PyTorch框架下分别使用Vgg、Resnet、Densenet提取图像集特征

这里主要是使用预训练好的模型进行图片特征的提取,分别使用三个模型进行抽取。

而特征提取是提取神经网络模型的倒数第二层,这里自己对模型的进行了微调,话不多说,直接上代码。

使用resnet

import torch
import torch.nn as nn
from torch.autograd import Variable
from torchvision import models, transforms
from PIL import Image
import numpy as np
import os, glob

data_dir = './test'   # train
features_dir = './Resnet_features_test'  # Resnet_features_train


//这里自己修改网络
class net(nn.Module):
    def __init__(self):
        super(net, self).__init__()
        self.net = models.resnet50(pretrained=True)

    def forward(self, input):
        output = self.net.conv1(input)
        output = self.net.bn1(output)
        output = self.net.relu(output)
        output = self.net.maxpool(output)
        output = self.net.layer1(output)
        output = self.net.layer2(output)
        output = self.net.layer3(output)
        output = self.net.layer4(output)
        output = self.net.avgpool(output)
        return output


model = net()
//加载cuda
model = model.cuda()


def extractor(img_path, saved_path, net, use_gpu):
    transform = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor()]
    )

    img = Image.open(img_path)
    img = transform(img)
    print(img.shape)

    x = Variable(torch.unsqueeze(img, dim=0).float(), requires_grad=False)
    print(x.shape)

    if use_gpu:
        x = x.cuda()
        net = net.cuda()
    y = net(x).cpu()
    y = torch.squeeze(y)
    y = y.data.numpy()
    print(y.shape)
    np.savetxt(saved_path, y, delimiter=',')


if __name__ == '__main__':
    extensions = ['jpg', 'jpeg', 'JPG', 'JPEG']

    files_list = []
    x = os.walk(data_dir)
    for path,d,filelist in x:
        for filename in filelist:
            file_glob = os.path.join(path, filename)
            files_list.extend(glob.glob(file_glob))

    print(files_list)

    use_gpu = torch.cuda.is_available()

    for x_path in files_list:
        print("x_path" + x_path)
        file_name = x_path.split('/')[-1]
        fx_path = os.path.join(features_dir, file_name + '.txt')
        print(fx_path)
        extractor(x_path, fx_path, model, use_gpu)

使用vgg

import torch
import torch.nn as nn
from torch.autograd import Variable
from torchvision import models, transforms
from PIL import Image
import numpy as np
import os, glob

data_dir = './test'  # train
features_dir = './Vgg_features_test'  # Vgg_features_train


class Encoder(nn.Module):
    def __init__(self):
        super(Encoder, self).__init__()
        VGG = models.vgg16(pretrained=True)
        self.feature = VGG.features
        self.classifier = nn.Sequential(*list(VGG.classifier.children())[:-3])
        pretrained_dict = VGG.state_dict()
        model_dict = self.classifier.state_dict()
        pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
        model_dict.update(pretrained_dict)
        self.classifier.load_state_dict(model_dict)

    def forward(self, x):
        output = self.feature(x)
        output = output.view(output.size(0), -1)
        output = self.classifier(output)
        return output


model = Encoder()
model = model.cuda()


def extractor(img_path, saved_path, net, use_gpu):
    transform = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor()]
    )

    img = Image.open(img_path)
    img = transform(img)
    print(img.shape)

    x = Variable(torch.unsqueeze(img, dim=0).float(), requires_grad=False)
    print(x.shape)

    if use_gpu:
        x = x.cuda()
        net = net.cuda()
    y = net(x).cpu()
    y = torch.squeeze(y)
    y = y.data.numpy()
    print(y.shape)
    np.savetxt(saved_path, y, delimiter=',')


if __name__ == '__main__':
    extensions = ['jpg', 'jpeg', 'JPG', 'JPEG']

    files_list = []
    x = os.walk(data_dir)
    for path, d, filelist in x:
        for filename in filelist:
            file_glob = os.path.join(path, filename)
            files_list.extend(glob.glob(file_glob))

    print(files_list)

    use_gpu = torch.cuda.is_available()

    for x_path in files_list:
        print("x_path" + x_path)
        file_name = x_path.split('/')[-1]
        fx_path = os.path.join(features_dir, file_name + '.txt')
        print(fx_path)
        extractor(x_path, fx_path, model, use_gpu)

使用Densnet

import torch
import torch.nn as nn
from torch.autograd import Variable
from torchvision import models, transforms
from PIL import Image
import numpy as np
import os, glob

data_dir = './test'  # train
features_dir = './DenseNet_features_test'  # DenseNet_features_train


class Encoder(nn.Module):
    def __init__(self):
        super(Encoder, self).__init__()
        densnet = models.densenet121(pretrained=True)
        self.feature = densnet.features
        self.classifier = nn.Sequential(*list(densnet.classifier.children())[:-1])
        pretrained_dict = densnet.state_dict()
        model_dict = self.classifier.state_dict()
        pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
        model_dict.update(pretrained_dict)
        self.classifier.load_state_dict(model_dict)

    def forward(self, x):
        output = self.feature(x)
        avg = nn.AvgPool2d(7, stride=1)
        output = avg(output)
        return output


model = Encoder()
model = model.cuda()


def extractor(img_path, saved_path, net, use_gpu):
    transform = transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor()]
    )

    img = Image.open(img_path)
    img = transform(img)
    print(img.shape)

    x = Variable(torch.unsqueeze(img, dim=0).float(), requires_grad=False)
    print(x.shape)

    if use_gpu:
        x = x.cuda()
        net = net.cuda()
    y = net(x).cpu()
    y = torch.squeeze(y)
    y = y.data.numpy()
    print(y.shape)
    //保存为txt
    np.savetxt(saved_path, y, delimiter=',')


if __name__ == '__main__':
    extensions = ['jpg', 'jpeg', 'JPG', 'JPEG']

    files_list = []
    x = os.walk(data_dir)
    for path, d, filelist in x:
        for filename in filelist:
            file_glob = os.path.join(path, filename)
            files_list.extend(glob.glob(file_glob))

    print(files_list)

    use_gpu = torch.cuda.is_available()

 
    for x_path in files_list:
        # print("x_path" + x_path)
        file_name = x_path.split('/')[-1]
        fx_path = os.path.join(features_dir, file_name + '.txt')
        # print(fx_path)
        extractor(x_path, fx_path, model, use_gpu)

以上是使用三个模型的特征提取,可以根据不同的需求进行选择。

  • 31
    点赞
  • 239
    收藏
    觉得还不错? 一键收藏
  • 4
    评论
好的,我可以给你一个简单的示例代码。首先,你需要导入相关的库: ```python import torch import torchvision.models as models import torchvision.transforms as transforms from PIL import Image ``` 接下来,我们可以定义一个函数来加载和预处理图像,以便将其传递到模型中进行特征提取: ```python def load_image(image_path): image = Image.open(image_path) # 定义预处理转换 transform = transforms.Compose([ transforms.Resize(256), transforms.CenterCrop(224), transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]) ]) # 对图像进行预处理 image = transform(image).unsqueeze(0) return image ``` 现在我们可以定义一个函数来提取VGG16和ResNet50模型特征: ```python def extract_features(image_path, model): # 加载和预处理图像 image = load_image(image_path) # 将图像传递到模型中进行特征提取 features = model(image) return features.detach().numpy() ``` 现在我们可以使用这些函数来进行特征提取。首先,我们将加载VGG16模型提取图像特征: ```python # 加载VGG16模型 vgg16 = models.vgg16(pretrained=True).features # 提取图像特征 vgg16_features = extract_features('image.jpg', vgg16) ``` 接下来,我们将加载ResNet50模型提取图像特征: ```python # 加载ResNet50模型 resnet50 = models.resnet50(pretrained=True) # 删除ResNet50模型的最后一层全连接层 resnet50 = torch.nn.Sequential(*list(resnet50.children())[:-1]) # 提取图像特征 resnet50_features = extract_features('image.jpg', resnet50) ``` 现在,我们已经提取VGG16和ResNet50模型特征,可以进行比较和分析。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论 4
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值