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。