pytorch自动编码器实现有损图像压缩

自动编码器(AutoEncoder)由编码器(Encoder)和解码器(Decoder)两部分组成。编码器和解码器可以是任意模型,通常神经网络模型作为编码器和解码器。

自动编码器作为一种数据压缩的方法,其原理是:输入数据经过编码器变成一个编码(code),然后将这个编码作为解码器的输入,观察解码器的输出是否能还原原始数据,因此将解码器的输出和原始数据的误差作为最优化的目标。

下面以MNIST数据集为例,使用pytorch1.0构建一个卷积神经网络做自动编码器。


1.添加引用的库文件

import os
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torchvision.utils import save_image

2.定义超参数,是否使用GPU加速

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
batch_size = 512

3.加载MNIST数据集,并将图片的大小变为-1~1之间,这样可以使输入变得更对称,训练更加容易收敛。

# 标准化
data_tf = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize([0.5], [0.5])]
)


train_dataset = datasets.MNIST(root='./data', train=True, transform=data_tf, download=True)
train_data = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)

4.定义卷积神经网络的自动编码器

class AutoEncoder(nn.Module):
    def __init__(self):
        super(AutoEncoder, self).__init__()
        self.encoder = nn.Sequential(
            nn.Conv2d(1, 16, 3, stride=3, padding=1),  # b,16,10,10
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=2),  # b,16,5,5
            nn.Conv2d(16, 8, 3, stride=2, padding=1),  # b,8,3,3
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=1)  # b,8,2,2
        )
        self.decoder = nn.Sequential(
            nn.ConvTranspose2d(8, 16, 3, stride=2),   # b,16,5,5
            nn.ReLU(True),
            nn.ConvTranspose2d(16, 8, 5, stride=3, padding=1),  # b,8,15,15
            nn.ReLU(True),
            nn.ConvTranspose2d(8, 1, 2, stride=2, padding=1),   # b,1,28,28
            nn.Tanh()
        )

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

torch.nn.Conv2d(in_channels, out_channels, kernel_size, stride=1, padding=0,groups=1, bias=True, dilation=1)

  • in_channels(int):输入数据的通道数;
  • out_channels(int):输出数据的通道数;
  • kernel_size(int or tuple):滤波器或卷积核的大小;
  • stride(int or tuple,optional) :步长;
  • padding(int or tuple, optional):四周是否进行0填充;
  • groups(int, optional) – 从输入通道到输出通道的阻塞连接数
  • bias(bool, optional) - 如果bias=True,添加偏置
  • dilation(int or tuple, optional) – 卷积核元素之间的间距

对于每一条边输入,输出的尺寸的公式如下:

output=(input-kernel\_size+2*padding)/stride+1

 

解码器使用nn.ConvTranspose2d(),可以看作卷积的反操作。具体参数如下:

torch.nn.ConvTranspose2d(in_channels, out_channels, kernel_size, stride=1, padding=0,output_padding=0, groups=1, bias=True, dilation=1)

  • in_channels(int) – 输入信号的通道数
  • out_channels(int) – 卷积产生的通道数
  • kerner_size(int or tuple) - 卷积核的大小
  • stride(int or tuple,optional) - 卷积步长,即要将输入扩大的倍数。
  • padding(int or tuple, optional) - 输入的每一条边补充0的层数,高宽都增加2*padding
  • output_padding(int or tuple, optional) - 输出边补充0的层数,高宽都增加padding
  • groups(int, optional) – 从输入通道到输出通道的阻塞连接数
  • bias(bool, optional) - 如果bias=True,添加偏置
  • dilation(int or tuple, optional) – 卷积核元素之间的间距

对于每一条边输入,输出的尺寸的公式如下:

output=(input-1)*stride+outputpadding-2*padding+kernel\_size

5.实例化模型,定义loss函数和优化函数

model = AutoEncoder().to(device)

# 定义loss函数和优化方法
loss_fn = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3, weight_decay=1e-5)

6.训练并保存解码器生成的图片

for t in range(40):
    for data in train_data:
        img, label = data
        img = img.to(device)
        label = label.to(device)
        _, output = model(img)
        loss = loss_fn(output, img) / img.shape[0]  # 平均损失

        # 反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    if (t + 1) % 5 == 0:  # 每 5 次,保存一下解码的图片和原图片
        print('epoch: {}, Loss: {:.4f}'.format(t + 1, loss.item()))
        pic = to_img(output.cpu().data)
        if not os.path.exists('./conv_autoencoder'):
            os.mkdir('./conv_autoencoder')
        save_image(pic, './conv_autoencoder/decode_image_{}.png'.format(t + 1))
        save_image(img, './conv_autoencoder/raw_image_{}.png'.format(t + 1))

结果对比(左边生成图片,右边原始图片):

pytorch自动编码器实现有损图像压缩_第1张图片pytorch自动编码器实现有损图像压缩_第2张图片

附上完整代码:

import os
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader
from torchvision import datasets, transforms
from torchvision.utils import save_image

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
batch_size = 512

# 标准化
data_tf = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize([0.5], [0.5])]
)


train_dataset = datasets.MNIST(root='./data', train=True, transform=data_tf, download=True)
train_data = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)

def to_img(x):
    x = 0.5 * (x + 1.)  # 将-1~1转成0-1
    x = x.clamp(0, 1)
    x = x.view(x.shape[0], 1, 28, 28)
    return x


class AutoEncoder(nn.Module):
    def __init__(self):
        super(AutoEncoder, self).__init__()
        self.encoder = nn.Sequential(
            nn.Conv2d(1, 16, 3, stride=3, padding=1),  # b,16,10,10
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=2),  # b,16,5,5
            nn.Conv2d(16, 8, 3, stride=2, padding=1),  # b,8,3,3
            nn.ReLU(True),
            nn.MaxPool2d(2, stride=1)  # b,8,2,2
        )
        self.decoder = nn.Sequential(
            # nn.ConvTranspose2d(8, 8, 3, stride=2, padding=1),  # b,8,3,3
            # nn.ReLU(True),
            # nn.ConvTranspose2d(8, 16, 4, stride=4, padding=1),  # b,16,10,10
            # nn.ReLU(True),
            # nn.ConvTranspose2d(16, 1, 3, stride=3, padding=1),  # b,1,28,28
            # nn.Tanh()
            nn.ConvTranspose2d(8, 16, 3, stride=2),   # b,16,5,5
            nn.ReLU(True),
            nn.ConvTranspose2d(16, 8, 5, stride=3, padding=1),  # b,8,15,15
            nn.ReLU(True),
            nn.ConvTranspose2d(8, 1, 2, stride=2, padding=1),   # b,1,28,28
            nn.Tanh()
        )

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


model = AutoEncoder().to(device)

# 定义loss函数和优化方法
loss_fn = nn.MSELoss()
optimizer = optim.Adam(model.parameters(), lr=1e-3, weight_decay=1e-5)

for t in range(40):
    for data in train_data:
        img, label = data
        img = img.to(device)
        label = label.to(device)
        _, output = model(img)
        loss = loss_fn(output, img) / img.shape[0]  # 平均损失

        # 反向传播
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    if (t + 1) % 5 == 0:  # 每 5 次,保存一下解码的图片和原图片
        print('epoch: {}, Loss: {:.4f}'.format(t + 1, loss.item()))
        pic = to_img(output.cpu().data)
        if not os.path.exists('./conv_autoencoder'):
            os.mkdir('./conv_autoencoder')
        save_image(pic, './conv_autoencoder/decode_image_{}.png'.format(t + 1))
        save_image(img, './conv_autoencoder/raw_image_{}.png'.format(t + 1))

 

 

你可能感兴趣的:(深度学习入门)