0
点赞
收藏
分享

微信扫一扫

Autoencoder线性和卷积的Pytorch实现

ivy吖 2023-05-07 阅读 112
pytorch深度学习机器学习git2dPython后端开发


我的代码在kaggle上跑的。

Autoencoder线性和卷积的Pytorch实现_深度学习

线性AE

import os
import datetime
import numpy as np
import torch
import torchvision
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.utils import save_image
from torchvision.datasets import MNIST


if not os.path.exists('./dc_img'):
    os.mkdir('./dc_img')


def to_img(x):
    x = 0.5 * (x + 1)
    x = x.clamp(0, 1)
    x = x.view(x.size(0), 1, 28, 28)
    return x


num_epochs = 20
batch_size = 128
learning_rate = 1e-3

img_transform = transforms.Compose([
    transforms.ToTensor(),
    # transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
    transforms.Normalize([0.5], [0.5])
])

dataset = MNIST('./data', transform=img_transform, download=True)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)

class autoencoder(nn.Module):
    def __init__(self):
        super(autoencoder, self).__init__()
        self.encoder = nn.Sequential(
            nn.Linear(28*28, 128),
            nn.ReLU(True),
            nn.Linear(128, 64),
            nn.ReLU(True),
            nn.Linear(64, 12),
            nn.ReLU(True),
            nn.Linear(12, 3)
        )
        self.decoder = nn.Sequential(
            nn.Linear(3, 12),
            nn.ReLU(True),
            nn.Linear(12, 64),
            nn.ReLU(True),
            nn.Linear(64, 128),
            nn.ReLU(True),
            nn.Linear(128, 28*28),
            nn.Tanh()
        )

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

model = autoencoder()
print(model)

# 查看网络流程
net = nn.Sequential(
            nn.Linear(28*28, 128),nn.ReLU(True),
            nn.Linear(128, 64),nn.ReLU(True),
            nn.Linear(64, 12),nn.ReLU(True),
            nn.Linear(12, 3),
            nn.Linear(3, 12),nn.ReLU(True),
            nn.Linear(12, 64),nn.ReLU(True),
            nn.Linear(64, 128),nn.ReLU(True),
            nn.Linear(128, 28*28),nn.Tanh())
X = torch.rand(size=(1,28*28), dtype=torch.float32)
for layer in net:
    print(layer.__class__.__name__,'output shape: \t',X.shape)
    X = layer(X)

if torch.cuda.is_available():
    model.cuda()
    print('cuda is OK!')
#     model = model.to('cuda')
else:
    print('cuda is NO!')
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate,weight_decay=1e-5)
starttime = datetime.datetime.now()

for epoch in range(num_epochs):
    for data in dataloader:
        img, label = data
        img = img.view(img.size(0), -1)
        img = Variable(img).cuda()
        # ===================forward=====================
        output = model(img)
        loss = criterion(output, img)
        # ===================backward====================
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    # ===================log========================
    endtime = datetime.datetime.now()
    print('epoch [{}/{}], loss:{:.4f}, time:{:.2f}s'.format(epoch+1, num_epochs, loss.item(), (endtime-starttime).seconds))
    
    # if epoch % 10 == 0:
    pic = to_img(output.cpu().data)
    save_image(pic, './dc_img/image_{}.png'.format(epoch))

torch.save(model.state_dict(), './conv_autoencoder.pth')


import matplotlib.pyplot as plt
from scipy.stats import norm

n = 15 #15*15 225个数字图片
digit_size = 28
figure = np.zeros((digit_size*n,digit_size*n))#最终图片
grid_x = norm.ppf(np.linspace(0.05,0.95,n))#假设隐变量空间符合高斯分布
grid_y = norm.ppf(np.linspace(0.05,0.95,n))#ppf随机取样

for i,yi in enumerate(grid_x):
    for j, xi in enumerate(grid_y):
        z_sample = np.array([[[[xi, yi]]]],dtype=np.float32)#重复z_sample多次，形成一个完整的batch
        z_sample = np.tile(z_sample, batch_size*392).reshape(batch_size,784)
        z_sample = torch.from_numpy(z_sample) # 转tensor
        z_sample = z_sample.cuda()# 放到cuda上
        output=model(z_sample)
        digit=output[0].reshape(digit_size, digit_size)#128*784->28*28
        digit = digit.cpu().detach().numpy() # 转numpy
        figure[i*digit_size:(i+1)*digit_size,j*digit_size:(j+1)*digit_size] = digit

plt.figure(figsize=(10, 10))
plt.imshow(figure, cmap='Greys_r')
plt.show()

卷积AE

import os
import datetime

import torch
import torchvision
from torch import nn
from torch.autograd import Variable
from torch.utils.data import DataLoader
from torchvision import transforms
from torchvision.utils import save_image
from torchvision.datasets import MNIST


if not os.path.exists('./dc_img'):
    os.mkdir('./dc_img')


def to_img(x):
    x = 0.5 * (x + 1)
    x = x.clamp(0, 1)
    x = x.view(x.size(0), 1, 28, 28)
    return x


num_epochs = 100
batch_size = 128
learning_rate = 1e-3

img_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5), (0.5))
])

dataset = MNIST('./data', transform=img_transform, download=True)
dataloader = DataLoader(dataset, batch_size=batch_size, shuffle=True)

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):
        x = self.encoder(x)
        x = self.decoder(x)
        return x

model = autoencoder()
print(model)

# 查看网络流程
net = nn.Sequential(
            nn.Conv2d(1, 16, 3, stride=3, padding=1), nn.ReLU(True),nn.MaxPool2d(2, stride=2),  
            nn.Conv2d(16, 8, 3, stride=2, padding=1),nn.ReLU(True),nn.MaxPool2d(2, stride=1),
            nn.ConvTranspose2d(8, 16, 3, stride=2), nn.ReLU(True),
            nn.ConvTranspose2d(16, 8, 5, stride=3, padding=1), nn.ReLU(True),
            nn.ConvTranspose2d(8, 1, 2, stride=2, padding=1), nn.Tanh())
X = torch.rand(size=(1,1,28,28), dtype=torch.float32)
for layer in net:
    print(layer.__class__.__name__,'output shape: \t',X.shape)
    X = layer(X)


if torch.cuda.is_available():
    model.cuda()
    print('cuda is OK!')
#     model = model.to('cuda')
else:
    print('cuda is NO!')
criterion = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate,weight_decay=1e-5)
starttime = datetime.datetime.now()

for epoch in range(num_epochs):
    for data in dataloader:
        img, label = data
        img = Variable(img).cuda()
        # ===================forward=====================
        output = model(img)
        loss = criterion(output, img)
        # ===================backward====================
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
    # ===================log========================
    endtime = datetime.datetime.now()
    print('epoch [{}/{}], loss:{:.4f}, time:{:.2f}s'.format(epoch+1, num_epochs, loss.item(), (endtime-starttime).seconds))
    
    # if epoch % 10 == 0:
    pic = to_img(output.cpu().data)
    save_image(pic, './dc_img/image_{}.png'.format(epoch))

# torch.save(model.state_dict(), './conv_autoencoder.pth')

import matplotlib.pyplot as plt
from scipy.stats import norm
import numpy as np

n = 15 #15*15 225个数字图片
digit_size = 28
figure = np.zeros((digit_size*n,digit_size*n))#最终图片
grid_x = norm.ppf(np.linspace(0.05,0.95,n))#假设隐变量空间符合高斯分布
grid_y = norm.ppf(np.linspace(0.05,0.95,n))#ppf随机取样

for i,yi in enumerate(grid_x):
    for j, xi in enumerate(grid_y):
        z_sample = np.array([[[[xi, yi]]]],dtype=np.float32)#重复z_sample多次，形成一个完整的batch
        z_sample = np.tile(z_sample, batch_size*392).reshape(batch_size,1,28,28)
        z_sample = torch.from_numpy(z_sample) # 转tensor
        z_sample = z_sample.cuda()# 放到cuda上
        output=model(z_sample)
        digit=output[0].reshape(digit_size, digit_size)#128*784->28*28
        digit = digit.cpu().detach().numpy() # 转numpy
        figure[i*digit_size:(i+1)*digit_size,j*digit_size:(j+1)*digit_size] = digit

plt.figure(figsize=(10, 10))
plt.imshow(figure, cmap='Greys_r')
plt.show()

 参考：

pytorch-beginner/08-AutoEncoder at master · L1aoXingyu/pytorch-beginner (github.com)


https://github.com/L1aoXingyu/pytorch-beginner/tree/master/08-AutoEncoder


举报

相关推荐

pytorch的卷积层池化层和非线性变化 和机器学习线性回归

react.jsjavascript前端

Pytorch实现的卷积算子

pytorch深度学习人工智能2d卷积Python后端开发

pytorch实现线性回归

人工智能大数据信息可视化

Pytorch 实现下采样的方法（卷积和池化）

pythonpytorch

PyTorch实现基本的线性回归

pytorch线性回归python

Pytorch线性回归实现（Pycharm实现）

电脑经验分享安全性测试百度性能优化

Pytorch实现线性回归模型

数据集反向传播神经网络编程语言

Pytorch API实现线性回归

开发语言深度学习

pytorch代码实现之SAConv卷积

qt开发语言

5、使用PyTorch 实现线性回归

深度学习python设计模型数据归零Java编程语言
0 条评论