Alexey

@EtheneXiang > and i have another porblem, do you have tools to visualize the cfg. You can try: https://github.com/lutzroeder/netron

You have provided too little information. Also you didn't give source image for reproducing this issue. May be you use CSPResNeXt50-PANet-SPP and Yolov3 with different network resolution. Or you are...

@ekarabulut Try to run detection with flag `-thresh 0.1` `./darknet detector demo cfg/coco.data cfg/csresnext50-panet-spp-original-optimal.cfg csresnext50-panet-spp-original-optimal_final.weights sys6_day.mp4 -thresh 0.1` ---- > According to this result, Yolov3 inference still looks like better....

@WongKinYiu Did you use `darknet.exe detector calc_anchors data/obj.data -num_of_clusters 9 -width 608 -height 608` for recalculating anchors for `csresnext50-panet-spp-original-optimal.cfg` ? Did you change achors manually?

@glenn-jocher > I saw that the mosaic augmentation outperformed all of the rest in your readme tests, including more well known ones like cutmix. Yes. It seems: more parts of...

@glenn-jocher > Are you sure your Swish implementation was correct? Yes, Swish implementation is correct, since Swish improves accuracy for other models: EfficientNet, MixNet, PeleeNet, CSPPeleeNet, ... https://github.com/AlexeyAB/darknet/issues/3994#issuecomment-565692356 > but...

@ekarabulut Hi, Do the same thing: https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects

> CSPDarknet53 or CSPDarknet53-Elastic These models are Classifiers for ImageNet dataset. ---- Look at Detectors for MS COCO dataset: https://github.com/WongKinYiu/CrossStagePartialNetworks#ms-coco Or these models: https://github.com/WongKinYiu/CrossStagePartialNetworks/tree/master/in%20progress

We set the ground truth probability in proportion to the area occupied by each sample: https://github.com/AlexeyAB/darknet/blob/4ee3be7e68fb9c7eda5cc390e47e59f01e40dded/src/data.c#L1913-L1942 So if areas for: Car=10%, Table=20%, Cat=30%, Dog = 40%, then we set labels:...

@07hyx06 > Another question is, in EVALUATION.md I notice that when evaluate on KITTI, the argument absolute_depth is specified and the prediction is scaled by 256. There are no more...