计算神经网络测试准确性的错误

Question

我尝试训练我的神经网络，然后评估它的测试准确性。我正在使用本文底部的代码进行培训。事实是，对于其他神经网络，我可以使用我的代码评估测试准确性而没有问题。但是，对于该神经网络（我根据神经网络论文的描述正确构建了该神经网络），我无法正确评估测试准确性，并且无法给出下面的追溯。所以也许我的前传球出了什么问题？

这是培训和测试代码：

//imports including import deepnet.py
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 = deepnet.cifar10_deep()
#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/DeepNetC2BatchSize" + 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])
                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


grid_size = 18 #How many points of interpolation between [0, 5000]
data_for_plotting = np.zeros((grid_size, 3)) #Uncomment this line if running entire code from scratch
sharpnesses1eNeg3 = []
sharpnesses5eNeg4 = []
#data_for_plotting = np.load("DeepNetCIFAR10-intermediate-values.npy") #Uncomment this line to use an existing NumPy array
print(data_for_plotting)
i = 0

# Fill in test accuracy values for `grid_size' points in the interpolation
for batch_size in batch_range:
    mydict = {}
    batchmodel = torch.load("./models/DeepNetC2BatchSize" + str(batch_size) + ".pth")
    for key, value in batchmodel.items():
        mydict[key] = value
    model.load_state_dict(mydict)

    j = 0
    for datatype in [(X_train, y_train), (X_test, y_test)]:
        dataX = datatype[0]
        datay = datatype[1]
        for smpl in np.split(np.random.permutation(range(dataX.shape[0])), 10):
            ops = opfun(dataX[smpl])
            tgts = Variable(torch.from_numpy(datay[smpl]).long().squeeze())
            var = F.nll_loss(ops, tgts).data.numpy() / 10
            if j == 1:
                data_for_plotting[i, j-1] += accfun(ops, datay[smpl]) / 10.
        j += 1
    print(data_for_plotting[i])
    np.save('DeepNetCIFAR10-intermediate-values', data_for_plotting)
    i += 1

模型代码在这里，并包括向前通过

import torch
import torch.nn as nn
F = nn.functional
__all__ = ['cifar10_deepnet', 'cifar100_deepnet']

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)

Answer 1

您正在尝试加载属于另一个模型的状态字典。

该错误表明您的模型是类AlexNet。

RunTimeError: Error(s) in loading state_dict for AlexNet:

但是您要加载的状态字典来自您发布的VGG，该模块与AlexNet没有相同的模块。

您需要使用之前保存状态的同一模型。