一、visdom可视化配置
1、安装visdom库
pip install visdom2、配置环境
python -m visdom server
3、浏览器打开网址：
visdom
http://localhost:8097/
二、显示的结果
三、代码
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from visdom import Visdom# 尽可能地设大batch_size，不断尝试。
batch_size=200
learning_rate=0.01
epochs=10# cross-entropy 等同于 softmax + log + nll_loss三个和
# 加载的代码操作
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=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(datasets.MNIST('../data', train=False, transform=transforms.Compose([transforms.ToTensor(),# transforms.Normalize((0.1307,), (0.3081,))])),batch_size=batch_size, shuffle=True)# nn.Module是Pytorch封装的一个类，是搭建神经网络时需要继承的父类：
class MLP(nn.Module):# 括号中加入nn.Module（父类）。MLP变成子类，继承父类（nn.Module）的所有特性。def __init__(self):# MLP类定义初始化方法super(MLP, self).__init__() # 父类初始化# simply,三层神经网络结构。# 可以添加各种网络层self.model = nn.Sequential(nn.Linear(784, 200),nn.LeakyReLU(inplace=True),nn.Linear(200, 200),nn.LeakyReLU(inplace=True),nn.Linear(200, 10),nn.LeakyReLU(inplace=True),)# 定义向前传播def forward(self, x):x = self.model(x)return xdevice = torch.device('cuda:0') # 编号0-9
net = MLP().to(device) # .to 运到GPU上去
optimizer = optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss().to(device) # .to 运到GPU上去viz = Visdom()
# imgae/tensor直接的数据,x坐标
viz.line([0.], [0.], win='train_loss', opts=dict(title='train loss'))
viz.line([[0.0, 0.0]], [0.], win='test', opts=dict(title='test loss&acc.',legend=['loss', 'acc.']))
global_step = 0for epoch in range(epochs):for batch_idx, (data, target) in enumerate(train_loader):data = data.view(-1, 28*28)data, target = data.to(device), target.cuda()logits = net(data)loss = criteon(logits, target)optimizer.zero_grad()loss.backward()# print(w1.grad.norm(), w2.grad.norm())optimizer.step()global_step += 1viz.line([loss.item()], [global_step], win='train_loss', update='append')if batch_idx % 100 == 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()))test_loss = 0correct = 0for data, target in test_loader:data = data.view(-1, 28 * 28)data, target = data.to(device), target.cuda()logits = net(data)test_loss += criteon(logits, target).item()pred = logits.argmax(dim=1)correct += pred.eq(target).float().sum().item()viz.line([[test_loss, correct / len(test_loader.dataset)]],[global_step], win='test', update='append')# 图片中的数字，打印出来viz.images(data.view(-1, 1, 28, 28), win='x')viz.text(str(pred.detach().cpu().numpy()), win='pred',opts=dict(title='pred'))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)))
