import torch
from torch import nn
import d2l
# 修改1:输入通道改为3(CIFAR10是RGB图像)
net = nn.Sequential(
nn.Conv2d(3, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(), # 修改输入通道
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Conv2d(256, 384, kernel_size=3, padding=1), nn.ReLU(),
nn.Conv2d(384, 384, kernel_size=3, padding=1), nn.ReLU(),
nn.Conv2d(384, 256, kernel_size=3, padding=1), nn.ReLU(),
nn.MaxPool2d(kernel_size=3, stride=2),
nn.Flatten(),
nn.Linear(6400, 4096), nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(4096, 4096), nn.ReLU(),
nn.Dropout(p=0.5),
nn.Linear(4096, 10)) # 输出类别保持10(CIFAR10有10类)
batch_size = 128
# 修改2:加载CIFAR10数据集(保持resize=224以匹配网络输入尺寸)
train_iter, test_iter = d2l.load_data_cifar10(batch_size=batch_size, resize=224)
lr, num_epochs = 0.05, 30
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu()) 请给我加入预处理,请再看看有什么办法可以提高test acc