莫烦 pytorch 自编码 AutoEncoder

我的视频学习记录

视频原址：https://www.bilibili.com/video/av15997678?p=25
源代码：https://github.com/MorvanZhou/PyTorch-Tutorial/blob/master/tutorial-contents/404_autoencoder.py

import torch
import torchvision
import torch.utils.data as Data
import matplotlib.pyplot as plt
import torch.nn as nn
import numpy as np
from mpl_toolkits.mplot3d import Axes3D
from matplotlib import cm

torch.manual_seed(1)  # reproducible

# hyper parameters
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005
DOWNLOAD_MNIST = False
N_TEST_IMG = 5

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

train_loader = Data.DataLoader(
    dataset=train_data,
    batch_size=BATCH_SIZE,
    shuffle=True,
    num_workers=0
)

# print(train_data.data.size())
# print(train_data.targets.size())
# plt.imshow(train_data.data[0].numpy(), cmap='gray')
# plt.title('%i' % train_data.targets[0])
# plt.show()

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(),  # 将输出值范围压缩到0~1
        )

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


autoencoder = AutoEncoder()
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)  # optimize all cnn parameters
loss_func = nn.MSELoss()

f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()

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 = x.view(-1, 28 * 28)  # batch x, shape(batch, 28 * 28)
        b_y = x.view(-1, 28 * 28)  # batch y, shape(batch, 28 * 28)

        encoder, decoder = autoencoder(b_x)

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

        if step % 100 == 0:
            print('Epoch: ', epoch, '|train_loss:%.4f' % loss.item())

            _, 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_data.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()