编程基础很弱,需要机器学习,学习记录,按自己理解写的,希望以后能学懂吧,要是有大神看到还请赐教。
一般来说,网络和代码分开。在模型中引入网络。
# 搭建神经网络
import torch
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
class Tudui(nn.Module):
def __init__(self):
super(Tudui, self).__init__()
self.model1 = 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.model1(x)
return x
# 很多人喜欢在这里测试网络正确性
if __name__ == '__main__':
tudui = Tudui()
input = torch.ones((64, 3, 32, 32))
output = tudui(input)
print(output.shape)
import torch.optim
import torchvision.datasets
from torch.utils.tensorboard import SummaryWriter
from modelCIFAR10 import *
from torch import nn
from torch.nn import Conv2d, MaxPool2d, Flatten, Linear
from torch.utils.data import DataLoader
# 准备数据集
train_data = torchvision.datasets.CIFAR10(root='./dataset', train=True, transform=torchvision.transforms.ToTensor(),
download=True)
test_data = torchvision.datasets.CIFAR10(root='./dataset', train=False, transform=torchvision.transforms.ToTensor(),
download=True)
# 看看数据集多大
train_data_size = len(train_data)
test_data_size = len(test_data)
print(train_data_size)
print(test_data_size)
# 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
tudui = Tudui()
# 创建损失函数
loss_function = nn.CrossEntropyLoss()
# 创建优化器
learning_rate = 0.01
optimizer = torch.optim.SGD(tudui.parameters(), lr=learning_rate)
# 设置训练网络的一些参数
total_train_step = 0 # 用这个变量记录训练的次数
total_test_step = 0 # 用这个变量记录测试的次数
# 设置训练的轮数
epoch = 10
# 添加tensorboard
writer = SummaryWriter("logs")
# 开始写循环
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
output = tudui(imgs)
loss = loss_function(output, targets)
# 优化器优化模型
optimizer.zero_grad()
loss.backward()
optimizer.step()
# 记录训练次数
total_train_step = total_train_step + 1
# 不让它每次训练都打印
if total_train_step % 100 == 0:
print("训练次数{},损失值{}".format(total_train_step, loss.item()))
writer.add_scalar("Train Loss", loss.item(), total_train_step)
# 每轮训练完后在测试集上跑一遍,以评估是否训练好
'''在测试过程中不需要对模型调优,因为是想测试这个当前模型效果,因此不需要调优'''
# 测试步骤开始
total_test_loss = 0
total_accuracy=0#
with torch.no_grad(): # 在with内的代码没有梯度,保证不会进行调优
for data in test_dataloader:
imgs, targets = data
outputs = tudui(imgs)
loss = loss_function(outputs, targets)
total_test_loss = total_test_loss + loss.item()
total_test_step = total_test_step + 1
accuracy= (outputs.argmax(1)==targets).sum()#这里没太明白,回头再仔细研究一下
total_accuracy = total_accuracy+accuracy#
print("整体测试集loss{}".format(total_test_loss))
print("整体测试集上的正确率:{}".format(total_accuracy/test_data_size))
writer.add_scalar("Test Loss", total_test_loss, total_test_step)
writer.add_scalar("Test accuracy",total_accuracy/test_data_size,total_test_step)
#保存每轮训练模型
torch.save(tudui,"tudui_{}.pth".format(i+1))
print("模型已保存")
writer.close()
一些小细节:
#有些代码会在训练前输入.train()
#在测试前输入.eval()
...
for i in range(epoch):
print("第{}轮训练开始".format(i + 1))
# 训练步骤开始
tudui.train()
for data in train_dataloader:
imgs, targets = data
...
# 仅对一些网络层有作用,如Dropout等
整个流程:
1.准备数据集
2.DataLoader
3.创建网络模型
4.创建损失函数
5.创建优化器
6.设置训练参数
7.设置训练轮数
8.取数据计算误差反向传播优化
9.采用特定方式进行输出展示
10.在一轮完成后或特定步骤中进行测试(注意不用梯度)