深度学习编程入门deep-learning-for-image-processing-master 关于图片分类test1_official_demo的学习

这个小文件夹有三个部分组成，分别有model,predict和train

首先从train开始学习

import torch
import torchvision
import torch.nn as nn
from model import LeNet
import torch.optim as optim
import torchvision.transforms as transforms


def main():
    transform = transforms.Compose(
        [transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

    # 50000张训练图片
    # 第一次使用时要将download设置为True才会自动去下载数据集
    train_set = torchvision.datasets.CIFAR10(root='./data', train=True,
                                             download=False, transform=transform)
    train_loader = torch.utils.data.DataLoader(train_set, batch_size=36,
                                               shuffle=True, num_workers=0)

    # 10000张验证图片
    # 第一次使用时要将download设置为True才会自动去下载数据集
    val_set = torchvision.datasets.CIFAR10(root='./data', train=False,
                                           download=False, transform=transform)
    val_loader = torch.utils.data.DataLoader(val_set, batch_size=5000,
                                             shuffle=False, num_workers=0)
    val_data_iter = iter(val_loader)
    val_image, val_label = val_data_iter.next()
    
    # classes = ('plane', 'car', 'bird', 'cat',
    #            'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

    net = LeNet()
    loss_function = nn.CrossEntropyLoss()
    optimizer = optim.Adam(net.parameters(), lr=0.001)

    for epoch in range(5):  # loop over the dataset multiple times

        running_loss = 0.0
        for step, data in enumerate(train_loader, start=0):
            # get the inputs; data is a list of [inputs, labels]
            inputs, labels = data

            # zero the parameter gradients
            optimizer.zero_grad()
            # forward + backward + optimize
            outputs = net(inputs)
            loss = loss_function(outputs, labels)
            loss.backward()
            optimizer.step()

            # print statistics
            running_loss += loss.item()
            if step % 500 == 499:    # print every 500 mini-batches
                with torch.no_grad():
                    outputs = net(val_image)  # [batch, 10]
                    predict_y = torch.max(outputs, dim=1)[1]
                    accuracy = torch.eq(predict_y, val_label).sum().item() / val_label.size(0)

                    print('[%d, %5d] train_loss: %.3f  test_accuracy: %.3f' %
                          (epoch + 1, step + 1, running_loss / 500, accuracy))
                    running_loss = 0.0

    print('Finished Training')

    save_path = './Lenet.pth'
    torch.save(net.state_dict(), save_path)


if __name__ == '__main__':
    main()

主函数中，首先是transform

def main():

  transform=transform.Compose([transforms.Totensor(),transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])这里看你的想法添加操作，比如旋转、切割等等

  train_set=torchvision.datasets.CIFAR10(root='./data',train=True,download=False, transform=transform)设置训练数据

  train_loader=torch.utils.data.Dataloader(train_set, batch_size=36,shuffle=True,num_workers=0)

加载数据集

val_sset=torchvision.dataset.CIFAR10(root=./data/,train=false,download=false,transform=transform)这里可以和训练使用不一样的transform

val_loader=torch.utils.data.Dataloader(val_set,natch_size=50000,shuffle=false,num_worker=0)

val_data_iter=iter(val_loader)

val_image,val_label=val_data_iter.next()每次取一个，相当于之前那个dataset的作用

# classes = ('plane', 'car', 'bird', 'cat',
#            'deer', 'dog', 'frog', 'horse', 'ship', 'truck')d
定义网络

net=lenet()

loss_function=nn.CrossEntroyLoss()设置损失函数

optimizer=optim.Adam(net.parameters(),lr=0.001)

for epoch in range(5)开始训练

  running_loss=0.0

 for step,data in enumerate(train_loader,start=0):

   inputs,labels=data

[inputs, labels]

  optimizer.zero_grad()

 outputs=net(inputs)

 loss=loss_function(outputs,labels)

 loss.backward()

 optimizer.step()

 running_loss+=loss.item()

 这里都是常规操作，记住就行

 if step %500==499:开始验证

   with torch.no_grad():

    outputs=net(val_image)

  predict_y=torch.max(outputs,dim=1)[1]

  accuary=torch.eq(predict_y,val_label).sum().item()/val_label.size(0)

  running_loss=0.0

保存模型

save_path='./lenet.pth'

torch.save(net.state_dict(),save.path)

接下来看predict.py

import torch
import torchvision.transforms as transforms
from PIL import Image

from model import LeNet


def main():
    transform = transforms.Compose(
        [transforms.Resize((32, 32)),
         transforms.ToTensor(),
         transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

    classes = ('plane', 'car', 'bird', 'cat',
               'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

    net = LeNet()
    net.load_state_dict(torch.load('Lenet.pth'))

    im = Image.open('1.jpg')
    im = transform(im)  # [C, H, W]
    im = torch.unsqueeze(im, dim=0)  # [N, C, H, W]

    with torch.no_grad():
        outputs = net(im)
        predict = torch.max(outputs, dim=1)[1].numpy()
    print(classes[int(predict)])


if __name__ == '__main__':
    main()

    

def main():

  transform=transform.Compose([transforms.Resize((32,32)),transforms.ToTensor(),

                                                      transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])

 classes=('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

 net=LeNet()

 net.load_state_dict(torch.load('Lenet.pth'))

 im=Image.open('1.jpg')

 im=transform(im)

 im=torch.unsqueeze(im,dim=0)

 with torch.no_grad():

   outputs=net(im)

   predict=torch.max(   outputs,dim=1)[1].numpy()

最后是moedl

本文中的模型是简单的lenet

import torch.nn as nn
import torch.nn.functional as F


class LeNet(nn.Module):
    def __init__(self):
        super(LeNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, 5)
        self.pool1 = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(16, 32, 5)
        self.pool2 = nn.MaxPool2d(2, 2)
        self.fc1 = nn.Linear(32*5*5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))    # input(3, 32, 32) output(16, 28, 28)
        x = self.pool1(x)            # output(16, 14, 14)
        x = F.relu(self.conv2(x))    # output(32, 10, 10)
        x = self.pool2(x)            # output(32, 5, 5)
        x = x.view(-1, 32*5*5)       # output(32*5*5)
        x = F.relu(self.fc1(x))      # output(120)
        x = F.relu(self.fc2(x))      # output(84)
        x = self.fc3(x)              # output(10)
        return x

这个网络非常简单,由卷积、池化、全连接这些层构成

class LeNet(nn.Module):

  def __init__(self):

    super(LeNet,self).__init__(）

   self.conv1=nn.Conv2d(3,16,5）

  self.pool1=nn.MaxPool2d(2,2)

  self.conv2d=nn/Conv2d(16,32,5)

  self.pool2=nn.MaxPool2d(2,2)

  self.fc1=nn.Linear(32**5,120)

  self.fc2=nn.Linear(120,84)

  self.fc3=nn.Linear(84,10)

def forward(self,x):

   x=F.relu(self.conv1(x)

  x=self.pool1(x)

  x=F.relu(self.conv2d(X)

 x=self.pool2(x)

 x=x.view(-1,32*5*5)调整尺寸

x=F.relu(self.fc1(x))

x=F.relu(self.fc2(x))

x=self.fc3(x)

return x