Official YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

• paper: https://arxiv.org/abs/2207.02696

• source code - Pytorch (use to reproduce results): https://github.com/WongKinYiu/yolov7

• darknet_ros: https://github.com/Ar-Ray-code/darknet_ros_fp16

YOLOv7:

• cfg: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov7.cfg
• weights: https://github.com/AlexeyAB/darknet/releases/download/yolov4/yolov7.weights
• weights for fine-tuning: https://github.com/AlexeyAB/darknet/releases/download/yolov4/yolov7.conv.132

YOLOv7x:

• cfg: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov7x.cfg
• weights: https://github.com/AlexeyAB/darknet/releases/download/yolov4/yolov7x.weights
• weights for fine-tuning: https://github.com/AlexeyAB/darknet/releases/download/yolov4/yolov7x.conv.147

YOLOv7-tiny-leaky-relu:

Darknet cfg/weights file - currently tested for inference only:

• cfg: https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov7-tiny.cfg
• weights: https://github.com/AlexeyAB/darknet/releases/download/yolov4/yolov7-tiny.weights
• weights for fine-tuning: https://github.com/AlexeyAB/darknet/releases/download/yolov4/yolov7-tiny.conv.87

Test FPS:

• without NMS: darknet.exe detector demo cfg/coco.data cfg/yolov7-tiny.cfg yolov7-tiny.weights test.mp4 -benchmark

• with NMS: darknet.exe detector demo cfg/coco.data cfg/yolov7-tiny.cfg yolov7-tiny.weights test.mp4 -dont_show