47,133 repositories indexed
1–24 of 182 · Most stars
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched
Visualizer for neural network, deep learning and machine learning models
OpenMMLab Detection Toolbox and Benchmark
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
Label Studio is a multi-type data labeling and annotation tool with standardized output format
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
ncnn is a high-performance neural network inference framework optimized for the mobile platform
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
Open standard for machine learning interoperability
The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Fast and accurate AI powered file content types detection
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Machine learning, in numpy
Image annotation with Python. Supports polygon, rectangle, circle, line, point, and AI-assisted annotation.
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.