architecture - Pytorch cifar 数据集：RuntimeError：大小不匹配，m1：[4 x 2048]，m2：[1568 x 10]

Question

我正在使用 2 个基本层制作自己的网络，并在 CIFAR10 数据集上进行训练。我收到不匹配错误。

import torch
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import Dataset, DataLoader
import torch.nn as nn

device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')

num_epochs = 5
num_classes = 10
batch_size = 4
learning_rate = 0.001

print("---------Train Dataset----------")
train_dataset = torchvision.datasets.CIFAR10(root='../data/', train=True,
                                             transform=transforms.ToTensor(), download=True)

print("---------Train Loader----------")
train_loader = torch.utils.data.DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)


class ConvNet(nn.Module):
    def __init__(self, num_classes=10):
        super(ConvNet, self).__init__()

        # First Layer
        self.layer1 = nn.Sequential(
            nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        # Second Layer
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))

        # Fully connected Layer
        self.fc = nn.Linear(7 * 7 * 32, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out


model = ConvNet(num_classes).to(device)

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

print("--------Train Model----------")

total_step = len(train_loader)
print("Total Step", total_step)

for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):

        images = images.to(device)
        labels = labels.to(device)

        print("-----Forward Pass-------")
        outputs = model(images)
        loss = criterion(outputs, labels)

        print ("----Backward Pass-------")
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i+1) % 100 == 0:
            print(epoch+1, num_epochs, i+1, total_step, loss.item())

标签： architecturedatasetpytorchconv-neural-network