#AI挑战营第一站#基于Pytorch的NN神经网络识别MNIST数据集

吾妻思萌

#AI挑战营第一站#基于Pytorch的NN神经网络识别MNIST数据集 [复制链接]

训练过程

CPU：I5-3210M 2.2GHz 双核心四线程

GPU：cuda无暂没启用

RAM：6G

pytorch 2.2.2

python 3.1.2

总的来说，MNIST时间悠久，基本上是图像识别的入门级课程，几乎每一个接触pytorch、tensorflow等主流机器学习框架的友友们都接触过的数据集咯。所以手写数字识别可以说是入门的门槛吧。而且其实不需要高端的显卡，很好的配置，楼主2012服役的十几年老兵还能跑起来，所以快跟着一起动手吧。

主要步骤：

1. 知其然知其所以然：先了解了解pytorch：https://pytorch.org/tutorials/，大家可以跟着这个教程去了解。
2. 看千万遍不如跑一遍：在上述链接都有一步一步步骤来即可，官方库有着丰富的模型和实例代码  
3. 训练基本就是修改Epoch参数，俗称炼丹。下面展示下训练一轮和训练6轮的结果

测试结果

训练一轮

训练六轮

解说&分享训练代码

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.optim.lr_scheduler import StepLR



class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):

        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output


def train(args, model, device, train_loader, optimizer, epoch):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))
            if args.dry_run:
                break


def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


def main():
      # Training settings
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=6, metavar='N',
                        help='number of epochs to train (default: 14)')
    parser.add_argument('--lr', type=float, default=1.0, metavar='LR',
                        help='learning rate (default: 1.0)')
    parser.add_argument('--gamma', type=float, default=0.7, metavar='M',
                        help='Learning rate step gamma (default: 0.7)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--no-mps', action='store_true', default=False,
                        help='disables macOS GPU training')
    parser.add_argument('--dry-run', action='store_true', default=False,
                        help='quickly check a single pass')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    parser.add_argument('--save-model', action='store_true', default=True,
                        help='For Saving the current Model')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()
    use_mps = not args.no_mps and torch.backends.mps.is_available()

    torch.manual_seed(args.seed)

    if use_cuda:
        device = torch.device("cuda")
    elif use_mps:
        device = torch.device("mps")
    else:
        device = torch.device("cpu")

    train_kwargs = {'batch_size': args.batch_size}
    test_kwargs = {'batch_size': args.test_batch_size}
    if use_cuda:
        cuda_kwargs = {'num_workers': 1,
                       'pin_memory': True,
                       'shuffle': True}
        train_kwargs.update(cuda_kwargs)
        test_kwargs.update(cuda_kwargs)

    transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
        ])
    dataset1 = datasets.MNIST('./data', train=True, download=True,
                    transform=transform
                    )
    dataset2 = datasets.MNIST('./data', train=False,
                    transform=transform
                    )
    train_loader = torch.utils.data.DataLoader(dataset1,**train_kwargs)
    test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)

    model = Net().to(device)
    optimizer = optim.Adadelta(model.parameters(), lr=args.lr)

    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)
        scheduler.step()

    if args.save_model:
        torch.save(model.state_dict(), "mnist_cnn.pt")
        x = torch.randn(args.batch_size,1,28,28,requires_grad=True)
        torch_out = model(x)
        torch.onnx.export(model, 
                          x,
                          "mnist_cnn.onnx",
                          export_params=True,
                          opset_version=10,
                          do_constant_folding=True,
                          input_names = ['input'],
                          output_names = ['output'],
                          dynamic_axes={'input' : {0 : 'batch_size'},
                                        'output' : {0 : 'batch_size'}})


if __name__ == '__main__':
    main()

代码是官方的加了点生成onnx的部分。

值得注意：如果你的python是3.12最新的，官方库中提供的torch.onnx.dynamo_export方法好像不支持python3.12，但是楼主没有仔细测哪个版本可以，有友友能够测试下吗？

 

 

附上最终生成的模型文件*.pth，以及转换的ONNX模型。

main.py (6.28 KB, 下载次数: 0)

2024-4-15 23:32 上传

点击文件名下载附件

mnist_cnn.pt (4.58 MB, 下载次数: 0)

2024-4-15 23:32 上传

点击文件名下载附件

mnist_cnn.onnx (4.58 MB, 下载次数: 3)

2024-4-15 23:32 上传

点击文件名下载附件

wangerxian

一看就是经常玩机器学习的~