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

12,832 proyectos
1,418estrellas
Arraymancer preview

A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends

  • Basic math operations generalized to tensors (sin, cos, ...)
  • Matrix algebra primitives: Matrix-Matrix, Matrix-Vector multiplication.

laser

mratsim

295estrellas

The HPC toolbox: fused matrix multiplication, convolution, data-parallel strided tensor primitives, OpenMP facilities, SIMD, JIT Assembler, CPU detection, state-of-the-art vectorized BLAS for floats and integers

pytorch-kaldi

mravanelli

2,408estrellas

pytorch-kaldi es un proyecto para desarrollar sistemas híbridos de reconocimiento de voz DNN/RNN de última generación. pytorch gestiona la parte DNN, mientras que la extracción de características, el cálculo de etiquetas y la decodificación se realizan con el kit de herramientas kaldi.

ModelsGenesis

MrGiovanni

796estrellas
ModelsGenesis preview

[MICCAI 2019 Young Scientist Award] [MedIA Best Paper Award] Models Genesis: self-supervised pre-training for 3D medical images. Learns transferable representations from unlabeled CT and MRI volumes, then fine-tunes for downstream segmentation and classification. Keras and PyTorch weights included.

GPTX

MrHacker-X

31estrellas

GPTX: AI chatbot for natural language conversations

  • 💬 - Streamed answers - Chat Completions stream token-by-token into the terminal - no long silent waits
  • 🧠 - Modern chat models - gpt-4o-mini default; any OpenAI chat model via config
427estrellas

Contains the online course about Data Science, Machine Learning, Programming Language, Operating System, Mechanial Engineering, Mathematics and Robotics provided by Coursera, Udacity, Linkedin Learning, Udemy and edX.

250estrellas

房价预测完整项目:1.爬取链家网数据 2.处理后,用sklearn中几个逻辑回归机器学习模型和keras神经网络搭建模型预测房价 最终结果神经网络效果更好,R^2值0.75左右

948estrellas
calculate-flops.pytorch preview

The calflops is designed to calculate FLOPs、MACs and Parameters in all various neural networks, such as Linear、 CNN、 RNN、 GCN、Transformer(Bert、LlaMA etc Large Language Model)