https://github.com/bestsongc/yolov8-deepsort-streamlit • Science 10%

YOLOv8 Object Tracking and Counting using PyTorch, OpenCV and DeepSORT, deployed on Streamlit.

https://github.com/bestsongc/yolov7_obb • Science 10%

YOLOv7+KLD

https://github.com/bestsongc/yolov5_obb • Science 10%

yolov5 + csl_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于yolov5的旋转目标检测

https://github.com/bestsongc/yolov5-distillation-5.0 • Science 10%

yolov5 5.0 version distillation || yolov5 5.0版本知识蒸馏，yolov5l >> yolov5s

https://github.com/bestsongc/yolov5-odconvnext • Science 10%

YOLOv5-ODConvNeXt is an improved version of YOLOv5 for ship detection on drone-captured images.

https://github.com/bestsongc/yolov5-multibackbone-compression • Science 10%

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantization (MQBench) and Deployment (TensorRT, ncnn) Compression Tool Box.

https://github.com/bestsongc/yolov5-6.0-distillation-master • Science 10%

目前，主流蒸馏模型采用方法为KD蒸馏、LD蒸馏或feature蒸馏，然蒸馏开源项目也较少。为此，我写了一份基于yolov5框架的蒸馏，并会有实验附带。该方法将会不断尝试论文方法，不断探索更有效的蒸馏方法。

https://github.com/bestsongc/micronet • Science 10%

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、regula

https://github.com/bestsongc/mobilesam • Science 10%

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

https://github.com/bestsongc/lite.ai.toolkit • Science 10%

🛠 A lite C++ toolkit of awesome AI models with ONNXRuntime, NCNN, MNN and TNN. YOLOv5, YOLOX, YOLOP, YOLOv6, YOLOR, MODNet, YOLOX, YOLOv7, YOLOv8. MNN, NCNN, TNN, ONNXRuntime.

https://github.com/bestsongc/json2yolo • Science 10%

Convert JSON annotations into YOLO format.

https://github.com/bestsongc/fire-detection-from-images • Science 10%

Detect fire in images using neural nets

https://github.com/bestsongc/faceid--yolov5.arcface • Science 10%

ONNX implementation of YOLOv5 and Siamese Network (ResNet100) with ArcFace loss for Face Detection and Recognition

https://github.com/bestsongc/bytetrack_yolov7 • Science 10%

https://github.com/bestsongc/bot-sort • Science 10%

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

https://github.com/bestsongc/awesome_lightweight_networks • Science 10%

The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

https://github.com/betalab-team/ita-domes • Science 26%

A national bottom-up energy model for the Italian residential building stock

https://github.com/bethan-mallabar-rimmer/bethan-mallabar-rimmer • Science 13%

https://github.com/bethan-mallabar-rimmer/crc_irm • Science 26%

https://github.com/bethgelab/onebench • Science 26%

[ACL'25] The official code for "ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities"