神经网络也能进行非监督学习, 只需要训练数据, 不需要标签数据. 自编码就是这样一种形式. 自编码能自动分类数据, 而且也能嵌套在半监督学习的上面, 用少量的有标签样本和大量的无标签样本学习.
更多可以查看官网 :
* PyTorch 官网
有关Autocoder可对比TensorFlow 的Autocoder.
还用 MNIST 手写数字数据来压缩再解压图片.
How old are U ?
训练数据
自编码只用训练集就行, 而且只需要训练 training data 的 image, 不用训练 labels.
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
# 超参数
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005
DOWNLOAD_MNIST = True #
N_TEST_IMG = 5 #
# Mnist digits dataset
train_data = torchvision.datasets.MNIST(
root='./mnist/',
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
)
AutoEncoder
AutoEncoder 形式很简单, 分别是 encoder 和 decoder, 压缩和解压, 压缩后得到压缩的特征值, 再从压缩的特征值解压成原图片.
class AutoEncoder(nn.Module):
def __init__(self):
super(AutoEncoder, self).__init__()
# 压缩
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), # 压缩成3个特征, 进行 3D 图像可视化
)
# 解压
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(), # 激励函数让输出值在 (0, 1)
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
autoencoder = AutoEncoder()
训练
训练, 并可视化训练的过程. 我们可以有效的利用 encoder 和 decoder 来做很多事,
比如这里用 decoder 的信息输出看和原图片的对比, 还能用 encoder 来看经过压缩后, 神经网络对原图片的理解.
encoder 能将不同图片数据大概的分离开来. 这样就是一个无监督学习的过程.
image
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
for epoch in range(EPOCH):
for step, (x, y) in enumerate(train_loader):
b_x = Variable(x.view(-1, 28*28)) # batch x, shape (batch, 28*28)
b_y = Variable(x.view(-1, 28*28)) # batch y, shape (batch, 28*28)
b_label = Variable(y) # batch label
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
