pytorch获得图片特征

最新推荐文章于 2024-01-25 01:55:40 发布

love_data_scientist

最新推荐文章于 2024-01-25 01:55:40 发布

阅读量1.3k

点赞数 1

分类专栏：数据挖掘

本文链接：https://blog.csdn.net/love_data_scientist/article/details/96496537

版权

本文介绍了如何使用PyTorch的预训练ResNet152模型来提取图像特征。通过去除全连接层并调整模型，处理非1:1比例图片时，输出维度为[1, 2048, 2, 6]。解决方法包括从输入和输出两端调整，如使用AdaptiveAvgPool2d将输出变为[1, 2048, 1, 1]。" 131011974,15036105,Java FTP定时下载xls文件问题,"['Java', '服务器', 'FTP']

摘要由CSDN通过智能技术生成

1.模型为resnet152, 默认输出图片大小是224*224*3

2.获取除去全连接层的模型

import torch
import torch.nn as nn
import torchvision.models as models
from torch.autograd import Variable
resnet152 = models.resnet152(pretrained=True)
modules=list(resnet152.children())[:-1]
resnet152=nn.Sequential(*modules)

for p in resnet152.parameters():
p.requires_grad = False

2.使用新模型处理图片

import cv2
import torch
import torch.nn as nn
import torchvision.models as models
from torch.autograd import Variable

from PIL import Image

import torchvision.transforms as transforms

class ResNet152Bottom(nn.Module):
def __init__(self, original_model):
super(ResNet152Bottom, self).__init__()
self.features = nn.Sequential(*list(original_model.children())[:-1])

def forward(self, x):
x = self.features(