图像分类,也可以称作图像识别,顾名思义,就是辨别图像中的物体属于什么类别。核心是从给定的分类集合中给图像分配一个标签的任务。实际上,这意味着我们的任务是分析一个输入图像并返回一个将图像分类的标签。在这里,我们将分别自己搭建卷积神经网路、迁移学习分别对图像数据集进行分类。本篇使用的数据集下载地址为:
链接:https://pan.baidu.com/s/1mS4xIf1sr3mhYn-cJNMqjQ
提取码:k57i
Pytorch_datasets文件夹底下包括两个文件夹存放各自的图片数据集。
卷积神经网络与普通的神经网络的区别在于,卷积神经网络包含了一个卷积层convolutional layer和池化层pooling layer构成的特征提取器。卷积神经网路中每层卷积层由若干卷积单元组成,每个卷积单元的参数都是通过反向传播算法优化得到的。卷积运算的目的是提取输入的不同特征,第一层卷积层可能只能提取一些低级的特征如边缘、线条和角等层级,更多层的网络能从低级特征中迭代提取更复杂的特征。池化层(Pooling layer),通常在卷积层之后会得到维度很大的特征,将特征切成几个区域,取其最大值或平均值,得到新的、维度较小的特征。
如上图左,全连接神经网络是一个“平面”,包括输入层—激活函数—全连接层,右图的卷积神经网络是一个“立体”,包括输入层—卷积层—激活函数—池化层—全连接层。卷积神经网络提取的数据量更大,因此常用在图像处理上。
接下来,我们自己搭建神经网络对上面同样的数据集进行分类
import os
import torch
from torch import nn,optim
from torch.nn import functional as F
from torch.utils import data
from torchvision import datasets,transforms
train_path = "./pytorch_datasets/train"
test_path = "./pytorch_datasets/test"
#定义数据集预处理的方法
data_transform = transforms.Compose([
# transforms.Resize((224,224)),
transforms.RandomResizedCrop(150),
transforms.ToTensor(),
transforms.Normalize((0.1307,),(0.3081,))
])
datasets_train = datasets.ImageFolder(train_path,data_transform)
datasets_test = datasets.ImageFolder(test_path,data_transform)
train_loader = data.DataLoader(datasets_train,batch_size=32,shuffle=True)
test_loader = data.DataLoader(datasets_test,batch_size=16,shuffle=False)
#搭建网络
class CNN(nn.Module):
def __init__(self):
super(CNN, self).__init__()
self.conv1 = nn.Conv2d(3, 32, 3)
self.max_pool1 = nn.MaxPool2d(2)
self.conv2 = nn.Conv2d(32, 64, 3)
self.max_pool2 = nn.MaxPool2d(2)
self.conv3 = nn.Conv2d(64, 128, 3)
self.max_pool3 = nn.MaxPool2d(2)
self.conv4 = nn.Conv2d(128, 128, 3)
self.max_pool4 = nn.MaxPool2d(2)
self.fc1 = nn.Linear(6272, 512)
self.fc2 = nn.Linear(512, 1)
def forward(self, x):
in_size = x.size(0)
x = self.conv1(x)
x = F.relu(x)
x = self.max_pool1(x)
x = self.conv2(x)
x = F.relu(x)
x = self.max_pool2(x)
x = self.conv3(x)
x = F.relu(x)
x = self.max_pool3(x)
x = self.conv4(x)
x = F.relu(x)
x = self.max_pool4(x)
# 展开
x = x.view(in_size, -1)
x = self.fc1(x)
x = F.relu(x)
x = self.fc2(x)
x = torch.sigmoid(x)
return x
DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(DEVICE)
model = CNN().to(DEVICE)
optimizer = optim.Adam(model.parameters(),lr=0.0001)
for epoch in range(30):
model.train()
for i,(image,label) in enumerate(train_loader):
data,target = Variable(image).cuda(),Variable(label.cuda()).unsqueeze(-1)
optimizer.zero_grad()
output = model(data)
output=output.to(torch.float32)
target=target.to(torch.float32)
# print(output.shape,target.shape)
loss = F.binary_cross_entropy(output,target)
loss.backward()
optimizer.step()
if (i+1)%10==0:
print('Train Epoch: {} [{}/{} ({:.0f}%)] Loss: {:.6f}'.format(
epoch, (i+1) * len(data), len(train_loader.dataset),
100. * (i+1) / len(train_loader), loss.item()))
for epoch in range(30):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(DEVICE), target.to(DEVICE).float().unsqueeze(-1)
output = model(data)
test_loss += F.binary_cross_entropy(output, target, reduction='sum').item() # 将一批的损失相加
pred = torch.tensor([[1] if num[0] >= 0.5 else [0] for num in output]).to(DEVICE)
correct += pred.eq(target.long()).sum().item()
print('
Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)
'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
问题来了?什么是迁移学习?迁移学习(Transfer learning) 顾名思义就是把已训练好的模型(预训练模型)参数迁移到新的模型来帮助新模型训练。考虑到大部分数据或任务都是存在相关性的,所以通过迁移学习我们可以将已经学到的模型参数(也可理解为模型学到的知识)通过某种方式来分享给新模型从而加快并优化模型的学习效率不用像大多数网络那样从零学习。其中,实现迁移学习有以下三种手段:
1.Transfer Learning:冻结预训练模型的全部卷积层,只训练自己定制的全连接层。
2.Extract Feature Vector:先计算出预训练模型的卷积层对所有训练和测试数据的特征向量,然后抛开预训练模型,只训练自己定制的简配版全连接网络。
3.Fine-tuning:冻结预训练模型的部分卷积层(通常是靠近输入的多数卷积层,因为这些层保留了大量底层信息)甚至不冻结任何网络层,训练剩下的卷积层(通常是靠近输出的部分卷积层)和全连接层。
预训练模型有很多,本文选用InceptionV3预训练模型,它是由谷歌团队从ImageNet的1000个类别的超大数据集训练而来的,表现优异,经常用来做计算机视觉方面的迁移学习研究和应用。
from sklearn.model_selection import train_test_split
import numpy as np
import os
from tqdm import tqdm
from PIL import Image
import torch
import torchvision.datasets
import torchvision.transforms as transforms
import torchvision.models as models
trainpath = "./pytorch_datasets/train"
testpath = "./pytorch_datasets/test"
batch_size = 16
traintransform = transforms.Compose([transforms.RandomRotation(20),
transforms.ColorJitter(brightness=0.1),
transforms.Resize([224,224]),
transforms.ToTensor()])
valtransform = transforms.Compose([transforms.Resize([224,224]),
transforms.ToTensor()])
trainData = torchvision.datasets.ImageFolder(trainpath,transform=traintransform)
testData = torchvision.datasets.ImageFolder(testpath,transform=valtransform)
trainLoader = torch.utils.data.DataLoader(dataset=trainData,batch_size=batch_size,shuffle=True)
testLoader = torch.utils.data.DataLoader(dataset=testData,batch_size=batch_size,shuffle=False)
model = models.resnet34(pretrained=True)
model.fc = torch.nn.Linear(512,2)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(),lr=0.0001)
from torch.autograd import Variable
import time
train_loss = []
valid_loss = []
accuracy = []
for epoch in range(100):
epoch_start_time = time.time()
model.train()
total_loss = 0
train_corrects = 0
for i,(image,label) in enumerate(trainLoader):
image = Variable(image.cuda())
label = Variable(label.cuda())
model.cuda()
target = model(image)
loss = criterion(target,label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_loss += loss.item()
max_value,max_index = torch.max(target,1)
pred_label = max_index.cpu().numpy()
true_label = label.cpu().numpy()
train_corrects += np.sum(pred_label==true_label)
loss = total_loss/float(len(trainLoader))
train_acc = train_corrects/100
train_loss.append(loss)
for epoch in range(100):
model.eval()
corrects = eval_loss = 0
with torch.no_grad():
for image,label in testLoader:
image = Variable(image.cuda())
label = Variable(label.cuda())
model.cuda()
pred = model(image)
loss = criterion(pred,label)
eval_loss += loss.item()
max_value,max_index = torch.max(pred,1)
pred_label = max_index.cpu().numpy()
true_label = label.cpu().numpy()
corrects += np.sum(pred_label==true_label)
loss = eval_loss/float(len(testLoader))
acc = corrects/100
valid_loss.append(loss)
accuracy.append(acc)
import matplotlib.pyplot as plt
print("**********ending*********")
plt.plot(train_loss)
plt.plot(valid_loss)
plt.title('loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'test'], loc='upper left')
plt.show()
原文链接:https://blog.csdn.net/qq_43018832/article/details/127832688?spm=1001.2014.3001.5502
页面更新:2024-04-16
本站资料均由网友自行发布提供,仅用于学习交流。如有版权问题,请与我联系,QQ:4156828
© CopyRight 2008-2024 All Rights Reserved. Powered By bs178.com 闽ICP备11008920号-3
闽公网安备35020302034844号