Pytorch的学习——自编码

自编码

自编码是一种神经网络形式即非监督学习，可以理解为通过将输入数据进行压缩训练，然后再通过另一个结构相同的神经网络解压，然后将解压后的结果与原数据进行比较计算误差再进行误差反向传递。

例子

这里小编还是以手写数字来作为列子

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


# 参数设置
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005        
DOWNLOAD_MNIST = False
N_TEST_IMG = 5

# 准备数据
train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                    
    transform=torchvision.transforms.ToTensor(),    
    download=DOWNLOAD_MNIST,                        
)

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),   # compress to 3 features which can be visualized in plt
        )
        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(),       # compress to a range (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()   # continuously plot

# 用于查看的原始数据(第一行)
view_data = train_data.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)   
        b_y = x.view(-1, 28*28)   

        encoded, decoded = autoencoder(b_x)

        loss = loss_func(decoded, b_y)    
        optimizer.zero_grad()           
        loss.backward()             
        optimizer.step()              

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

            # 画图
            _, 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绘图中可视化
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.targets[: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()

分类结果

手写数字的分类在3D空间的分布如下图，相似的数字会有重叠的部分