用于构建高质量数据集和计算机视觉模型的开源工具。 •• •••• 是由创建的开源ML工具，可帮助您构建高质量的数据集和计算机视觉模型。 使用FiftyOne，您可以搜索，排序，过滤，可视化，分析和改善数据集，而无需进行过多的整理或编写自定义脚本。它还提供了用于分析模型的强大功能，使您能够了解模型的优缺点，可视化，诊断和纠正其故障模式，等等。 FiftyOne的设计轻巧，可轻松集成到您现有的CV / ML工作流程中。 您可以加入我们的Slack社区，阅读我们在Medium上的博客，并在社交媒体上关注我们，从而参与其中： 安装 您可以通过pip安装FiftyOne的最新稳定版本： pip install fiftyone 请查阅以获取故障排除以及有关使用FiftyOne进行启动和运行的其他信息。 快速开始 通过启动快速入门，直接进入FiftyOne： fiftyone quicksta

(Article) Artificial Intelligence Algorithms人工智能算法

EGNN-Pytorch（WIP） 中的实现。 最终可用于Alphafold2复制。 安装 $ pip install egnn-pytorch 用法 import torch from egnn_pytorch import EGNN layer1 = EGNN ( dim = 512 ) layer2 = EGNN ( dim = 512 ) feats = torch . randn ( 1 , 16 , 512 ) coors = torch . randn ( 1 , 16 , 3 ) feats , coors = layer1 ( feats , coors ) feats , coors = layer2 ( feats , coors ) # (1, 16, 512), (1, 16, 3) 带边 import torch from egnn_pytorch impo

什么是人工智能？人工智能（Artificial Intelligence），英文缩写为AI。它是研究、开发用于模拟、延伸和扩展人的智能的理论、方法、技术及应用系统的一门新的技术科学。人工智能是计算机科学的一个分支，它试图了解智能的实质，并生产出一种新的能以人类智能相似的方式作出反应的智能机器。

《Artificial Intelligence A New Synthesis》 作者：Nils J，Nilson 1999，机械工业出版社， 英文，扫描版

Alphafold2-Pytorch（WIP） 要最终成为一个非官方的工作Pytorch实施 ，令人叹为观止的注意网络解决CASP14。 随着体系结构的更多细节发布，将逐步实施。 复制完成后，我打算将所有可用的氨基酸序列在计算机上折叠起来，并作为学术洪流发布，以供进一步科学使用。 如果您对复制工作感兴趣，请在此#alphafold 安装 $ pip install alphafold2-pytorch 用法 像Alphafold-1一样预测分布图，但要注意 import torch from alphafold2_pytorch import Alphafold2 from alphafold2_pytorch . utils import MDScaling , center_distogram_torch model = Alphafold2 ( dim = 256 ,

tegrastats_parser 一种简单的python算法，用于运行Tegrastats，然后从获得的带有时间戳的日志文件中解析数据。 命令行选项： --interval，-i（type = int，默认= 1000，help ='积分器的记录间隔，以毫秒为单位'） --log_file，-f（类型=字符串，默\u8ba4='output_log.txt'，help ='积分器数据的日志文件名'） --only_parse，-p（help ='在不运行tegrastats的情况下解析tegrastats日志文件'） --graph，-g（help ='从已解析的statstats数据绘制一些有用的图形'） 使用情况不生成图 python main.py --interval --log_file

deep-finance ： deep-finance深度学习 数据集 任务 描述 股票走势预测 通过推文和历史股价预测股票走势的综合数据集。 股票风险预测 标普500公司的电话会议数据集。 财务句子边界检测 FinSBD-2019数据集包含已自动分段的财务文本，可用于财务句子边界检测。 财务句子边界检测 Financial Phrasebank数据集包含4845个英语句子，这些句子是从LexisNexis数据库中发现的财经新闻中随机选择的。 财务问题解答 财务质量检查数据集是通过在2009年至2017年期间在“投资”主题下抓取Stack交换帖子来构建的。 财务情绪分析 FiQA SA数据集包括两种类型的论述：财经新闻头条和财经微博，以及带有手动注释的目标实体，情感评分和方面。 深度学习在股票市场预测中的应用：最新进展。 arxiv2020。 姜伟伟 个性化的所有人指标：具有股票嵌入功能的

This book highlights state-of-the-art research on big data and the Internet of Things (IoT), along with related areas to ensure efficient and Internet-compatible IoT systems. It not only discusses big data security and privacy challenges, but also energy-efficient approaches to improving virtual machine placement in cloud computing environments. Big data and the Internet of Things (IoT) are ultimately two sides of the same coin, yet extracting, analyzing and managing IoT data poses a serious challenge. Accordingly, proper analytics infrastructures/platforms should be used to analyze IoT data. Information technology (IT) allows people to upload, retrieve, store and collect information, which ultimately forms big data. The use of big data analytics has grown tremendously in just the past few years. At the same time, the IoT has entered the public consciousness, sparking people’s imaginations as to what a fully connected world can offer. Further, the book discusses the analysis of real-time big data to derive actionable intelligence in enterprise applications in several domains, such as in industry and agriculture. It explores possible automated solutions in daily life, including structures for smart cities and automated home systems based on IoT technology, as well as health care systems that manage large amounts of data (big data) to improve clinical decisions. The book addresses the security and privacy of the IoT and big data technologies, while also revealing the impact of IoT technologies on several scenarios in smart cities design. Intended as a comprehensive introduction, it offers in-depth analysis and provides scientists, engineers and professionals the latest techniques, frameworks and strategies used in IoT and big data technologies. . Read more... Abstract: This book highlights state-of-the-art research on big data and the Internet of Things (IoT), along with related areas to ensure efficient and Internet-compatible IoT systems. It not only discusses big data security and privacy challenges, but also energy-efficient approaches to improving virtual machine placement in cloud computing environments. Big data and the Internet of Things (IoT) are ultimately two sides of the same coin, yet extracting, analyzing and managing IoT data poses a serious challenge. Accordingly, proper analytics infrastructures/platforms should be used to analyze IoT data. Information technology (IT) allows people to upload, retrieve, store and collect information, which ultimately forms big data. The use of big data analytics has grown tremendously in just the past few years. At the same time, the IoT has entered the public consciousness, sparking people’s imaginations as to what a fully connected world can offer. Further, the book discusses the analysis of real-time big data to derive actionable intelligence in enterprise applications in several domains, such as in industry and agriculture. It explores possible automated solutions in daily life, including structures for smart cities and automated home systems based on IoT technology, as well as health care systems that manage large amounts of data (big data) to improve clinical decisions. The book addresses the security and privacy of the IoT and big data technologies, while also revealing the impact of IoT technologies on several scenarios in smart cities design. Intended as a comprehensive introduction, it offers in-depth analysis and provides scientists, engineers and professionals the latest techniques, frameworks and strategies used in IoT and big data technologies.

综合数据挖掘开源平台，性能非常好，功能包括：Classification: Support Vector Machines, Decision Trees, AdaBoost, Gradient Boosting, Random Forest, Logistic Regression, Neural Networks, RBF Networks, Maximum Entropy Classifier, KNN, Naïve Bayesian, Fisher/Linear/Quadratic/Regularized Discriminant Analysis. Regression: Support Vector Regression, Gaussian Process, Regression Trees, Gradient Boosting, Random Forest, RBF Networks, OLS, LASSO, ElasticNet, Ridge Regression. Feature Selection: Genetic Algorithm based Feature