35- tensorboard的使用 (PyTorch系列) (深度学习)

知识要点

• FashionMNIST数据集: 十种产品的分类.        # T-shirt/top, Trouser, Pullover, Dress, Coat,Sandal, Shirt, Sneaker, Bag, Ankle Boot.
• writer = SummaryWriter('run/fashion_mnist_experiment_1')    # 网站显示

---

一 tensorboard的使用

• 在网站显示pytorch的架构:

1.1 导包

import matplotlib.pyplot as plt 
import numpy as np
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

1.2 数据导入

# transforms
transform = transforms.Compose([transforms.ToTensor(),
                                transforms.Normalize((0.5, ), (0.5))])  # 正则化

# datasets
trainset = torchvision.datasets.FashionMNIST('./data',
                                             download=True,
                                             train=True,
                                             transform = transform)

testset = torchvision.datasets.FashionMNIST('./data',
                                             download=True,
                                             train=False,
                                             transform = transform)

• dataloader 设置

# dataloaders
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=True, num_workers=2)

# constant for classes
classes = ('T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
           'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle Boot')

1.3 定义模型

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 4 * 4, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)
        
    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 4 * 4)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x
    
net = Net()

# 定义损失和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr = 0.001, momentum=0.9)

1.4 tensorboard的使用

• tensorboard的安装: pip install tensorboard -i https://pypi.douban.com/simple

def matplotlib_imshow(img, one_channel=False):
    if one_channel:
        img = img.mean(dim=0)
    img = img / 2 + 0.5
    npimg = img.numpy()
    if one_channel:
        plt.imshow(npimg, cmap= 'Greys')
    else:
        plt.imshow(np.transpose(npimg, (1, 2, 0)))

dataiter = iter(trainloader)
images, labels = next(dataiter)
images.shape   # torch.Size([4, 1, 28, 28])

# torchvision 中make_grid 可以把多张图合并成一张图
img_grid = torchvision.utils.make_grid(images)
img_grid.shape   # torch.Size([3, 32, 122])
matplotlib_imshow(img_grid, one_channel=True)

• from torch.utils.tensorboard import SummaryWriter

writer = SummaryWriter('run/fashion_mnist_experiment_1')
writer.add_image('four_fashion_mnist_images', img_grid)

images, labels = next(dataiter)
img_grid2 = torchvision.utils.make_grid(images)
matplotlib_imshow(img_grid2, one_channel=True)

writer.add_image('img_grid2', img_grid2)

1.5 添加模型的结构图

writer.add_graph(net, images)  # 模型可视化

1.6 添加损失变化

# writer.add_scaler()
running_loss = 0.0
for epoch in range(1):  # loop over the dataset multiple times
    for i, data in enumerate(trainloader, 0):
        # get the inputs: data is list of [inputs, labels]
        inputs, labels = data
        
        # zero the parameter gradients
        optimizer.zero_grad()
        
        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
        if i % 1000 == 999:  # every 1000 mini-batches...
            
            # log the running loss
            writer.add_scalar('training loss',
                              running_loss / 1000,
                              epoch * len(trainloader) + i)
            
            running_loss = 0.0
print('Finished Training')