Pytorch使用tensorboard监视网络训练过程

Pytorch作为一大主流深度学习框架，在1.2版本之后自带tensorboard，这为监视训练过程带来了巨大的便利。但目前的教程多数没有写如何动态监视训练过程。在进行了一些探索后，实现了mnist分类训练动态监视这一功能，特此记录。文中分类demo来自https://blog.csdn.net/KyrieHe/article/details/80516737

1. 安装或者升级pytorch环境，安装必要依赖包；
2. 搭网络训练，但在代码中要插入如下代码，分为三个部分：

from torch.utils.tensorboard import SummaryWriter
writer = SummaryWriter() #定义writer,使用默认路径
# log_dir = 'dir_to_your_destination'
# writer = SummaryWriter(log_dir) #定义writer


writer.add_scalar('test/loss', test_loss, epoch+1) # add the information to the log file
writer.add_scalar('test/correct', correct, epoch+1)

writer.close()

程序一旦运行到writer.add_scalar后就会生成类似名字为Jan10_13-12-32_DESKTOP-G0RGKWD的文件夹，内有添加的数据
3. 从终端进入当前使用的虚拟环境和目录
4. 使用tensorboard --logdir=dir_to_your_destination --port=2200来启动tensorboard，该命令直行后会有一个连接http://localhost:2200/,将其复制粘贴到（pycharm的终端中可直接点击进入）浏览器中，即可打开
5. 选择要查看的数据进行查看，注意tensorboard是30秒更新一次数据，效果如下图


注意：

• 指定端口和完整日志路径比较容易出现效果，前期尝试中易出现无法打开或者打开后数据不对的情况，稍微多尝试几次
• 本例子只是以标量数据为例，可以添加多种类型的数据，可直接搜索查看tensorboard的官方说明
• 本例子的详细代码见https://github.com/AlvinLXS/Train_NN_with_Tensorboard

完整代码：

#!/usr/bin/env python
# encoding: utf-8
'''
@author: AlvinLXS
@time: 2020.1.10 12:50
@file: train_process.py
@desc: most part of the source codes comes from https://blog.csdn.net/KyrieHe/article/details/80516737
'''
from __future__ import absolute_import
from __future__ import print_function
from __future__ import division

import argparse  #Python 命令行解析工具
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.utils.tensorboard import SummaryWriter
writer = SummaryWriter() #定义writer,使用默认路径

# log_dir = 'dir_to_your_destination'
# writer = SummaryWriter(log_dir) #定义writer

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

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()))

def test(args, model, device, test_loader,epoch):
    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, size_average=False).item() # sum up batch loss
            pred = output.max(1, keepdim=True)[1] # 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)))
    writer.add_scalar('test/loss', test_loss, epoch+1) # add the information to the log file
    writer.add_scalar('test/correct', correct, epoch+1)

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=30, metavar='N',
                        help='number of epochs to train (default: 10)')
    parser.add_argument('--lr', type=float, default=0.000001, metavar='LR',
                        help='learning rate (default: 0.01)')  # use a small learning rate to slow the train
    parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
                        help='SGD momentum (default: 0.5)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    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')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

    device = torch.device("cuda" if use_cuda else "cpu")

    kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
    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=args.batch_size, shuffle=True, **kwargs)
    test_loader = torch.utils.data.DataLoader(
        datasets.MNIST('../data', train=False, transform=transforms.Compose([
                           transforms.ToTensor(),
                           transforms.Normalize((0.1307,), (0.3081,))
                       ])),
        batch_size=args.test_batch_size, shuffle=True, **kwargs)


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

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


if __name__ == '__main__':
    main()
    writer.close()