Skip to content
프로젝트 카테고리

머신러닝 · GitHub

모델 학습, 평가, 추론 프레임워크를 찾고 커뮤니티의 관심도를 비교하세요.

유용한 GitHub 프로젝트

12,809 프로젝트

vqvae

MishaLaskin

914스타

A pytorch implementation of the vector quantized variational autoencoder (https://arxiv.org/abs/1711.00937)

머신러닝Jupyter NotebookGitHub

MIST

mist-medical

58스타
MIST preview

MIST: A simple and scalable end-to-end framework for 3D medical imaging segmentation.

  • Automatic configuration — analysis step determines target spacing, patch size, normalization, and foreground cropping from your data
  • Five-fold cross-validation by default, with custom fold assignment support
머신러닝PythonApache-2.0GitHub

mcunet

mit-han-lab

724스타
mcunet preview

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

tinyengine

mit-han-lab

969스타
tinyengine preview

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

torchsparse

mit-han-lab

1,476스타
torchsparse preview

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

hydra-zen

mit-ll-responsible-ai

479스타

Create powerful Hydra applications without the yaml files and boilerplate code.

rlx-models

MIT-RLX

40스타
rlx-models preview

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

  • Qwen3-TTS - VoiceClone API, progressive streaming (StreamMode::Progressive), duplex voice chat (Whisper + Qwen3 LM), CustomVoice presets, optional incremental-decode / speculative-decode features
  • Voxtral-4B-TTS - Tekken tokenizer, compiled Ministral LM, reference WAV clone after native encoder training
1,405스타
Speech-Emotion-Analyzer preview

The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

머신러닝Jupyter NotebookMITGitHub

ssai-cnn

mitmul

262스타

Semantic Segmentation for Aerial / Satellite Images with Convolutional Neural Networks including an unofficial implementation of Volodymyr Mnih's methods

env-doctor

mitulgarg

174스타
env-doctor preview

Diagnose and Fix CUDA / GPU environments compatibility issues locally, in Docker, and CI/CD. CLI + MCP server available.

  • One-Command Diagnosis - Check compatibility: GPU Driver → CUDA Toolkit → cuDNN → PyTorch/TensorFlow/JAX
  • Compute Capability Check - Detect GPU architecture mismatches — catches why torch.cuda.is_available() returns False on new GPUs (e.g. Blackwell) even when driver and CUDA are healthy