Nguyen Mau Dzung
Nguyen Mau Dzung
Hi @AlexeyAB , Thanks for your comments. I'm trying to improve its performance before writing up a comparison. Actually, the IoU calculation for polygons is very expensive and different from...
Thank you @AlexeyAB I haven't used CIoU or GIoU loss yet, I'm trying to apply them to the loss function. I'm also trying to speed up the non-max-suppression step in...
Thank you so much @fsaxen
Hi @AlexeyAB I have added the implementation of GIoU loss for rotated boxes. I'm running experiments on it to test its performance. Can you please share with me the weights...
Thank you @AlexeyAB for your quick response. I have 1 more question. Did you apply weights `noobj_scale` and `obj_scale` for the `loss_obj` as YOLOv3? Your answer can help me save...
I ran the experiments on _6k_ samples with MSE loss and evaluated on _1.4k_ samples. The mAP for Complex-YOLOv3 and Complex-YOLOv4 are 0.90 and 0.89 corresponding. I tried to visualize...
Hi @AlexeyAB > Do you use [email protected] or [email protected]? I evaluated with [email protected]. I'll use [email protected]>0.95 to evaluate the models. > Why is the mAP for Complex-YOLOv3 higher than for...
Hi @AlexeyAB I read the paper that you suggest and tried to implement it, but it could not run real-time and the method was proposed only for car detection. Hence,...
> Do you mean that Voxelization -> 3d convolution ndchw -> Conv2d is very slow (only ~25 FPS), so you replaced it with small resnet18 + FPN and it works...
Hi @yangjin07 I didn't do it. Please contribute to the repo if you made it. Thank you so much!