以PyTorch進行自動編碼器的實作

1. MNIST手寫數據載入

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision

EPOCH = 10 #訓練數據10次
BATCH_SIZE = 64
LR = 0.001  #學習率
DOWNLOAD_MNIST = True 
N_TEST_IMG = 10

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

2. AutoEncoder模型

lass 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 encoded, decoded

autoencoder = AutoEncoder()

3. 訓練

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

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())

4. 畫出3D可視圖

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()

參考資料:

• https://zhuanlan.zhihu.com/p/67742390
• https://blog.csdn.net/NBDwo/article/details/119743450
• https://blog.csdn.net/weixin_33895396/article/details/112197185
• https://mofanpy.com/tutorials/machine-learning/torch/autoencoder