backward(tensors, grad_tensors, retain_graph, create_graph, grad_variables, inputs)
147 Variable._execution_engine.run_backward(
148 tensors, grad_tensors_, retain_graph, create_graph, inputs,
--> 149 allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag
150
151
RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn
任何帮助都是感激的。谢谢!
您正在使用torch.no_grad()上下文管理器推断输出，这意味着层的激活将不会被保存，并且反向传播将不可能。
因此，您必须替换train函数中的以下行:
with torch.no_grad():
outputs = self.model(inputs, lbp)
与简单:
outputs = self.model(inputs, lbp)