我正在尝试使用PyTorch上的预训练网络VGG16构建神经网络。
我了解到需要调整网络的分类器部分，因此我已经冻结了参数以防止通过它们进行反向传播。
代码:
%matplotlib inline%config InlineBackend.figure_format = 'retina'import matplotlib.pyplot as pltimport numpy as npimport timeimport torchfrom torch import nnfrom torch import optimimport torch.nn.functional as Ffrom torch.autograd import Variablefrom torchvision import datasets, transformsimport torchvision.models as modelsfrom collections import OrderedDictdata_dir = 'flowers'train_dir = data_dir + '/train'valid_dir = data_dir + '/valid'test_dir = data_dir + '/test'train_transforms = transforms.Compose([transforms.Resize(224), transforms.RandomRotation(30), transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])validn_transforms = transforms.Compose([transforms.Resize(224), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])test_transforms = transforms.Compose([ transforms.Resize(224), transforms.RandomResizedCrop(224), transforms.ToTensor(), transforms.Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225))])train_data = datasets.ImageFolder(train_dir, transform=train_transforms)validn_data = datasets.ImageFolder(valid_dir, transform=validn_transforms)test_data = datasets.ImageFolder(test_dir, transform=test_transforms)trainloader = torch.utils.data.DataLoader(train_data, batch_size=32, shuffle=True)validnloader = torch.utils.data.DataLoader(validn_data, batch_size=32, shuffle=True)testloader = torch.utils.data.DataLoader(test_data, batch_size=32, shuffle=True)model = models.vgg16(pretrained=True)modelfor param in model.parameters(): param.requires_grad = Falseclassifier = nn.Sequential(OrderedDict([ ('fc1', nn.Linear(3*224*224, 10000)), ('relu', nn.ReLU()), ('fc2', nn.Linear(10000, 5000)), ('relu', nn.ReLU()), ('fc3', nn.Linear(5000, 102)), ('output', nn.LogSoftmax(dim=1)) ]))model.classifier = classifierclassifiercriterion = nn.NLLLoss()optimizer = optim.Adam(model.classifier.parameters(), lr=0.001)model.cuda()epochs = 1steps = 0training_loss = 0print_every = 300for e in range(epochs): model.train() for images, labels in iter(trainloader): steps == 1 images.resize_(32,3*224*224) inputs = Variable(images.cuda()) targets = Variable(labels.cuda()) optimizer.zero_grad() output = model.forward(inputs) loss = criterion(output, targets) loss.backward() optimizer.step() training_loss += loss.data[0] if steps % print_every == 0: print("Epoch: {}/{}... ".format(e+1, epochs), "Loss: {:.4f}".format(training_loss/print_every)) running_loss = 0跟踪错误
ValueError Traceback (most recent call last)<ipython-input-17-30552f4b46e8> in <module>() 15 optimizer.zero_grad() 16 ---> 17 output = model.forward(inputs) 18 loss = criterion(output, targets) 19 loss.backward()/opt/conda/lib/python3.6/site-packages/torchvision-0.2.0-py3.6.egg/torchvision/models/vgg.py in forward(self, x) 39 40 def forward(self, x):---> 41 x = self.features(x) 42 x = x.view(x.size(0), -1) 43 x = self.classifier(x)/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs) 323 for hook in self._forward_pre_hooks.values(): 324 hook(self, input)--> 325 result = self.forward(*input, **kwargs) 326 for hook in self._forward_hooks.values(): 327 hook_result = hook(self, input, result)/opt/conda/lib/python3.6/site-packages/torch/nn/modules/container.py in forward(self, input) 65 def forward(self, input): 66 for module in self._modules.values():---> 67 input = module(input) 68 return input 69 /opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py in __call__(self, *input, **kwargs) 323 for hook in self._forward_pre_hooks.values(): 324 hook(self, input)--> 325 result = self.forward(*input, **kwargs) 326 for hook in self._forward_hooks.values(): 327 hook_result = hook(self, input, result)/opt/conda/lib/python3.6/site-packages/torch/nn/modules/conv.py in forward(self, input) 275 def forward(self, input): 276 return F.conv2d(input, self.weight, self.bias, self.stride,--> 277 self.padding, self.dilation, self.groups) 278 279 /opt/conda/lib/python3.6/site-packages/torch/nn/functional.py in conv2d(input, weight, bias, stride, padding, dilation, groups) 83 """ 84 if input is not None and input.dim() != 4:---> 85 raise ValueError("Expected 4D tensor as input, got {}D tensor instead.".format(input.dim())) 86 87 f = _ConvNd(_pair(stride), _pair(padding), _pair(dilation), False,ValueError: Expected 4D tensor as input, got 2D tensor instead.这是否是因为我在层定义中使用了Linear操作？
回答：
你的网络存在两个问题 –
-
你创建了自己的分类器，其第一层接受大小为(3*224*224)的输入，但这并不是vgg16特征部分的输出大小。特征输出的大小为(25088)
-
你将输入调整为形状为
(3*224*224)的张量（对于每个批次），但vgg16的特征部分期望输入形状为(3, 224, 224)。你的自定义分类器位于特征之后，所以你需要为特征而不是分类器准备输入。
