Skip to content
プロジェクトカテゴリ

機械学習 · GitHub

モデルの学習・評価・推論に使うフレームワークを探し、注目度を比較できます。

便利なGitHubプロジェクト

12,808 プロジェクト

shapenet

justusschock

348スター

PyTorch implementation of "Super-Realtime Facial Landmark Detection and Shape Fitting by Deep Regression of Shape Model Parameters" predicting facial landmarks with up to 400 FPS

機械学習PythonAGPL-3.0GitHub

nanoeuler

JustVugg

127スター

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

robert

jvalegre

58スター

Automated machine learning protocols that start from CSV databases of descriptors or SMILES and produce publication-quality results in Chemistry studies with only one command line.

670スター
Gaussian_YOLOv3 preview

Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Driving (ICCV, 2019)

234スター

This is the repository for the collection of Deep Learning for Traffic Prediction Problems.

機械学習Jupyter NotebookMITGitHub
231スター

PyTorch implementation of FedNova (NeurIPS 2020), and a class of federated learning algorithms, including FedAvg, FedProx.

mc-cnn

jzbontar

729スター
mc-cnn preview

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

機械学習CudaBSD-2-ClauseGitHub

PercepNet

jzi040941

372スター

Unofficial implementation of PercepNet: A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech

機械学習C++BSD-3-ClauseGitHub
845スター

An end-to-end Data Scientist

  • 🤖 Adaptive Multi-Agent Workflow: Iterative planning, execution, validation, and reflection
  • 📋 Intelligent Planning: Creates comprehensive analysis plans before starting work
56スター

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and target-discovery knowledge graphs.

karpathy

K-Dense-AI

1,582スター

An agentic Machine Learning Engineer

  • Modal sandbox integration - Choose any type of compute you want
  • K-Dense Web features - We might make some features from K-Dense Web available here based on interest