目录
一、卷积过程(基础)
If Move To GPU
#! /usr/bin/env python
# -*- coding: utf-8 -*-
"""
============================================
时间:2021.8.19
作者:手可摘星辰不去高声语
文件名:CNN.py
功能:实现上课内容
1、Ctrl + Enter 在下方新建行但不移动光标;
2、Shift + Enter 在下方新建行并移到新行行首;
3、Shift + Enter 任意位置换行
4、Ctrl + D 向下复制当前行
5、Ctrl + Y 删除当前行
6、Ctrl + Shift + V 打开剪切板
7、Ctrl + / 注释(取消注释)选择的行;
8、Ctrl + E 可打开最近访问过的文件
9、Double Shift + / 万能搜索
============================================
"""
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim
# 1.准备数据集
batch_size = 64
# batch_size = 64
transform = transforms.Compose([
transforms.ToTensor(), # 将输入的图片转化成张量
transforms.Normalize((0.1307,), (0.3081,)) # 对输入的图片进行归一化
])
train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)
# 2.设计模型
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
self.conv2 = torch.nn.Conv2d(10, 20, kernel_size=5)
self.pooling = torch.nn.MaxPool2d(2)
self.fc = torch.nn.Linear(320, 10)
def forward(self, x):
# Flatten data from (n, 1, 28, 28) to (n, 784)
batch_size = x.size(0)
x = F.relu(self.pooling(self.conv1(x)))
x = F.relu(self.pooling(self.conv2(x)))
x = x.view(batch_size, -1) # flatten
x = self.fc(x)
return x
model = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# 3.损失和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5) # 学习率0.01,冲量0.5
# 4.训练和测试
def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader, 0):
inputs, target = data # inputs是输入x,target是真实值y
optimizer.zero_grad()
# forward + backward + update
outputs = model(inputs)
loss = criterion(outputs, target)
loss.backward()
optimizer.step()
running_loss += loss.item()
if batch_idx % 300 == 299: # 将每次训练后得到一个loss,300个loss取平均值使曲线平滑
print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
running_loss = 0.0
def test():
correct = 0
total = 0
with torch.no_grad(): # 无需计算梯度
for data in test_loader:
images, labels = data
outputs = model(images)
_, predicted = torch.max(outputs.data, dim=1) # 输出的数据是一个N×10的矩阵,N表示图片数量为N,10行代表10各分类的概率,取出概率最大值(dim=1)
total += labels.size(0) # 计算第一列的数量(测试集样本总数)
correct += (predicted == labels).sum().item() # 如果预测的结果等于真实值标签,那么就把这个数记录到correct里面
print('Accuracy on test set: %.3f %%' % (100 * correct / total))
if __name__ == '__main__':
for epoch in range(10):
train(epoch)
test()
作业
二、卷积神经网络(高级)
Inception
Residual Network