这是介绍AOI(Age of Information)的资料,AOI是一个衡量信息新鲜度的一个指标
2021-10-18 22:07:34 4.15MB AOI 信息传输
1
这是全面介绍AOI(Age of Information)的资料。AOI是一个衡量信息新鲜度的一个指标,由于AOI这个概念比较新,全面介绍AOI的资料目前比较少
2021-10-18 22:07:34 3.07MB AOI 信息传输
1
PyTorch中的深度度量学习 Learn deep metric for image retrieval or other information retrieval. 我们的XBM被提名为2020年CVPR最佳论文。 知乎XBM上的一个博客 我写了一个知乎文章,通俗快速解读了XBM想法动机: 欢迎大家阅读指点! 推荐最近发表的不是我写的DML优秀论文: 来自康奈尔科技大学和Facebook AI 摘要:过去四年来,深度度量学习论文一直宣称准确性方面取得了长足进步,通常比十年前方法的性能提高一倍还多。 在本文中,我们将仔细研究该领域,以了解是否确实如此。 我们在这些论文的实验设置中发现了缺陷,并提出了一种评估度量学习算法的新方法。 最后,我们提供的实验结果表明,随着时间的推移,这种改进最多只能算是微不足道了。 XBM:DML的新Sota方法,被CVPR-2020接受为口服,并被提名
2021-10-17 14:51:47 44KB image-retrieval cvpr xbm deep-metric-learning
1
少量学习的原型网络 NIPS 2017论文》的代码。 如果您使用此代码,请引用我们的论文: @inproceedings{snell2017prototypical, title={Prototypical Networks for Few-shot Learning}, author={Snell, Jake and Swersky, Kevin and Zemel, Richard}, booktitle={Advances in Neural Information Processing Systems}, year={2017} } 训练原型网络 安装依赖 该代码
2021-10-08 09:58:44 209KB deep-learning pytorch metric-learning nips-2017
1
关于mnist的度量学习( 和)和t_SNE的可视化 n_pair_loss n_pair_angular_loss 用法 从终端运行pip install -r requirements.txt python src/utils/mnist_to_img.py返回由标签分隔的mnist数据python src/n_pair_train.py将模型保存到src/checkpoints/checkpoint.pth.tar并记录logs/2019_00_CNN/* python src/t_SNE.py显示t_SNE
1
Survey_of_Deep_Metric_Learning:深度度量学习和相关作品的全面调查
2021-09-24 14:30:18 102KB deep-learning tensorflow pytorch metric-learning
1
主要介绍了keras 自定义loss损失函数,sample在loss上的加权和metric详解,具有很好的参考价值,希望对大家有所帮助。一起跟随小编过来看看吧
2021-09-17 10:15:16 109KB keras sample loss函数 加权
1
containers: - args: - --cert-dir=/tmp - --secure-port=4443 - --kubelet-preferred-address-types=InternalIP - --kubelet-use-node-status-port - --kubelet-insecure-tls image: registry.cn-hangzhou.aliyuncs.com/k8s_police/metric-server:v0.5.0
2021-09-10 14:01:52 4KB /metric-server:v
1
metrics-server/metrics-server:v0.5.0 已打包 docker load -i metric-serverv0.5.0.tar && docker image ls
2021-09-09 18:01:21 61.77MB metrics-server/m
1
The proliferation of information housed in computerized domains makes it vital to find tools to search these resources efficiently and effectively. Ordinary retrieval techniques are inadequate because sorting is simply impossible. Consequently, proximity searching has become a fundamental computation task in a variety of application areas. Similarity Search focuses on the state of the art in developing index structures for searching the metric space. Part I of the text describes major theoretical principles, and provides an extensive survey of specific techniques for a large range of applications. Part II concentrates on approaches particularly designed for searching in large collections of data. After describing the most popular centralized disk-based metric indexes, approximation techniques are presented as a way to significantly speed up search time at the cost of some imprecision in query results. Finally, the scalable and distributed metric structures are discussed.
2021-08-10 16:00:00 11.61MB Similarity Search Metric Space
1