在 Mac M1 上运行 pytorch MNIST 模型

2023-02-17     tech vscode python

%load pytorch-m1-gpu-mnist.py
%run pytorch-m1-gpu-mnist.py

Train Epoch: 5 [0/60000 (0%)]	Loss: 0.046214
Train Epoch: 5 [1280/60000 (2%)]	Loss: 0.054890
Train Epoch: 5 [2560/60000 (4%)]	Loss: 0.126030
Train Epoch: 5 [3840/60000 (6%)]	Loss: 0.037496
Train Epoch: 5 [5120/60000 (9%)]	Loss: 0.082181
Train Epoch: 5 [6400/60000 (11%)]	Loss: 0.037875
Train Epoch: 5 [7680/60000 (13%)]	Loss: 0.085949
Train Epoch: 5 [8960/60000 (15%)]	Loss: 0.060418
Train Epoch: 5 [10240/60000 (17%)]	Loss: 0.118635
Train Epoch: 5 [11520/60000 (19%)]	Loss: 0.023937
Train Epoch: 5 [12800/60000 (21%)]	Loss: 0.182207
Train Epoch: 5 [14080/60000 (23%)]	Loss: 0.076019
Train Epoch: 5 [15360/60000 (26%)]	Loss: 0.033017
Train Epoch: 5 [16640/60000 (28%)]	Loss: 0.055296
Train Epoch: 5 [17920/60000 (30%)]	Loss: 0.028324
Train Epoch: 5 [19200/60000 (32%)]	Loss: 0.049647
Train Epoch: 5 [20480/60000 (34%)]	Loss: 0.056441
Train Epoch: 5 [21760/60000 (36%)]	Loss: 0.079691
Train Epoch: 5 [23040/60000 (38%)]	Loss: 0.065786
Train Epoch: 5 [24320/60000 (41%)]	Loss: 0.064102
Train Epoch: 5 [25600/60000 (43%)]	Loss: 0.165235
Train Epoch: 5 [26880/60000 (45%)]	Loss: 0.047473
Train Epoch: 5 [28160/60000 (47%)]	Loss: 0.123398
Train Epoch: 5 [29440/60000 (49%)]	Loss: 0.044776
Train Epoch: 5 [30720/60000 (51%)]	Loss: 0.070954
Train Epoch: 5 [32000/60000 (53%)]	Loss: 0.048687
Train Epoch: 5 [33280/60000 (55%)]	Loss: 0.129717
Train Epoch: 5 [34560/60000 (58%)]	Loss: 0.075629
Train Epoch: 5 [35840/60000 (60%)]	Loss: 0.026882
Train Epoch: 5 [37120/60000 (62%)]	Loss: 0.035822
Train Epoch: 5 [38400/60000 (64%)]	Loss: 0.020158
Train Epoch: 5 [39680/60000 (66%)]	Loss: 0.037771
Train Epoch: 5 [40960/60000 (68%)]	Loss: 0.024614
Train Epoch: 5 [42240/60000 (70%)]	Loss: 0.070286
Train Epoch: 5 [43520/60000 (72%)]	Loss: 0.104104
Train Epoch: 5 [44800/60000 (75%)]	Loss: 0.021874
Train Epoch: 5 [46080/60000 (77%)]	Loss: 0.027039
Train Epoch: 5 [47360/60000 (79%)]	Loss: 0.029215
Train Epoch: 5 [48640/60000 (81%)]	Loss: 0.033327
Train Epoch: 5 [49920/60000 (83%)]	Loss: 0.008433
Train Epoch: 5 [51200/60000 (85%)]	Loss: 0.058720
Train Epoch: 5 [52480/60000 (87%)]	Loss: 0.039366
Train Epoch: 5 [53760/60000 (90%)]	Loss: 0.109450
Train Epoch: 5 [55040/60000 (92%)]	Loss: 0.042343
Train Epoch: 5 [56320/60000 (94%)]	Loss: 0.077304
Train Epoch: 5 [57600/60000 (96%)]	Loss: 0.021365
Train Epoch: 5 [58880/60000 (98%)]	Loss: 0.090809

Test set: Average loss: 0.0475, Accuracy: 9853/10000 (99%)

"""
MNIST with PyTorch on Apple Silicon GPU

Script will be linked in the description as a Github Gist.

Install PyTorch nightly with this command:
pip3 install --pre torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/nightly/cpu

Code borrowed from PyTorch Examples.
"""

import torch
from torch import nn, optim
import torch.nn.functional as F
import torchvision
from torchvision import datasets, transforms

EPOCHS = 5

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 20, 5, 1)
        self.conv2 = nn.Conv2d(20, 50, 5, 1)
        self.fc1 = nn.Linear(4*4*50, 500)
        self.fc2 = nn.Linear(500, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2, 2)
        x = x.view(-1, 4*4*50)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

def train(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 % 10 == 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()))

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():
    print("PyTorch version:", torch.__version__)
    print("Torchvision version:", torchvision.__version__)

    device = torch.device("mps")
    print("Using Device: ", device)

    train_loader = torch.utils.data.DataLoader(
        datasets.MNIST('../data', train=True, download=True,
                       transform=transforms.Compose([
                           transforms.ToTensor(),
                           transforms.Normalize((0.1307,), (0.3081,))
                       ])),
        batch_size=128, shuffle=True)
    test_loader = torch.utils.data.DataLoader(
        datasets.MNIST('../data', train=False, transform=transforms.Compose([
                           transforms.ToTensor(),
                           transforms.Normalize((0.1307,), (0.3081,))
                       ])),
        batch_size=128, shuffle=True)


    model = Net().to(device)
    optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

    for epoch in range(1, EPOCHS + 1):
        train(model, device, train_loader, optimizer, epoch)
        test(model, device, test_loader)

if __name__ == "__main__":
    main()