47,133 repositories indexed
1–24 of 27 · Most stars
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Minimal reproduction of DeepSeek R1-Zero
Cleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Minimal and clean examples of machine learning algorithms implementations
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
A unified framework for machine learning with time series
Open-source, low-code AutoML platform for Python. PyCaret 4.0: sklearn-native engine + React control plane.
A python library for user-friendly forecasting and anomaly detection on time series.
Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)
POT : Python Optimal Transport
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
PyTorch to Keras model convertor
A machine learning tool that ranks strings based on their relevance for malware analysis.
斑海豹 — Phocinae-Largha-150M-v1: a 144.3M bilingual decision model. Tiny model. Big decisions. 小海豹，大决断。
Create adversarial attacks against machine learning Windows malware detectors
Trading Environment(OpenAI Gym) + PPO(TensorForce)
SABER enables identity-resolved quantification of multi-animal social behavior
基于 PatchCore 的工业异常检测项目，研究 layer2/layer3 分数融合、敏感性引导收缩与风险受控门控，并提供 Streamlit 工程化 Demo。
PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers
Effects of packers on machine-learning-based malware classifiers that use only static analysis
Docker image gathering packers and tools for making datasets of packed executables and training machine learning models for packing detection
🛡️ Free AI that blocks hackers while you sleep. Runs on cheap hardware. When someone in Tokyo gets attacked, you're protected in 30 seconds. No fees. No experts needed. Just protection. One node's detection → everyone's protection.
Cryptographic Dataset Generation & Modelling Framework