深度学习模型训练可视化工具wandb使用说明

1. wandb安装

pip install wandb -i https://pypi.tuna.tsinghua.edu.cn/simple
使用清华的源，快速安装。

2.wandb注册使用

2.1注册页面

https://wandb.ai/login?signup=true

2.2 获取API keys页面

https://wandb.ai/settings

3.使用过程演示

3.1 演示代码

演示代码来源：https://www.fpga-china.com/15139.html
这里为了提高可读性，将代码放在文章最后。

3.2演示操作

1.代码保存文件为test.py
2.在终端运行python test.py(注：本人在pycharm界面运行，wandb无法被调用)
3.运行结束后，终端显示：

然后运行倒数第二行：wandb sync /root/wandb/offline-run-20220707_105059-3hak77i5（注：pycharm中路径要用双引号或单引号，否则可能报错）
然后输入API keys（注：keys不会在界面显示），直接回车。得到如下结果：

最后一行网址，打开之后，结果如下图：

4.演示用到的代码：

from __future__ import print_function
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
import argparse
import torch
import wandb
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
import torch.utils.data



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, wandb):
    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()))
            wandb.log({
                "epoch": epoch,
                "loss": loss,
            })
            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, 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('--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()
    print("use_cuda:%s", str(use_cuda))
    torch.manual_seed(args.seed)
    device = torch.device("cuda" if use_cuda else "cpu")
    train_kwargs = {'batch_size': args.batch_size}
    test_kwargs = {'batch_size': args.test_batch_size}
    config = dict(
        batch_size=args.batch_size,
        epochs=args.epochs,
        learning_rate=args.lr,
        gamma=args.gamma)
    wandb.init(
        project="wandb-mnist",
        config=config,
        mode="offline")
    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, wandb)
        test(model, device, test_loader)
        scheduler.step()
    if args.save_model:
        torch.save(model.state_dict(), "mnist_cnn.pt")


if __name__ == '__main__':
    main()

参考内容：https://www.fpga-china.com/15139.html