自编码网络是非监督学习领域的一种,可以自动从无标注的数据中学习特征,是一种以重构输入信息为目标的神经网络,它可以给出比原始数据更好的特征描述,具有较强的特征学习能力,在深度学习中常用自编码网络生成的特征来取代原始数据,已取得更好效果。
换句话说,自编码网络的作用相当于PCA并且能获得比PCA更好的效果
这里我们把手写数据集里面的图片特征先压缩,根据压缩出来的特征,对数据进行分类,即无监督学习(无监督学习:不需要标签,只需要用到train_x,不需要用到train_y)
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
#超参数
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005 # learning rate
DOWNLOAD_MNIST = False
N_TEST_IMG = 5
# Mnist digits dataset
train_data = torchvision.datasets.MNIST(
root=r'D:\python\minist',
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, # 如果已经有了就填False,没有就填Ture
)
# 查看一个数据
print(train_data.train_data.size()) # (60000, 28, 28)
print(train_data.train_labels.size()) # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[2])
plt.show()
#将数据小批量训练,图像数据变成 (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
#构造神经网络
class AutoEncoder(nn.Module):
def __init__(self):
super(AutoEncoder, self).__init__()
self.encoder = nn.Sequential(
nn.Linear(28*28, 128),
nn.Tanh(), #激活函数
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
)
#定义解压器
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(), # 把输出值控制到0-1的范围
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
#自编码网络实例化
autoencoder = AutoEncoder()
#定义优化器和损失函数
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
首先画一个2*5的图
#显示原始图片
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()
#显示第一行数据
view_data = train_data.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(())
#训练过程
for epoch in range(EPOCH):
for step, (x, b_label) in enumerate(train_loader):
b_x = x.view(-1, 28*28) # batch x, 把x reshape成(batch, 28*28)
b_y = x.view(-1, 28*28) # batch y, 在数据上和b_x一样
encoded, decoded = autoencoder(b_x)
loss = loss_func(decoded, b_y) # 对比原图片和解压出来的图片的误差
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 100 == 0: #每一百步画一次图,并且画出解压的图片
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy())
# 在第二行画解压出来的图片
_, 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.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()
#这里的X,Y,Z表示编码之后的前三个属性
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()
完整:
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
#超参数
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005 # learning rate
DOWNLOAD_MNIST = False
N_TEST_IMG = 5 #测试数据是五个
# Mnist digits dataset
train_data = torchvision.datasets.MNIST(
root=r'D:\python\minist',
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, # 如果已经有了就填False,没有就填Ture
)
## 查看一个数据
#print(train_data.train_data.size()) # (60000, 28, 28)
#print(train_data.train_labels.size()) # (60000)
#plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
#plt.title('%i' % train_data.train_labels[2])
#plt.show()
#将数据小批量训练,图像数据变成 (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
#构造神经网络
class AutoEncoder(nn.Module):
def __init__(self):
super(AutoEncoder, self).__init__()
self.encoder = nn.Sequential(
nn.Linear(28*28, 128),
nn.Tanh(), #激活函数
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
)
#定义解压器
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(), # 把输出值控制到0-1的范围
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
#自编码网络实例化
autoencoder = AutoEncoder()
#定义优化器和损失函数
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
#显示原始图片
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion()
#显示第一行数据
view_data = train_data.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255 #训练集的前五个数字
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(())
#训练过程
for epoch in range(EPOCH):
for step, (x, b_label) in enumerate(train_loader):
b_x = x.view(-1, 28*28) # batch x, 把x reshape成(batch, 28*28)
b_y = x.view(-1, 28*28) # batch y, 在数据上和b_x一样
encoded, decoded = autoencoder(b_x)
loss = loss_func(decoded, b_y) # 对比原图片和解压出来的图片的误差
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 100 == 0: #每一百步画一次图,并且画出解压的图片
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy())
# 在第二行画解压出来的图片
_, 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.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()
#这里的X,Y,Z表示编码之后的前三个属性
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()