无人机小目标

Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

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

Multi-backbone, Prune, Quantization, KD

OpenMMLab Detection Toolbox and Benchmark

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet), Pruning (EagleEye) and Quantization (MQBench) Compression Tool Box.

SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks from research to industrial applications.

A Pytorch implementation of SMU: SMOOTH ACTIVATION FUNCTION FOR DEEP NETWORKS USING SMOOTHING MAXIMUM TECHNIQUE

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

YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite

MicroPython - a lean and efficient Python implementation for microcontrollers and constrained systems

Arduino library for the DHT series temperature&humidity sensors

CV backbones including GhostNet, TinyNet and TNT, developed by Huawei Noah's Ark Lab.

Grove_Temper_Humidity based on TH02

Face recognition and live estimation on Raspberry Pi 4B with average FPS around 20 and 2800+ faces loaded.

Yolov5 distillation training | Yolov5知识蒸馏训练，支持训练自己的数据

YOLOv3 in PyTorch > ONNX > CoreML > TFLite

机器学习算法经典案例

Model Compression—YOLOv3 with multi lightweight backbones(ShuffleNetV2 HuaWei GhostNet), attention, prune and quantization