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