![](https://img-blog.csdnimg.cn/20201014180756927.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
模型
文章平均质量分 83
lilso
这个作者很懒,什么都没留下…
展开
-
论文阅读《Learning visual similarity for product design with convolutional neural networks》
参考:论文 | 图像检索经典论文解读《Learning visual similarity for product design with convolutional neural networks》Learning visual similarity for product design with convolutional neural networks1. idea该文章研究的是用卷积神经网络学习产品相似性的两个问题,一是对于给定区域的图像,找出与这个区域中包含物品最相似的其它物品,二是原创 2021-07-28 22:18:20 · 298 阅读 · 0 评论 -
论文阅读《Cross-domain Image Retrieval with a DualAttribute-aware Ranking Network》
参考:读论文,衣物检索:Cross-domain Image Retrieval with a DualAttribute-aware Ranking Network (2015)Cross-domain Image Retrieval with a Dual Attribute-aware Ranking NetworkCross-domain Image Retrieval with a Dual Attribute-aware Ranking Network1. idea该论文基于一原创 2021-07-28 22:05:20 · 211 阅读 · 0 评论 -
YoLo V1
参考1.目标检测——搭建更好更快的YOLO!2.You Only Look Once: Unified, Real-Time Object Detection模型框架1. 论文模型框架1.1 Backbone1.2 HeadSPP+SAM1.2.1 SPP1.2.2 SAM代码实现1. Backbone(ResNet)1.1 残差原理1.2 ResNet 基本结构1.3 BasicBlock and Bottleneck1.4 实现思路通过形如resnet*(原创 2021-07-28 21:38:52 · 143 阅读 · 0 评论 -
VGG细节
参考1.Very Deep Convolutional Networks for Large-Scale Image Recognition2.VGG16学习笔记1. 模型组成input: 224 x 224 RGB imagepreprocessing: the mean RGB value, computed ont the training set, from each pixel组件: 3 x 3 convolution filters, 1 x 1 convolution filte原创 2021-05-31 13:15:20 · 311 阅读 · 0 评论