YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )

High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀

🔥🔥🔥 专注于YOLOv5，YOLOv7、YOLOv8、YOLOv9改进模型，Support to improve backbone, neck, head, loss, IoU, NMS and other modules🚀

Improvement on Object Detection by Self-Attention and Receptive Field Expansion; YOLOv4s(scaled-yolo) with Vision Transformer.

使用Colab運行PyTorch ScaledYOLOv4範例，包括COCO資料集預訓練參數及自定義資料集。

A Tensorflow2.x implementation of Scaled-YOLOv4 as described in Scaled-YOLOv4: Scaling Cross Stage Partial Network

Trained a deep neural network on official SAR (Search and Rescue) dataset for drones on the IPSAR (Image Processing for Search and Rescue) project. Scaled YOLOv4 has been employed in the model that detects humans in images, which will be used on drones in missing person cases in terrain that cannot be searched by humans.

This is implementation of YOLOv4,YOLOv4-relu,YOLOv4-tiny,YOLOv4-tiny-3l,Scaled-YOLOv4 and INT8 Quantization in OpenVINO2021.3

Scaled-YOLOv4: Scaling Cross Stage Partial Network is yolov4-csp. Actual produces erros on CPU so there is a bit modification. There is a small code to build API for newcomers.

Training and Evaluating Scaled Yolo v4 on custom dataset

🔥🔥🔥 Scaled-YOLOv4训练自己的数据集详细教程PDF，关于paper解读请联系小编获取PDF文档