47,133 repositories indexed
1–14 of 14 · 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
Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.
TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
Fit interpretable models. Explain blackbox machine learning.
AI digital-human talking-head videos from one photo: Renoise MCP generation + 5 editing styles + 48 creator-grade packaging components. Agent skill for Claude Code / Codex / OpenClaw / WorkBuddy …
Official PyTorch implementation of VisionHOPE: Visual Backbones as Self-Modifying Learning Systems.
Deep Pink is a chess AI that learns to play chess using deep learning.
Build fully-functioning computer vision models with PyTorch
A hyperparameter optimization framework, inspired by Optuna.
A collection of tasks to probe the effectiveness of protein sequence representations in modeling aspects of protein design
TranslatedOpenMinutes · Voice recorder workbench: import · transcription · AI categorization · search and review of MemoTalk S1 recordings (open-source implementation of Floatboat Workbench)
Towards Reverse-Engineering Black-Box Neural Networks, ICLR'18
Workbench for practical machine learning in Ruby.