Open xjinai opened 3 years ago
@AlexeyAB For those of us like myself only familiar with YOLOv4.cfg and YOLOv4-tiny.cfg, what is YOLOv4-p5.cfg and YOLOv4-p6.cfg you've recently added? What would be the guideline we should use to determine which configuration to use on a project?
@xjinai @stephanecharette
For Detection - use the same as usual:
./darknet detector test cfg/coco.data cfg/yolov4-p5.cfg yolov4-p5.weights -ext_output dog.jpg
./darknet detector test cfg/coco.data cfg/yolov4-p6.cfg yolov4-p6.weights -ext_output dog.jpg
You can download pre-trained weights on COCO:
yolov4-p5.cfg
https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-p5.weightsyolov4-p6.cfg
https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-p6.weightsFor Training - change these lines before each of 3 for p5 (of 4 for p6) [yolo]
-layers:
https://github.com/AlexeyAB/darknet/blob/9a86fce494b1d82b774d36be76747fcb58f81aa4/cfg/yolov4-p5.cfg#L1810-L1811
filters=<(5 + num_classes) x 4>
activation=logistic
- for training and detection by using Darknet: https://github.com/AlexeyAB/darknet
activation=linear
- for training and detection by using Pytorch Scaled-YOLOv4 (CSP-branch): https://github.com/WongKinYiu/ScaledYOLOv4/tree/yolov4-csp
For training use pre-trained weights:
yolov4-p5.cfg
https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-p5.conv.232yolov4-p6.cfg
https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-p6.conv.289Currently Pytorch is more suitable for training on multiple-GPUs.
Accuracy - Speed:
Scaled-YOLOv4-P6 is slower, but +2% more accurate than YOLOR-P6 that is the best in terms of speed/accuracy for Waymo autonomous driving challenge: https://github.com/AlexeyAB/darknet/issues/7828
Speed and accuracy on COCO is validated by using Pytorch: https://github.com/WongKinYiu/ScaledYOLOv4/tree/yolov4-csp
Are YOLOv4-P5 (896x896) and YOLOv4-P6 (1280x1280) described in the Scaled-YOLOv4 paper supported? If so, could you point me to the cfg and pre-trained weights files for YOLOv4-P5 and YOLOv4-P6? If not, is it possible to add the support of those?