mnist手寫數字分類初體驗(pytorch)

mnist_train.py

import torch
from torch import nn
from torch.nn import functional as F
from torch import optim

import torchvision
from matplotlib import pyplot as plt

from utils import plot_image, plot_curve, one_hot

batch_size = 512

# step1. load dataset
train_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('mnist_data', train=True, download=True,
                               transform=torchvision.transforms.Compose([
                                   torchvision.transforms.ToTensor(),
                                   torchvision.transforms.Normalize(
                                       (0.1307,), (0.3081,))
                               ])),
    batch_size=batch_size, shuffle=True)

test_loader = torch.utils.data.DataLoader(
    torchvision.datasets.MNIST('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)

x, y = next(iter(train_loader))
print(x.shape, y.shape, x.min(), x.max())
plot_image(x, y, 'image sample')  # 輸出圖片

# 創建網絡


class Net(nn.Module):

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

        # xw+b  三層
        self.fc1 = nn.Linear(28 * 28, 256) # output 256
        self.fc2 = nn.Linear(256, 64) # input 256
        self.fc3 = nn.Linear(64, 10)

    def forward(self, x):
        # x: [b, 1, 28, 28]
        # h1 = relu(xw1+b1)
        x = F.relu(self.fc1(x))
        # h2 = relu(h1w2+b2)
        x = F.relu(self.fc2(x))
        # h3 = h2w3+b3
        x = self.fc3(x)

        return x


net = Net()
# [w1, b1, w2, b2, w3, b3]
optimizer = optim.SGD(net.parameters(), lr=0.01, momentum=0.9)

train_loss = []  # 記錄損失值

for epoch in range(3):

    for batch_idx, (x, y) in enumerate(train_loader):

        # x: [b, 1, 28, 28], y: [512]
        # [b, 1, 28, 28] => [b, 784]  四維張量變爲二維張量
        x = x.view(x.size(0), 28 * 28)
        # => [b, 10]
        out = net(x)
        # [b, 10]
        y_onehot = one_hot(y)
        # loss = mse(out, y_onehot)
        loss = F.mse_loss(out, y_onehot)

        optimizer.zero_grad()  # 清零梯度
        loss.backward()  # 計算梯度
        # w' = w - lr*grad 更新
        optimizer.step()

        train_loss.append(loss.item())

        # 每隔10epoch 打印出
        if batch_idx % 10 == 0:
            print(epoch, batch_idx, loss.item())

plot_curve(train_loss)
# we get optimal [w1, b1, w2, b2, w3, b3]


total_correct = 0
for x, y in test_loader:
    x = x.view(x.size(0), 28 * 28)
    out = net(x)
    # out: [b, 10] => pred: [b]
    pred = out.argmax(dim=1)  # 返回值最大的索引
    correct = pred.eq(y).sum().float().item()  # 這個batch中正確的數量
    total_correct += correct

total_num = len(test_loader.dataset)
acc = total_correct / total_num
print('test acc:', acc)


# sample
x, y = next(iter(test_loader))
out = net(x.view(x.size(0), 28 * 28))
pred = out.argmax(dim=1)
plot_image(x, pred, 'test')

utils.py

import torch
from matplotlib import pyplot as plt


def plot_curve(data):
    fig = plt.figure()
    plt.plot(range(len(data)), data, color='blue')
    plt.legend(['value'], loc='upper right')
    plt.xlabel('step')
    plt.ylabel('value')
    plt.show()


def plot_image(img, label, name):

    fig = plt.figure()
    for i in range(6):
        plt.subplot(2, 3, i + 1)
        plt.tight_layout()
        plt.imshow(img[i][0]*0.3081+0.1307, cmap='gray', interpolation='none')
        plt.title("{}: {}".format(name, label[i].item()))
        plt.xticks([])
        plt.yticks([])
    plt.show()


def one_hot(label, depth=10):
    out = torch.zeros(label.size(0), depth)
    idx = torch.LongTensor(label).view(-1, 1)
    out.scatter_(dim=1, index=idx, value=1)
    return out