机器学习14

 visdom 可视化

import numpy as np
import torch
import torch.nn.functional as f

logits = torch.rand(4, 10)

print(logits)

pred = f.softmax(logits, dim=1)
print(pred)

print(pred.sum())

print(pred.shape)
pred_label = pred.argmax(dim=1)
print('pred_label: ', pred_label)
# 输出每行最大值索引
print(logits.argmax(dim=1))
# 输出每行最大值索引
label = torch.tensor([9, 5, 9, 4])
# 标签
correct = torch.eq(pred_label, label)
# eq 如果pred_label  与label中有相同的数值输出True
print(correct)

le = len(correct)
print(le)
print('输出True个数', correct.sum().float().item())
a = correct.sum().float().item() / le
print(a)

# Visdom

print('------------# Visdom------------')
'''以下不建议使用'''
# from tensorboardX import SummaryWriter
#
# writer = SummaryWriter()
# # SummaryWriter实例
# # dummy_s1[0] 监听的数据
# writer.add_scalar('./data/scalar1', dummy_s1[0], n_iter)
# writer.add_scalar('./data/scalar_group', {'xsinx': n_iter * np.sin(n_iter)
#                                           'xcosx': n_iter * np.cos(n_iter)
#                                           'arctanx': np.arctan(n_iter)
#                                           },n_iter)
#
# writer.add_image('Image', x, n_iter)
# writer.add_text('Text', 'text logged at step:' + str(n_iter), n_iter)
#
# from name, param in resnet18.named_parameters():
#     writer.add_histogram(name, param.clone().cpu().data.numpy(), n_iter)
#
# writer.close()

'''
1、安装

# pip install visdom

如果进行第二步失败
pip uninstall visdom
进行以下安装
git clone https://github.com/fossasia/visdom.git

切换到下载目录

# Install visdom from source
pip install -e .
# If the above runs into issues, you can try the below
easy_install .

安装目录下\Lib\site-packages\visdon

server.py 1917行
注释掉
# download_scripts()
2、 
开启监听进程
python -m visdom.server

3、复制IP 浏览器打开
http://localhost:8097/
'''

# from visdom import Visdom
#
# viz = Visdom()
# # 创建直线 y x '[0.], [0.]' win 窗口
# viz.line([0.], [0.], win='train_loss', opts=dict(title='train loss'))
#
# viz.line([loss.item()], [global_step], win='train_loss', update='append')
import torch
import torch.nn as nn
from torchvision import datasets,transforms
import torch.optim as optim
from torch.nn import functional as F
from visdom import Visdom
import torchvision

batch_size = 64
learning_rate  = 1e-2
epochs = 10

train_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('./data',
                train=True,
                download=True,
                transform=torchvision.transforms.Compose([
                torchvision.transforms.ToTensor(),                       # 数据类型转化
                torchvision.transforms.Normalize((0.1307, ), (0.3081, )) # 数据归一化处理
    ])), batch_size=batch_size,shuffle=True)

test_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('./data',
                train=False,
                download=True,
                transform=torchvision.transforms.Compose([
                torchvision.transforms.ToTensor(),
                torchvision.transforms.Normalize((0.1307, ), (0.3081, ))
    ])),batch_size=batch_size,shuffle=False)

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()
        # print(w1.grad.norm(), w2.grad.norm())
        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)))