AutoEncoder（自编码：以Mnist数据集为例）

本例以pytorch框架进行实验：

#coding = utf-8
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import torch.optim as optim
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm
import numpy as np
from torch.autograd import Variable

# torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 5
BATCH_SIZE = 64
LR = 0.001         # learning rate
DOWNLOAD_MNIST = True
N_TEST_IMG = 5

# Mnist digits dataset
train_data = torchvision.datasets.MNIST(
    root='./mnist_data/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,                        # download it if you don't have it
)

# plot one example
# 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()

# Data Loader for easy mini-batch return in training, the image batch shape will be (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),

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

en = AutoEncoder()
print(en)

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

# initialize figure
plt.figure()
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()   # continuously plot

# original data (first row) for viewing
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,y) in enumerate(train_loader):
        b_x = Variable(x.view(-1,28*28))
        b_y = Variable(x.view(-1,28*28))
        b_label = Variable(y)

        decoded = en(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.item())

            # plotting decoded image (second row)
            decoded_data = en(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()

# visualize in 3D plot
view_data = train_data.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.
encoded_data= en(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()