Pytorch框架 + MINST手写数字图像识别项目

10分钟入门神经网络 PyTorch 手写数字识别-哔哩哔哩】 https://b23.tv/nwjMNSz

pytorch tutorial: PyTorch 手写数字识别 教程代码

手写数字识别项目

安装库： pip3 install numpy torch torchvision matplotlib -i https://pypi.tuna.tsinghua.edu.cn/simple/

运行: python test.py

通过 pip list可以查看Pillow版本信息

python版本：3.12

Pillow版本信息10.4.0(注意默认是10.2.0会报错)，执行升级到最新即可

pip3 install --upgrade Pillow  -i https://pypi.tuna.tsinghua.edu.cn/simple/
 

import torch
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.datasets import MNIST
import matplotlib.pyplot as plt


class Net(torch.nn.Module):

    def __init__(self):
        super().__init__()
        self.fc1 = torch.nn.Linear(28*28, 64)
        self.fc2 = torch.nn.Linear(64, 64)
        self.fc3 = torch.nn.Linear(64, 64)
        self.fc4 = torch.nn.Linear(64, 10)
    
    def forward(self, x):
        x = torch.nn.functional.relu(self.fc1(x))
        x = torch.nn.functional.relu(self.fc2(x))
        x = torch.nn.functional.relu(self.fc3(x))
        x = torch.nn.functional.log_softmax(self.fc4(x), dim=1)
        return x


def get_data_loader(is_train):
    to_tensor = transforms.Compose([transforms.ToTensor()])
    data_set = MNIST("", is_train, transform=to_tensor, download=True)
    return DataLoader(data_set, batch_size=15, shuffle=True)


def evaluate(test_data, net):
    n_correct = 0
    n_total = 0
    with torch.no_grad():
        for (x, y) in test_data:
            outputs = net.forward(x.view(-1, 28*28))
            for i, output in enumerate(outputs):
                if torch.argmax(output) == y[i]:
                    n_correct += 1
                n_total += 1
    return n_correct / n_total


def main():

    train_data = get_data_loader(is_train=True)
    test_data = get_data_loader(is_train=False)
    net = Net()
    
    print("initial accuracy:", evaluate(test_data, net))
    optimizer = torch.optim.Adam(net.parameters(), lr=0.001)
    for epoch in range(2):
        for (x, y) in train_data:
            net.zero_grad()
            output = net.forward(x.view(-1, 28*28))
            loss = torch.nn.functional.nll_loss(output, y)
            loss.backward()
            optimizer.step()
        print("epoch", epoch, "accuracy:", evaluate(test_data, net))

    for (n, (x, _)) in enumerate(test_data):
        if n > 3:
            break
        predict = torch.argmax(net.forward(x[0].view(-1, 28*28)))
        plt.figure(n)
        plt.imshow(x[0].view(28, 28))
        plt.title("prediction: " + str(int(predict)))
    plt.show()


if __name__ == "__main__":
    main()

执行后，可以看到效果

其他：如何安装dlib 、  opencv

需要安装以下命令：

 pip3 install tensorflow -i https://pypi.tuna.tsinghua.edu.cn/simple/  

conda install -c conda-forge dlib -i https://pypi.tuna.tsinghua.edu.cn/simple/  

CV2对应opencv-python

pip3 install -i https://pypi.tuna.tsinghua.edu.cn/simple opencv-python
pip3  install -i https://pypi.tuna.tsinghua.edu.cn/simple opencv-contrib-python

 train_test_split对应 scikit-learn模块

pip3 install scikit-learn -i https://pypi.tuna.tsinghua.edu.cn/simple/