pytorch7-可视化训练过程（过程中显示）

import torch
import torch.nn as nn
import torchvision
import torchvision.utils as vutils
from torch.optim import SGD
import torch.utils.data as Data
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
import hiddenlayer as hl
from torchviz import make_dot
from tensorboardX import SummaryWriter


import tensorboard
print(tensorboard.__file__)
#使用手写字体数据，准备训练数据集
train_data = torchvision.datasets.MNIST(
    root="./data/",  # 指定数据集路径
    train=True, # 只使用训练数据集
    transform=torchvision.transforms.ToTensor(),  # 将数据转化为张量
    download=False  # 已经下载过，不用再次下载
)

# 定义个数据加载器
train_loader = Data.DataLoader(
    dataset=train_data,
    batch_size=128,  # 设定每个批量的数据量
    shuffle=True,   # 每次迭代前打乱数据
    num_workers=2,  # 使用两个进程
)

# 准备需要的测试数据集
test_data = torchvision.datasets.MNIST(
    root="./data/",  # 数据路径
    train=False,  # 不需要训练数据集
    download=False
)

# 为数据添加一个通道维度，将取值范围缩到0-1
test_data_x = test_data.data.type(torch.FloatTensor) / 255.0
test_data_x = torch.unsqueeze(test_data_x, dim=1)
test_data_y = test_data.targets  # 获取测试集的标签
print("test_data_x.shape", test_data_x.shape)
print("test_data_y.shape", test_data_y.shape)


class ConvNet(nn.Module):
    def __init__(self):
        super(ConvNet, self).__init__()
        # 定义第一个卷积层
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,  #输入的feature map
                out_channels=16, # 输出的feature map
                kernel_size=3,
                stride=1,
                padding=1,
            ),
            nn.ReLU(),
            nn.AvgPool2d(
                kernel_size=2,
                stride=2,
            )
        )

        # 定义第二个卷积层
        self.conv2 = nn.Sequential(
            nn.Conv2d(16, 32, 3, 1, 1),
            nn.ReLU(),
            nn.MaxPool2d(2, 2)
        )

        # 定义全连接层
        self.fc = nn.Sequential(
            nn.Linear(
                in_features=32 * 7 * 7,
                out_features=128,
            ),
            nn.ReLU(),
            nn.Linear(128, 64),
            nn.ReLU()
        )
        self.out = nn.Linear(64, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        output = self.out(x)
        return output

if __name__ == "__main__":
    MyConvnet = ConvNet()
    print(MyConvnet)

    # 定义优化器
    optimizer = torch.optim.Adam(MyConvnet.parameters(), lr=0.0003)
    lossfunc = nn.CrossEntropyLoss()
    history1 = hl.History()
    canvas1 = hl.Canvas()


    print_step = 100  # 每经100次迭代后输出损失

    # 对模型进行迭代训练，对所有的数据训练epoch轮
    for epoch in range(5):
        # 对训练数据的加载器进行迭代训练
        for step, (b_x, b_y) in enumerate(train_loader):
            # 计算每个batch的损失
            output = MyConvnet(b_x)
            loss  = lossfunc(output, b_y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

            # 计算每经print_step次迭代后的数据输出
            if step%print_step == 0:
                # 计算在测试机上的精度
                output = MyConvnet(test_data_x)
                _,pre_lab = torch.max(output, 1)
                acc = accuracy_score(test_data_y, pre_lab)
                history1.log(
                    (epoch, step),
                    train_loss = loss,
                    test_acc = acc,
                    hidden_weight = MyConvnet.fc[2].weight
                )

                with canvas1:
                    canvas1.draw_plot(history1["train_loss"])
                    canvas1.draw_plot(history1["test_acc"])
                    canvas1.draw_image(history1["hidden_weight"])