實戰手寫數字識別—使用visdom首先loss函數值可視化

首先使用 python -m visdom.server激活visdom環境，再運行以下代碼。

import torch
import torch.nn as nn
import torchvision.datasets as normal_datasets
import torchvision.transforms as transforms
from torch.autograd import Variable
import visdom
import numpy as np
import matplotlib.pyplot as plt

num_epochs = 5
batch_size = 100
learning_rate = 0.001


# 將數據處理成Variable, 如果有GPU, 可以轉成cuda形式
def get_variable(x):
    x = Variable(x)
    return x.cuda() if torch.cuda.is_available() else x


# 從torchvision.datasets中加載一些常用數據集
train_dataset = normal_datasets.MNIST(
    root='./data',  # 數據集保存路徑
    train=True,  # 是否作爲訓練集
    transform=transforms.ToTensor(),  # 數據如何處理, 可以自己自定義
    download=True)  # 路徑下沒有的話, 可以下載

# 見數據加載器和batch
test_dataset = normal_datasets.MNIST(root='./data',
                                     train=False,
                                     transform=transforms.ToTensor(),
                                     download=True)

train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
                                           batch_size=batch_size,
                                           shuffle=True)

test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
                                          batch_size=batch_size,
                                          shuffle=False)

viz = visdom.Visdom(env='train-mnist')
loss_win = viz.line(np.arange(10))
# 兩層卷積
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        # 使用序列工具快速構建
        self.conv1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.conv2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(2))
        self.fc = nn.Linear(7 * 7 * 32, 10)

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


cnn = CNN()
if torch.cuda.is_available():
    cnn = cnn.cuda()

# 選擇損失函數和優化方法
loss_func = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate)

loss_point = []  ####
x_point = []   ####
iter_count = 0  ####

for epoch in range(num_epochs):

    running_loss = 0.0  ####
    for i, (images, labels) in enumerate(train_loader):


        images = get_variable(images)
        labels = get_variable(labels)

        outputs = cnn(images)
        loss = loss_func(outputs, labels)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        running_loss += loss.item()  ####

        if (i + 1) % 100 == 0:
            print('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
                  % (epoch + 1, num_epochs, i + 1, len(train_dataset) // batch_size, loss.item()))

            tr_loss = running_loss / 100
            iter_count += 100
            if iter_count == 100:
                viz.line(Y=np.array([tr_loss]), X=np.array([iter_count]), update='replace', win=loss_win)
            else:
                viz.line(Y=np.array([tr_loss]), X=np.array([iter_count]), update='append', win=loss_win)
        running_loss = 0 ####


# Save the Trained Model
torch.save(cnn.state_dict(), 'cnn.pkl')