# 下載
wget https://github.com/conda-forge/miniforge/releases/latest/download/Mambaforge-MacOSX-arm64.sh
# 安裝
bash Mambaforge-MacOSX-arm64.sh

mamba create -n pytorch \
   jupyterlab jupyterhub pytorch torchvision torchaudio 
   -c pytorch-nightly

import torch
torch.has_mps
# True
# 配置device
device = torch.device("mps")

conda create -n pytorch pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia

import torch
torch.has_cuda
# True

import torch
import torchvision
import torchvision.transforms as transforms

# 轉(zhuǎn)換數(shù)據(jù)格式并且加載數(shù)據(jù)
transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5,), (0.5,))])

trainset = torchvision.datasets.MNIST(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64,
                                          shuffle=True, num_workers=2)

testset = torchvision.datasets.MNIST(root='./data', train=False,
                                       download=False, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=64,
                                         shuffle=False, num_workers=2)

# 定義網(wǎng)絡(luò)模型
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 6, 5)
        self.pool = torch.nn.MaxPool2d(2, 2)
        self.conv2 = torch.nn.Conv2d(6, 16, 5)
        self.fc1 = torch.nn.Linear(16 * 4 * 4, 120)
        self.fc2 = torch.nn.Linear(120, 84)
        self.fc3 = torch.nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(torch.nn.functional.relu(self.conv1(x)))
        x = self.pool(torch.nn.functional.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = torch.nn.functional.relu(self.fc1(x))
        x = torch.nn.functional.relu(self.fc2(x))
        x = self.fc3(x)
        return x

net = Net()

# 這里的代碼比較隨意，就是用哪個(gè)平臺(tái)運(yùn)行哪個(gè)
# CPU
device = torch.device("cpu")
# CUDA
device = torch.device("cuda:0")
# MPS
device = torch.device("mps")

net.to(device)

# 定義損失函數(shù)和優(yōu)化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# 訓(xùn)練網(wǎng)絡(luò)

import time

start_time = time.time()  # 記錄開(kāi)始時(shí)間

for epoch in range(10):  # 進(jìn)行10次迭代訓(xùn)練
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)
        optimizer.zero_grad()
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 100 == 99:
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

end_time = time.time()  # 記錄結(jié)束時(shí)間
training_time = end_time - start_time  # 計(jì)算訓(xùn)練時(shí)間

print('Training took %.2f seconds.' % training_time)

print('Finished Training')

# 測(cè)試網(wǎng)絡(luò)
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data[0].to(device), data[1].to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
      ))