HW5 Autoencoder

# 这是一个示例 Python 脚本。
# 按 Shift+F10 执行或将其替换为您的代码。
# 按 双击 Shift 在所有地方搜索类、文件、工具窗口、操作

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import numpy as np
import os
os.environ['KMP_DUPLICATE_LIB_OK']='TRUE'
# torch.manual_seed(1)    # reproducible

# 超参数
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005  # learning rate
DOWNLOAD_MNIST = False
N_TEST_IMG = 5

# 导入数据集
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,  # 这是训练集
    transform=torchvision.transforms.ToTensor(),  # 转换一个 PIL.Image or numpy.ndarray to
    # torch.FloatTensor 的形状 (C x H x W) 和 常规范围 [0.0, 1.0]
    download=DOWNLOAD_MNIST,  # 下载它如果还没有下载
)

# 展示样例
print(train_data.train_data.size())  # (60000, 28, 28)
print(train_data.train_labels.size())  # (60000)
plt.imshow(train_data.train_data[2].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[2])
plt.show()

# 数据簇加载为图片(50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)


class AutoEncoder(nn.Module):
    def __init__(self):
        super(AutoEncoder, self).__init__()

        self.encoder = nn.Sequential(
            nn.Linear(28 * 28, 128),
            nn.Tanh(),
            nn.Linear(128, 64),
            nn.Tanh(),
            nn.Linear(64, 12),
            nn.Tanh(),
            nn.Linear(12, 3),  # 精简到三个特征
        )
        self.decoder = nn.Sequential(
            nn.Linear(3, 12),
            nn.Tanh(),
            nn.Linear(12, 64),
            nn.Tanh(),
            nn.Linear(64, 128),
            nn.Tanh(),
            nn.Linear(128, 28 * 28),
            nn.Sigmoid(),  # 减小到在（0，1）之间的概率
        )

    def forward(self, x):
        encoded = self.encoder(x)
        decoded = self.decoder(encoded)
        return encoded, decoded


autoencoder = AutoEncoder()

optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()

# 初始化图片
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()  # continuously plot

# 为了查看组织数据
view_data = train_data.train_data[:N_TEST_IMG].view(-1, 28 * 28).type(torch.FloatTensor) / 255.
for i in range(N_TEST_IMG):
    a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray');
    a[0][i].set_xticks(());
    a[0][i].set_yticks(())

for epoch in range(EPOCH):
    for step, (x, b_label) in enumerate(train_loader):
        b_x = x.view(-1, 28 * 28)  # batch x, shape (batch, 28*28)
        b_y = x.view(-1, 28 * 28)  # batch y, shape (batch, 28*28)

        encoded, decoded = autoencoder(b_x)

        loss = loss_func(decoded, b_y)  # mean square error
        optimizer.zero_grad()  # clear gradients for this training step
        loss.backward()  # backpropagation, compute gradients
        optimizer.step()  # apply gradients

        if step % 100 == 0:
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy())

            # plotting decoded image (second row)
            _, decoded_data = autoencoder(view_data)
            for i in range(N_TEST_IMG):
                a[1][i].clear()
                a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray')
                a[1][i].set_xticks(());
                a[1][i].set_yticks(())
            plt.draw();
            plt.pause(0.05)

plt.ioff()
plt.show()

# 在3D视图中可视化
view_data = train_data.train_data[:200].view(-1, 28 * 28).type(torch.FloatTensor) / 255.
encoded_data, _ = autoencoder(view_data)
fig = plt.figure(2);
ax = Axes3D(fig)
X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
values = train_data.train_labels[:200].numpy()
for x, y, z, s in zip(X, Y, Z, values):
    c = cm.rainbow(int(255 * s / 9));
    ax.text(x, y, z, s, backgroundcolor=c)
ax.set_xlim(X.min(), X.max());
ax.set_ylim(Y.min(), Y.max());
ax.set_zlim(Z.min(), Z.max())
plt.show()

展示样例

训练结果