前言#
為了預習大三課程，想提前學習下 PyTorch。
於是我遇到了神仙學習教程《動手學深度學習》，同時以此為參考完成了環境配置，感謝大佬們無私奉獻 Thanks♪(･ω･)ﾉ
本教程展示了獨顯 windows 電腦用 WSL Ubuntu 子系統跑 PyTorch 深度學習的環境配置，至於為什麼用 WSL 嘛。因為自己測試一番發現性能比 win 強很多。篇幅有限，省略 WSL 安裝過程。
安裝#
設備：#
Windows11: WSL-Ubuntu-22.04
1660ti-6g 獨顯
Miniconda 安裝#
Miniconda 官網 wget 方式配合鏈接下載對應 Linux 版本
wget https://repo.anaconda.com/miniconda/Miniconda3-py310_23.3.1-0-Linux-x86_64.sh
sh 指令默認安裝
sh Miniconda3-py310_23.3.1-0-Linux-x86_64.sh -b
初始化環境
~/miniconda3/bin/conda init
提示關閉該 Terminal，重新打開一個。
創建新環境，名稱 d2l 可更改。
conda create --name d2l python=3.9 -y
啟動環境
conda activate d2l
注意每次運行都要運行此指令，切換到 d2l 環境。
如要退出當前環境：conda deactivate。
如要完整刪除名為dal的環境：conda remove -n d2l --all
CUDA 安裝#
CUDA(官網)是英偉達官方的深度學習工具包，如圖是 WSL 的選項。運行下載代碼。
wget https://developer.download.nvidia.com/compute/cuda/repos/wsl-ubuntu/x86_64/cuda-wsl-ubuntu.pin
sudo mv cuda-wsl-ubuntu.pin /etc/apt/preferences.d/cuda-repository-pin-600
wget https://developer.download.nvidia.com/compute/cuda/12.1.1/local_installers/cuda-repo-wsl-ubuntu-12-1-local_12.1.1-1_amd64.deb
sudo dpkg -i cuda-repo-wsl-ubuntu-12-1-local_12.1.1-1_amd64.deb
sudo cp /var/cuda-repo-wsl-ubuntu-12-1-local/cuda-*-keyring.gpg /usr/share/keyrings/
sudo apt-get update
sudo apt-get -y install cuda
添加完成後需更新~/.bashrc文件
sudo vi ~/.bashrc
i進入 insert 模式，添加以下代碼到文件最後，注意修改為對應版本。
export PATH=/usr/local/cuda-12.1/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-12.1/lib64\
${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
Esc, :wq，回車保存。
source ~/.bashrc
運行以下代碼，輸出如圖則 CUDA 安裝成功。
nvcc -V
安裝 PyTorch 框架#
GPU 版本的需要在PyTorch 官網選擇，我下的是 Preview 版本的剛好適配 CUDA12.1 如圖，不過向下兼容性也不錯。
conda install pytorch torchvision torchaudio pytorch-cuda=12.1 -c pytorch-nightly -c nvidia
下載 d2l 包
pip install d2l==0.17.6
顯卡測試#
克隆測試文件
git clone https://github.com/pytorch/examples.git
cd example_pytorch/mnist/
替換main.py文件內容為以下：
from __future__ import print_function
import argparse
import torch
import time
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=14, 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=False,
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': 5, #線程數
'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)
start_time = time.time()
for epoch in range(1, args.epochs + 1):
train(args, model, device, train_loader, optimizer, epoch)
test(model, device, test_loader)
scheduler.step()
end_time = time.time()
total_time = end_time - start_time
print(f"Total time: {total_time:.2f} seconds.")
if args.save_model:
torch.save(model.state_dict(), "mnist_cnn.pt")
if __name__ == '__main__':
main()
此處採用 5 線程，可自行修改。
運行對應模式測速，根據配置可能 cpu 和 gpu 運行代碼剛好相反。
$ python main.py #cpu模式
$ CUDA_VISIBLE_DEVICES=2 python main.py #gpu模式
測試代碼來源及參考：
pytorch/examples - github
深度學習：Windows11 VS WSL2 VS Ubuntu 性能對比，pytorch2.0 性能測試！
完成！#
至此環境配置完畢，我繼續跟隨《動手學深度學習》了。
mkdir d2l-zh && cd d2l-zh
curl https://zh-v2.d2l.ai/d2l-zh-2.0.0.zip -o d2l-zh.zip
unzip d2l-zh.zip && rm d2l-zh.zip
cd pytorch
。。。。。