Skip to content
Categorías de proyectos

Aprendizaje automático · GitHub

Explora herramientas para entrenar, evaluar y ejecutar modelos, y compara el interés de la comunidad.

Proyectos útiles de GitHub

12,809 proyectos
462estrellas

Pytorch、Scikit-learn实现多种分类方法,包括逻辑回归(Logistic Regression)、多层感知机(MLP)、支持向量机(SVM)、K近邻(KNN)、CNN、RNN,极简代码适合新手小白入门,附英文实验报告(ACM模板)

pyedmine

ZhijieXiong

85estrellas
pyedmine preview

A library of algorithms for reproducing knowledge tracing, cognitive diagnosis, exercise recommendation and learning path recommendation models.

854estrellas
awesome-machine-learning-resources preview

😎 A curated list of awesome lists across all machine learning topics. | 机器学习/深度学习/人工智能一切主题 (学习范式/任务/应用/模型/道德/交叉学科/数据集/框架/教程) 的资源列表汇总。

imbalanced-ensemble

ZhiningLiu1998

428estrellas
imbalanced-ensemble preview

[NeurIPS'25]🛠️Class-imbalanced Ensemble Learning Toolbox. | 类别不平衡/长尾机器学习库

  • 🧑‍💻 Ease-of-use: Unified user-friendly scikit-learn-style APIs.
  • 📒 Documentation: Detailed documentation and examples.

yolort

zhiqwang

730estrellas
yolort preview

yolort is a runtime stack for yolov5 on specialized accelerators such as tensorrt, libtorch, onnxruntime, tvm and ncnn.

RNNSharp

zhongkaifu

285estrellas
RNNSharp preview

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.

  • Tokyo - NNP - S_LOCATION
  • New - NNP - B_LOCATION

Seq2SeqSharp

zhongkaifu

214estrellas

Seq2SeqSharp is a tensor based fast & flexible deep neural network framework written by .NET (C#). It has many highlighted features, such as automatic differentiation, different network types (Transformer, LSTM, BiLSTM and so on), multi-GPUs supported, cross-platforms (Windows, Linux, MacOS), multimodal model for text and images and so on.