Skip to content
프로젝트 카테고리

머신러닝 · GitHub

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

유용한 GitHub 프로젝트

12,832 프로젝트

xla

openxla

4,681스타+1in 24h
xla preview

GPU, CPU 및 머신러닝 가속기를 위한 머신러닝 컴파일러

머신러닝C++Apache-2.0GitHub

LMFlow

OptimalScale

8,483스타+1in 24h
LMFlow preview

대규모 기반 모델의 파인튜닝과 추론을 위한 확장 가능한 툴킷입니다. 모두를 위한 대규모 모델.

  • LoRA LoRA is a parameter-efficient finetuning algorithm and is more efficient than full finetuning. Check out finetuning-lora for more details.
  • FlashAttention LMFlow supports both FlashAttention-1 and the latest FlashAttention-2. Check out flash_attention for more details.
머신러닝PythonApache-2.0GitHub

optuna

optuna

15,071스타+1in 24h
optuna preview

하이퍼파라미터 최적화 프레임워크

  • Handle a wide variety of tasks with a simple installation that has few requirements.
  • Define search spaces using familiar Python syntax including conditionals and loops.

whatsmybitrate

oren-cohen

33스타+1in 24h
whatsmybitrate preview

Whatsmybitrate analyzes audio files for quality metrics such as bit rate, frequency, and codec type in bulk. It also generates spectrograms for visual representation of the audio spectrum. It supports a variety of audio formats, including MP3, FLAC, WAV, AAC, M4A, and more.

  • Detailed Quality Analysis: Reports codec, sample rate, stated bit rate, and more.
  • Perceptual Quality Estimation: Estimates the equivalent bitrate (e.g., 128, 192, 256, 320 kbps) based on spectral frequency cutoffs.

owl

owlbarn

1,359스타+1in 24h
owl preview

Owl - OCaml Scientific Computing @ https://ocaml.xyz

Oxen

Oxen-AI

1,211스타+1in 24h
Oxen preview

Lightning fast data version control system for large repositories of data. Feels like git, pushes and pulls like oxen.

  • 🔥 Fast (efficient indexing and syncing of data)
  • 🧠 Easy to learn (same commands as git)
머신러닝RustApache-2.0GitHub

Paddle

PaddlePaddle

24,149스타+1in 24h

병렬 분산 딥러닝: 산업 현장에서 탄생한 머신러닝 프레임워크(『飞桨』 핵심 프레임워크로, 딥러닝 및 머신러닝을 위한 고성능 단일 머신·분산 학습과 크로스 플랫폼 배포 지원)

머신러닝C++Apache-2.0GitHub

what-if-tool

PAIR-code

1,029스타+1in 24h
what-if-tool preview

Source code/webpage/demos for the What-If Tool

  • For classification models, this includes inferred label, confidence of inferred label, and inference correctness.
  • For regression models, this includes inferred score and amount of error (including absolute or squared error) in the inference.
머신러닝HTMLApache-2.0GitHub

diffrax

patrick-kidger

2,130스타+1in 24h

JAX용 수치 미분방정식 솔버입니다. 자동 미분과 GPU를 지원합니다. https://docs.kidger.site/diffrax/

머신러닝PythonApache-2.0GitHub

signatory

patrick-kidger

316스타+1in 24h

Differentiable computations of the signature and logsignature transforms, on both CPU and GPU. (ICLR 2021)

머신러닝C++Apache-2.0GitHub

NeuralFoil

peterdsharpe

510스타+1in 24h
NeuralFoil preview

NeuralFoil is a practical airfoil aerodynamics analysis tool using physics-informed machine learning, exposed to end-users in pure Python/NumPy.

  • Post-stall aerodynamics (i.e., truly 360 degree range of $\alpha$). This is useful for applications like wind turbine blades or propeller roots, where the airfoil may be operating at high angles of attack.
  • Control surface deflections. Currently only trailing-edge control surface deflections are supported in AeroSandbox's NeuralFoil interface.

adaptdl

petuum

460스타+1in 24h

Resource-adaptive cluster scheduler for deep learning training.

머신러닝PythonApache-2.0GitHub

DDColor

piddnad

1,521스타+1in 24h
DDColor preview

[ICCV 2023] DDColor: Towards Photo-Realistic Image Colorization via Dual Decoders

머신러닝PythonApache-2.0GitHub

pie

pie-project

245스타+1in 24h
pie preview

A programmable system for high-performance model serving

머신러닝RustApache-2.0GitHub

gensim

piskvorky

16,518스타+1in 24h
gensim preview

사람을 위한 토픽 모델링

  • All algorithms are memory-independent w.r.t. the corpus size (can process input larger than RAM, streamed, out-of-core),
  • easy to plug in your own input corpus/datastream (trivial streaming API)
머신러닝PythonLGPL-2.1GitHub