visdom——數據可視化

安裝visdom
win+R打開運行，鍵入：

pip install visdom

打開使用，鍵入：

python -m visdom.server

然後我電腦直接報錯就打不開visdom，然後我嘗試鍵入：

visdom

成功打開

把生成的網頁 http://localhost:8097複製到瀏覽器上打開，會出現一個藍色的屏。

from visdom import Visdom
#生成一個viz的環境
viz = Visdom()

#初始化兩個小的窗格，來分別繪製train,test的情況
# 繪製初始點，原點
viz.line([0.], [0.], win='train_loss',opts=dict(title='train loss'))  #single-line
viz.line([loss.item()], [global_step], win='trian_loss', update='append')
viz.line([[0., 0.]], [0.], win='test',opts=dict(title='train loss',  legend=['loss', 'acc.']))
viz.line([[test_loss, correct / len(test_loader.dataset)]], [global_step], win='test', update='append')
#這裏前兩個參數，一個表示指定變化指標數量，一個或者兩個提前佔位，並初始化爲0，
#第二個參數表示進行到第幾步全局minibatch批次號總共進行了幾個minibatch

viz.images(data.view(-1,1,28,28), win='x')
viz.text(str(pred.detach().cpu().numpy()), win='pred', opts=dict(title='pred'))  

運行代碼：

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

batch_size = 200
learning_rate = 0.01
epochs = 10

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)


class MLP(nn.Module):

	def __init__(self):
		super(MLP, self).__init__()

		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),
		)

	def forward(self, x):
		x = self.model(x)
		return x


device = torch.device('cuda:0')
net = MLP().to(device)
optimizer = optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss().to(device)

viz = Visdom()
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 = 0

for 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()
		optimizer.step()

		global_step += 1
		viz.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 = 0
	correct = 0
	for 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')
	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)))