多层自编码器手写版

#导入实验需要的包
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)    # reproducible

#超参数
# Hyper Parameters
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005         # learning rate
DOWNLOAD_MNIST = True
N_test_IMG = 5

#下载数据集
# Mnist digits dataset
Train_dataset = torchvision.datasets.MNIST(
    root='./mnist/',
    Train=True,                                     # this is Training data
    transform=torchvision.transforms.ToTensor(),
    download=DOWNLOAD_MNIST,                        # download it if you don't have it
)

# plot one example
print(Train_dataset.Train_data.size())     # (60000, 28, 28)
print(Train_dataset.Train_labels.size())   # (60000)
plt.imshow(Train_dataset.Train_data[2].numpy(), cmap='gray')
plt.title('%i' % Train_dataset.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_dataset, batch_size=BATCH_SIZE, shuffle=TruE)

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

# initialize 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_dataset.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).cuda()   # batch x, shape (batch, 28*28)
        b_y = x.view(-1, 28*28).cuda()   # 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()

# visualize in 3D plot
view_data = Train_dataset.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_dataset.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()