一、搭建神经网络
网络模型的架构是根据CIFAR10网络模型搭建的。
import torch
from torch import nn
# 搭建神经网络
class Cow(nn.Module):
def __init__(self):
super(Cow, self).__init__()
self.model = nn.Sequential(
nn.Conv2d(3, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 32, 5, 1, 2),
nn.MaxPool2d(2),
nn.Conv2d(32, 64, 5, 1, 2),
nn.MaxPool2d(2),
nn.Flatten(),
nn.Linear(64 * 4 * 4, 64),
nn.Linear(64, 10)
)
def forward(self, x):
x = self.model(x)
return x
if __name__ == '__main__':
cow = Cow()
input = torch.ones((64, 3, 32, 32))
output = cow(input)
print(output.shape)
二、训练模型
import torchvision
from torch.utils.data import DataLoader
from model import *
# 准备数据集
train_data = torchvision.datasets.CIFAR10("./dataset", train=True, transform=torchvision.transforms.ToTensor(), download=True)
test_data = torchvision.datasets.CIFAR10("./dataset", train=False, transform=torchvision.transforms.ToTensor(), download=True)
# 查看训练集和验证集的长度
train_data_size = len(train_data)
test_data_size = len(test_data)
print("训练数据集的长度为:{}".format(train_data_size))
print("测试数据集的长度为:{}".format(test_data_size))
# 利用Dataloader来加载数据集
train_dataloader = DataLoader(train_data, batch_size=64)
test_dataloader = DataLoader(test_data, batch_size=64)
# 创建网络模型
cow = Cow()
# 损失函数,使用交叉熵损失函数
loss_fn = nn.CrossEntropyLoss()
# 优化器
# 1e-3 = 1 x 10^(-3) = 0.001
learning_rate = 1e-3
optimizer = torch.optim.SGD(cow.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练的次数
total_train_step = 0
# 记录测试的次数
total_test_step = 0
# 训练的轮数
epoch = 10
for i in range(epoch):
print("------第{}轮训练开始".format(i+1))
# 训练步骤开始
for data in train_dataloader:
imgs, targets = data
outputs = cow(imgs)
loss = loss_fn(outputs, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_train_step = total_train_step + 1
print("训练次数:{}, Loss:{}".format(total_train_step, loss.item()))
其中loss.item跟直接使用loss相比,可以将输出转换为一个真实的数字,如下:
import torch
a = torch.tensor(5)
print(a)
print(a.item)
运行结果:
tensor(5)
5