Skip to content
项目分类

机器学习 · GitHub

发现模型训练、评估与推理框架,比较深度学习和机器学习项目的社区关注度。

实用 GitHub 项目

12,832 个项目
1,588星标+124小时
CS231n-2017-Summary preview

看完著名的斯坦福 CS231n 2017 课程的全部视频后,我决定总结整门课程,帮助自己记忆,也方便任何想了解这门课程的人阅读。部分讲座中的一些内容对我来说并不重要,因此略过了。

calvin

mees

1,006星标+124小时
calvin preview

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

MOTRv2

megvii-research

489星标+124小时

[CVPR2023] MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors

211星标+124小时

Plant Disease Detection is one of the mind-boggling issues when we talk about using Technology in Agriculture. Although researches have been done to detect whether a plant is healthy or diseased using Deep Learning and with the help of Neural Network, new techniques are still being discovered. For Fewer Data Classical Machine Learning Models are said to outstand given the data is pre-processed well. On the same theory here is my approach for Detecting whether a plant leaf is healthy or unhealthy by utilizing the classical Machine Learning Models, Pre-processing the Image Data. The data was fed to 7 Machine Learning Models with 10 fold cross-validation out of which Random Forest Classifier outperformed all the other models giving an accuracy of 97% on the test set.

机器学习Jupyter NotebookGitHub
1,380星标+124小时
deep-learning-from-scratch preview

《深度学习入门-基于Python的理论与实现》,包含源代码和高清PDF(带书签);慕课网imooc《深度学习之神经网络(CNN-RNN-GAN)算法原理-实战》;《菜菜的机器学习sklearn》

机器学习Jupyter NotebookGitHub

llama-cookbook

meta-llama

18,596星标+124小时

欢迎来到 Llama Cookbook!这是使用 Llama 构建应用的指南,涵盖推理、微调和 RAG 的入门方法。我们还将介绍如何使用 Llama 模型系列解决端到端问题,以及如何在各种提供商服务中使用这些模型。

机器学习Jupyter NotebookMITGitHub

gpt-fast

meta-pytorch

6,275星标+124小时

使用不到 1000 行 Python 实现简单高效、原生基于 PyTorch 的 Transformer 文本生成。

机器学习PythonBSD-3-ClauseGitHub

nnscaler

microsoft

138星标+124小时
nnscaler preview

nnScaler: Compiling DNN models for Parallel Training

  • Ease of Use: Only a few lines of code need to be changed to enable automated parallelization.
  • Pythonic: The parallelization output is in PyTorch code, making it easy for users to understand and convenient for further development or customization.
1,859星标+124小时
responsible-ai-toolbox preview

Responsible AI Toolbox 是一套工具,提供用于模型和数据探索与评估的用户界面及库,帮助更好地理解 AI 系统。这些界面和库支持 AI 系统的开发者及利益相关方以更负责任的方式开发和监控 AI,并采取更好的数据驱动行动。

机器学习TypeScriptMITGitHub

DeepLearning

Mikoto10032

17,904星标+124小时
DeepLearning preview

深度学习入门教程,优秀文章,Deep Learning Tutorial

机器学习Jupyter NotebookApache-2.0GitHub

gdrl

mimoralea

1,051星标+124小时

Grokking Deep Reinforcement Learning

机器学习Jupyter NotebookBSD-3-ClauseGitHub

model2vec

MinishLab

2,286星标+124小时

快速的最先进静态嵌入模型

  • State-of-the-Art Performance: Model2Vec models outperform any other static embeddings (such as GLoVe and BPEmb) by a large margin, as can be seen in our results.
  • Small: Model2Vec reduces the size of a Sentence Transformer model by a factor of up to 50. Our best model is just ~30 MB on disk, and our smallest model just ~8 MB (making it the smallest model on MTEB!).