Machine learning `THIndexTensor(尺寸)(目标,0)=批量尺寸和x27;失败。位于d:\projects\pytorch\torch\lib\thnn\generic/ClassNLLCriterion.c:54
我试图在狗的品种数据集上训练我的神经网络。前馈后,在损耗计算过程中抛出以下错误:Machine learning `THIndexTensor(尺寸)(目标,0)=批量尺寸和x27;失败。位于d:\projects\pytorch\torch\lib\thnn\generic/ClassNLLCriterion.c:54,machine-learning,neural-network,deep-learning,conv-neural-network,pytorch,Machine Learning,Neural Network,Deep Learning,Conv Neural Network,Pytorch,我试图在狗的品种数据集上训练我的神经网络。前馈后,在损耗计算过程中抛出以下错误: RuntimeError: Assertion `THIndexTensor_(size)(target, 0) == batch_size' failed. at d:\projects\pytorch\torch\lib\thnn\generic/ClassNLLCriterion.c:54 代码: criterion =nn.CrossEntropyLoss() optimizer=optim.Adam
RuntimeError: Assertion `THIndexTensor_(size)(target, 0) == batch_size' failed. at d:\projects\pytorch\torch\lib\thnn\generic/ClassNLLCriterion.c:54
代码:
criterion =nn.CrossEntropyLoss()
optimizer=optim.Adam(net.parameters(),lr=0.001)
for epoch in range(10): # loop over the dataset multiple times
running_loss = 0.0
print(len(trainloader))
for i, data in enumerate(trainloader, 0):
# get the inputs
inputs, labels = data
# wrap them in Variable
inputs, labels = Variable(inputs).float(), Variable(labels).float().type(torch.LongTensor)
# zero the parameter gradients
optimizer.zero_grad()
# forward + backward + optimize
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# print statistics
running_loss += loss.data[0]
if i % 2000 == 1999: # print every 2000 mini-batches
print('[%d, %5d] loss: %.3f' %
(epoch + 1, i + 1, running_loss / 2000))
running_loss = 0.0
print('Finished Training')
此行中生成错误:
loss = criterion(outputs, labels)
有什么问题吗?我认为问题在于您缺少张量
标签上的批次维度。错误表明0th
维度的大小不等于批次大小
尝试更改此选项:
loss = criterion(outputs, labels.unsqueeze(0))
请注意,输出
张量应该比对应于每个标签分数的标签
张量多一个维度,标签
应该只包含正确标签的索引。您能打印输出
和标签
的形状吗?在loss=criteria(输出,标签)
之前使用print(outputs.size(),labels.size())
。下面是“print(outputs.size(),labels.size())”torch.size([2500,120])torch.size([4])的结果