Open AlexeyAB opened 3 years ago
Hi @AlexeyAB, for yolov4-csp-x-swish.cfg at 640x640, you state APsmall is 0.35798. From the YOLOv4 paper, at 608x608 res APsmall is 0.267. Does this suggest that yolov4-csp-x-swish is better than yolov4 at detecting small objects?
@amish25 Hi, Yes, at least if you use 640x640 or higher for yolov4-csp-x-swish.cfg then it is better for small objects than 608x608 for yolov4.cfg.
yolov4-csp-x-swish.cfg
was validated on Pytorch, so I will validate it on Darknet too.
Hi @AlexeyAB,
Does Open-CV DNN support?
yolov4-p6 ? yolov4-csp-x-swish ? yolov4x-mish ?
Thanks
Hi @AlexeyAB,
Does Open-CV DNN support?
yolov4-p6 ? yolov4-csp-x-swish ? yolov4x-mish ?
Thanks
Curious to know the answer to this also.
Apart from the activation function have you done any other changes in cfg of yolov4-csp-swish? What are the key factors in which it's performing well compared to yolov4-mish & csp? @AlexeyAB
I have done inference on images & yolov4swish is detecting more objects with high confidence.
Yolov4x-mish
Yolov4-csp-swish
Apart from the activation function have you done any other changes in cfg of yolov4-csp-swish? What are the key factors in which it's performing well compared to yolov4-mish & csp? @AlexeyAB
I have done inference on images & yolov4swish is detecting more objects with high confidence.
Yolov4x-mish
Yolov4-csp-swish
@AlexeyAB I'm also curious to know the key factors.
It was trained with representation layer on Pytorch, and then these layers were fused to conv.
@AlexeyAB I tried swish on custom data performance of the swish model is far better than mish model. specially for detecting small objects (map of both mish & csp-swish model same is same). I have one question what is ema_alpha? when training of yolov4-csp-swish is completed ,we will get ema.weight. can you explain how should we tweak & what's purpose of this
yolov4-csp-x-swish.cfg - 640x640 - 69.9% mAP@0.5 (51.5% AP@0.5:0.95) - 23(R) FPS / 50(V) FPS - 221 BFlops (110 FMA) - 381 MB: yolov4-csp-x-swish.weights
yolov4-csp-swish.cfg - 640x640 - 68.7% mAP@0.5 (50.0% AP@0.5:0.95) - 70(V) FPS - 120 (60 FMA) - 202 MB: yolov4-csp-swish.weights
For Training - change these lines before each of 3
[yolo]
-layers: https://github.com/AlexeyAB/darknet/blob/1be96802a030ae2216c7e19b7523e1e2f0948aaf/cfg/yolov4-csp-x-swish.cfg#L1533-L1534filters=<(5 + num_classes) x 3>
activation=logistic
- for training and detection by using Darknet: https://github.com/AlexeyAB/darknetactivation=linear
- for training and detection by using Pytorch YOLOR: https://github.com/WongKinYiu/yolor