我正在尝试训练我的用PyTorch编写的神经网络，但是由于尺寸错误，我得到了以下回溯。得到了以下回溯
Traceback (most recent call last):
File "plot_parametric_pytorch.py", line 139, in <module>
ops = opfun(X_train[smpl])
File "plot_parametric_pytorch.py", line 92, in <lambda>
opfun = lambda X: model.forward(Variable(torch.from_numpy(X)))
File "/mnt_home/klee/LBSBGenGapSharpnessResearch/deepnet.py", line 77, in forward
x = self.features(x)
File "/home/klee/anaconda3/envs/sharpenv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/home/klee/anaconda3/envs/sharpenv/lib/python3.7/site-packages/torch/nn/modules/container.py", line 100, in forward
input = module(input)
File "/home/klee/anaconda3/envs/sharpenv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 550, in __call__
result = self.forward(*input, **kwargs)
File "/home/klee/anaconda3/envs/sharpenv/lib/python3.7/site-packages/torch/nn/modules/pooling.py", line 141, in forward
self.return_indices)
File "/home/klee/anaconda3/envs/sharpenv/lib/python3.7/site-packages/torch/_jit_internal.py", line 209, in fn
return if_false(*args, **kwargs)
File "/home/klee/anaconda3/envs/sharpenv/lib/python3.7/site-packages/torch/nn/functional.py", line 539, in _max_pool2d
input, kernel_size, stride, padding, dilation, ceil_mode)
RuntimeError: Given input size: (512x1x1). Calculated output size: (512x0x0). Output size is too small
这就是尝试运行前向通行证的全部。我很确定这是一个小错误，但是我本人是编写PyTorch代码的新手，所以不确定是否知道它在哪里。作为参考，当我使用model.summary（）检查了Keras模型版本的尺寸时，在展平并添加密集层之前的最终尺寸（我认为应该发生在pytorch的self.classifier中，我也不确定）是512 x 1 x 1。
这是我在PyTorch中的模型：
class VGG(nn.Module): def __init__(self, num_classes=10): super(VGG, self).__init__() self.features = nn.Sequential( nn.Conv2d(3, 64, kernel_size=3, bias=False), nn.BatchNorm2d(64), nn.ReLU(inplace=True), nn.Dropout(0.3), nn.Conv2d(64, 64, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(64), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(64, 128, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(128), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(128, 128, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(128), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(128, 256, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(256), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(256, 256, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(256), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(256, 256, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(256), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(256, 512, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.Dropout(0.4), nn.Conv2d(512, 512, kernel_size=3, padding = 1, bias=False), nn.BatchNorm2d(512), nn.ReLU(inplace=True), nn.MaxPool2d(kernel_size=2, stride=2), ) self.classifier = nn.Sequential( nn.Linear(512, 512, bias=False), nn.Dropout(0.5), nn.BatchNorm1d(512), nn.ReLU(inplace=True), nn.Dropout(0.5), nn.Linear(512, num_classes) ) def forward(self, x): x = self.features(x) x = x.view(-1, 512) x = self.classifier(x) return F.log_softmax(x) def cifar10_deep(**kwargs): num_classes = getattr(kwargs, 'num_classes', 10) return VGG(num_classes) def cifar100_deep(**kwargs): num_classes = getattr(kwargs, 'num_classes', 100) return VGG(num_classes)而且我正在尝试运行以下代码：
cudnn.benchmark = True (X_train, y_train), (X_test, y_test) = cifar10.load_data() X_train = X_train.astype('float32') X_train = np.transpose(X_train, axes=(0, 3, 1, 2)) X_test = X_test.astype('float32') X_test = np.transpose(X_test, axes=(0, 3, 1, 2)) X_train /= 255 X_test /= 255 device = torch.device('cuda:0') # This is where you can load any model of your choice. # I stole PyTorch Vision's VGG network and modified it to work on CIFAR-10. # You can take this line out and add any other network and the code # should run just fine. model = cifar_shallow.cifar10_shallow() #model.to(device) # Forward pass opfun = lambda X: model.forward(Variable(torch.from_numpy(X))) # Forward pass through the network given the input predsfun = lambda op: np.argmax(op.data.numpy(), 1) # Do the forward pass, then compute the accuracy accfun = lambda op, y: np.mean(np.equal(predsfun(op), y.squeeze()))*100 # Initial point x0 = deepcopy(model.state_dict()) # Number of epochs to train for # Choose a large value since LB training needs higher values # Changed from 150 to 30 nb_epochs = 30 batch_range = [25, 40, 50, 64, 80, 128, 256, 512, 625, 1024, 1250, 1750, 2048, 2500, 3125, 4096, 4500, 5000] # parametric plot (i.e., don't train the network if set to True) hotstart = False if not hotstart: for batch_size in batch_range: optimizer = torch.optim.Adam(model.parameters()) model.load_state_dict(x0) #model.to(device) average_loss_over_epoch = '-' print('Optimizing the network with batch size %d' % batch_size) np.random.seed(1337) #So that both networks see same sequence of batches for e in range(nb_epochs): model.eval() print('Epoch:', e, ' of ', nb_epochs, 'Average loss:', average_loss_over_epoch) average_loss_over_epoch = 0 # Checkpoint the model every epoch torch.save(model.state_dict(), "./models/ShallowNetCIFAR10BatchSize" + str(batch_size) + ".pth") array = np.random.permutation(range(X_train.shape[0])) slices = X_train.shape[0] // batch_size beginning = 0 end = 1 # Training loop! for _ in range(slices): start_index = batch_size * beginning end_index = batch_size * end smpl = array[start_index:end_index] model.train() optimizer.zero_grad() ops = opfun(X_train[smpl]) <<----- error in this line tgts = Variable(torch.from_numpy(y_train[smpl]).long().squeeze()) loss_fn = F.nll_loss(ops, tgts) average_loss_over_epoch += loss_fn.data.numpy() / (X_train.shape[0] // batch_size) loss_fn.backward() optimizer.step() beginning += 1 end += 1我想知道我的模型哪里出错了。我正在编写以下Keras模型的PyTorch版本。修复小错误的任何帮助将不胜感激！
def deepnet(nb_classes): global img_size model = Sequential() model.add(Conv2D(64, (3, 3), input_shape=img_size)) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) model.add(Dropout(0.3)) model.add(Conv2D(64, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same')) model.add(Conv2D(128, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(128, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same')) model.add(Conv2D(256, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(256, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(256, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same')) model.add(Conv2D(512, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(512, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(512, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same')) model.add(Conv2D(512, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(512, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')); model.add(Dropout(0.4)) model.add(Conv2D(512, (3, 3), padding='same')) model.add(BatchNormalization(axis=1)) model.add(Activation('relu')) model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='same')) model.add(Flatten()); model.add(Dropout(0.5)) model.add(Dense(512)) model.add(BatchNormalization()) model.add(Activation('relu')); model.add(Dropout(0.5)) model.add(Dense(nb_classes, activation='softmax')) return model[请让我知道将神经网络模型从PyTorch转换为Keras的方式是否存在问题。据我了解，由于pyras中的padding = same设置相同，pytorch中的padding应该始终等于1。
我正在尝试训练我的用PyTorch编写的神经网络，但是由于尺寸错误，我得到了以下回溯。获得了以下回溯Traceback（最近一次通话）：...
第一个卷积不使用填充。