YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

Open standard for machine learning interoperability

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

Setup and customize deep learning environment in seconds.

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

PyTorch ,ONNX and TensorRT implementation of YOLOv4

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

Effortless data labeling with AI support from Segment Anything and other awesome models.

DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥

Sparsity-aware deep learning inference runtime for CPUs

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

OpenMMLab Model Deployment Framework

🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools

Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2), MobileSAM!!

Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、reg…

QualityScaler - image/video AI upscaler app