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

12,806 プロジェクト

split_raster

cuicaihao

27スター
split_raster preview

Split Raster is an open-source and highly versatile Python package designed to easily break down large images into smaller, more manageable tiles. While the package is particularly useful for deep learning and computer vision tasks, it can be applied to a wide range of applications.

機械学習Jupyter NotebookMITGitHub
589スター
Illumination-Adaptive-Transformer preview

🌕 [BMVC 2022] You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction. SOTA for low light enhancement, 0.004 seconds try this for pre-processing.

機械学習PythonApache-2.0GitHub
917スター
pytorch_face_landmark preview

Fast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.

awesome-llms-fine-tuning

Curated-Awesome-Lists

534スター

Explore a comprehensive collection of resources, tutorials, papers, tools, and best practices for fine-tuning Large Language Models (LLMs). Perfect for ML practitioners and researchers!

GPT-Awesome-List-Generator

Curated-Awesome-Lists

44スター

A powerful and automatic awesome list generator leveraging GPT models. Enter your keyword and its description to get a comprehensive list of resources in Markdown format

LTSF-Linear

cure-lab

2,534スター
LTSF-Linear preview

[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"

  • Add a benchmark for long-term time series forecasting.
  • Support both Univariate and Multivariate long-term time series forecasting.
機械学習PythonApache-2.0GitHub

MagicDrive

cure-lab

1,169スター
MagicDrive preview

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

機械学習PythonApache-2.0GitHub

PnPInversion

cure-lab

417スター
PnPInversion preview

[ICLR2024] Official repo for paper "PnP Inversion: Boosting Diffusion-based Editing with 3 Lines of Code"

機械学習Jupyter NotebookGitHub

ladder

CuriousAI

518スター

Ladder network is a deep learning algorithm that combines supervised and unsupervised learning

1,081スター
Deep-Learning-For-Hackers preview

Machine Learning tutorials with TensorFlow 2 and Keras in Python (Jupyter notebooks included) - (LSTMs, Hyperameter tuning, Data preprocessing, Bias-variance tradeoff, Anomaly Detection, Autoencoders, Time Series Forecasting, Object Detection, Sentiment Analysis, Intent Recognition with BERT)

機械学習Jupyter NotebookMITGitHub
2,517スター
Getting-Things-Done-with-Pytorch preview

Jupyter Notebook tutorials on solving real-world problems with Machine Learning & Deep Learning using PyTorch. Topics: Face detection with Detectron 2, Time Series anomaly detection with LSTM Autoencoders, Object Detection with YOLO v5, Build your first Neural Network, Time Series forecasting for Coronavirus daily cases, Sentiment Analysis with BER

機械学習Jupyter NotebookApache-2.0GitHub

extractnet

currentslab

302スター

A fork of Dragnet that also extract author, headline, date, keywords from context, as well as built in metadata extraction all in one package

BraTs

cv-lee

275スター

PyTorch & Keras implementation for BraTs (Brain Tumor Segmentation)

sussyfinder

Cvar1984

77スター
sussyfinder preview

A self-contained PHP webshell scanner that uses token analysis, hash filtering, machine learning, and entropy-based anomaly detection to hunt for backdoors, supports legacy PHP 4.3 to the very recent PHP 8, no dependencies required

  • Token-based detection – scans PHP tokens for known obfuscation, shell execution, file I/O, and credential-related functions (method names like $pdo->exec() and text inside strings/comments are ignored)
  • Structural detection – catches what name matching can't: calls through variables or superglobals ($_GET['a']($_GET['b'])), function names hidden in strings ('ba'.'se64_decode', "\x73ystem"), preg_replace with /e, backtick shell execution, payloads after __halt_compiler(), and giant single-line blobs