PyTorch中的MeshCNN SIGGRAPH 2019 MeshCNN是用于3D三角形网格的通用深度神经网络,可用于诸如3D形状分类或分割之类的任务。 该框架包括直接应用于网格边缘的卷积,池化和解池层。 该代码由和在支持下编写。 入门 安装 克隆此仓库: git clone https://github.com/ranahanocka/MeshCNN.git cd MeshCNN 安装依赖项: 1.2版。 可选: 用于训练图。 通过新的conda环境conda env create -f environment.yml (创建一个名为meshcnn的环境) SHREC上的3D形状分类 下载数据集 bash ./scripts/shrec/get_data.sh 运行训练(如果使用conda env首先激活env,例如source activate meshcnn ) bash ./scripts/shrec/train.sh 要查看训练损失图,请在另一个终端中运行tensorboard --logdir runs并单击 。 运行测试并导出中间池网格: bas
2024-04-02 16:20:14 3.54MB machine-learning computer-graphics pytorch mesh
1
金融机器学习
2024-03-05 14:51:16 5.04MB JupyterNotebook
1
使用scikit-learn掌握机器学习-第二版 这是发行的的代码库。 它包含从头到尾完成本书所必需的所有支持项目文件。 关于这本书 本书探讨了各种机器学习模型,包括k最近邻,逻辑回归,朴素贝叶斯,k均值,决策树和人工神经网络。 它讨论了数据预处理,超参数优化和集成方法。 您将建立对文档进行分类,识别图像,检测广告等的系统。 您将学习使用scikit-learn的API从分类变量,文本和图像中提取功能; 评估模型性能; 并就如何改善模型的性能形成直觉。 说明和导航 所有代码都组织在文件夹中。 每个文件夹均以数字开头,后跟应用程序名称。 例如,Chapter02。 该代码将如下所示: Code words in text, database table names, folder names, filenames, file extensions, pathnames, dummy U
2024-02-17 17:49:07 2.77MB JupyterNotebook
1
Inside Java Virtual Machine(深入Java虚拟机),经典原著。
1
学习数据挖掘和机器学习的一本非常著名的书。是第二版。不太完美的地方是,本书是英文版。
2024-01-26 20:45:02 9.08MB 数据挖掘 data mining Morgan.Kaufmann
1
Mastering Machine Learning with Python in Six Steps - 1E (2017) Mastering Machine Learning with Python in Six Steps - 1E (2017)
2024-01-19 23:11:56 4.74MB Mastering Machine Learning Python
1
RetinaFace C ++重新实现源参考资源RetinaFace带有python代码。 模型转换工具MXNet2Caffe您需要自己添加一些层,并且在caffe中没有upsam RetinaFace C ++重新实现源参考资源RetinaFace用python代码提供在Insightface中。 模型转换工具MXNet2Caffe您需要自己添加一些图层,并且在caffe中没有上采样,您可以用反卷积代替,并且可能会有一点精度损失。 来自mobilenet25的原始模型参考,我已经对其进行了重新培训。 演示$ mkdir build $ cd build / $ cmake ../ $使您需要修改CmakeList文件中的依赖路径。 测速硬件:1080Ti test1:mod
2024-01-17 00:21:28 6.66MB C/C++ Machine Learning
1
使用 Java 8 实现 JVM 特性 元循环(Metacircular) mini-jvm on mini-jvm on hotspot. 可以在 mini-jvm 里运行 mini-jvm . $ java -jar jvm-core/target/mini-jvm.jar -jar jvm-core/target/mini-jvm.jar -jar test.jar # Hello World! 动机 尝试了解 JVM 原理, Learning by doing 纸上得来终觉浅, 实践 用简单的代码帮助 Javaer 理解 JVM 快速体验 [Macos 用户] Hello world brew tap guxingke/repo && brew install mini-jvm cat < HelloWorld.java public class HelloWorld
2024-01-16 23:07:42 1.31MB interpreter jvm8 Java
1
A step-by-step gentle journey through the mathematics of neural networks, and making your own using the Python computer language. Neural networks are a key element of deep learning and artificial intelligence, which today is capable of some truly impressive feats. Yet too few really understand how neural networks actually work. This guide will take you on a fun and unhurried journey, starting from very simple ideas, and gradually building up an understanding of how neural networks work. You won't need any mathematics beyond secondary school, and an accessible introduction to calculus is also included. The ambition of this guide is to make neural networks as accessible as possible to as many readers as possible - there are enough texts for advanced readers already! You'll learn to code in Python and make your own neural network, teaching it to recognise human handwritten numbers, and performing as well as professionally developed networks. Part 1 is about ideas. We introduce the mathematical ideas underlying the neural networks, gently with lots of illustrations and examples. Part 2 is practical. We introduce the popular and easy to learn Python programming language, and gradually builds up a neural network which can learn to recognise human handwritten numbers, easily getting it to perform as well as networks made by professionals. Part 3 extends these ideas further. We push the performance of our neural network to an industry leading 98% using only simple ideas and code, test the network on your own handwriting, take a privileged peek inside the mysterious mind of a neural network, and even get it all working on a Raspberry Pi. All the code in this has been tested to work on a Raspberry Pi Zero.
2024-01-13 11:04:46 4.97MB neural netwo machine lear
1
机器学习算法第二版 这是Packt发布的《 的代码库。 流行于数据科学和机器学习的算法 这本书是关于什么的? 机器学习以其强大而快速的大型数据集预测而获得了极大的普及。 但是,强大功能背后的真正力量是涉及大量统计分析的复杂算法,该算法搅动大型数据集并产生实质性见解。 本书涵盖以下激动人心的功能: 研究特征选择和特征工程过程 评估性能和误差权衡以进行线性回归 建立数据模型并使用不同类型的算法了解其工作方式 学习调整支持向量机(SVM)的参数 探索自然语言处理(NLP)和推荐系统的概念 如果您觉得这本书适合您,请立即获取! 说明和导航 所有代码都组织在文件夹中。 例如,Chapter02。 该代码将如下所示: from sklearn.svm import SVC from sklearn.model_selection import cross_val_score svc =
2023-12-15 16:31:18 97KB Python
1