AI-Hunter

For different number of classes?

1

Can it work for different number of classes? My class number = 2 Where I change in train_semseg.py? What is label_weights, the value of the similar to class number? Anyone...

Don't work for different dataset (custom data)?

10

When I use S3DIS dataset, it is working, but when I am using my own dataset, it is stuck at classifier.train()! What is the reason? is it normalization issue? I...

Anchors in yolov5?

1

@ifzhang @jadielam @cclauss @mgoldchild , Thank you very much for this awesome repository. I would like to know, why you don't use anchors in your config file (yolov5)? Thank in...

@ifzhang You have modified yolo5s. Would you tell me why and where you modified the yolo5s network? Thanks

Thanks for the nice repo. Have you used validation during training? I did not find it in your code, maybe this is my mistake. If you use the validation, would...

@ifzhang Would explain about pretrained and baseline model? Why do you use two models?

@ifzhang Thank you very much for your nice repo I would like to calculate performance (e.g., MOTA) on my custom data. Would you tell please, which evaluation metric(package) have you...

Pytorch implementation of yolov3?

2

Thanks for nice repo and your youtube explanation. I run your program, if I don't use pretrained model, where it initialized the weights ? Thanks a lot

Could you explain a little about deep sort initialization? # initialize deep sort model_filename = 'model_data/mars-small128.pb' How you created it? Thanks for your awesome work

@CaptainEven , Thanks for the nice repo. Have you used validation during training? If yes, where it is in your code?