AutoEncoder (自编码/非监督学习)

"""
View more, visit my tutorial page: https://mofanpy.com/tutorials/
My Youtube Channel: https://www.youtube.com/user/MorvanZhou
Dependencies:
torch: 0.4
matplotlib
numpy
"""

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
 
 
# torch.manual_seed(1)    # 可重复
 
# 超参数
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005         # 学习率
DOWNLOAD_MNIST = True
N_TEST_IMG = 5
 
# Mnist数字数据集
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # 训练数据
    transform=torchvision.transforms.ToTensor(),    # 将PIL.Image或numpy.ndarray转换为
                                                    # torch.FloatTensor，其形状为（C x H x W），范围为[0.0, 1.0]的标准化
    download=DOWNLOAD_MNIST,                        # 如果没有，就下载它
)
 
# 绘制一个样例
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()
 
# 数据加载器，方便训练时返回小批量，图像批量形状将是（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),   # 压缩为3个特征，可在plt中可视化
        )
        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(),       # 压缩到范围（0,1）
        )
 
    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()
 
# 初始化图形
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()   # 连续绘图
 
# 原始数据（第一行）进行查看
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，形状（batch，28*28）
        b_y = x.view(-1, 28*28)   # batch y，形状（batch，28*28）
 
        encoded, decoded = autoencoder(b_x)
 
        loss = loss_func(decoded, b_y)      # 均方误差
        optimizer.zero_grad()               # 清空此训练步骤的梯度
        loss.backward()                     # 反向传播，计算梯度
        optimizer.step()                    # 应用梯度
 
        if step % 100 == 0:
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy())
 
            # 绘制解码图像（第二行）
            _, 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()
 
# 以3D图形可视化
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()