search

AI-liu / Complex-YOLO

Complex-YOLO: Real-time 3D Object Detection on Point Clouds pytorch Darknet
442 stars 113 forks source link

How can I get predicted class in eval.py #18

Open atinfinity opened 5 years ago

atinfinity commented 5 years ago

In https://github.com/AI-liu/Complex-YOLO#result, predicted box and predicted class is drawn. But, I think that eval.py draws only predicted box and target box. So, I want to know how to get predicted class from all_boxes.

abhigoku10 commented 5 years ago

@atinfinity i am too facing the same issue did u get a solution for it

atinfinity commented 5 years ago

@abhigoku10 I think that pred_boxes has 15 elements. And, pred_boxes[7]~[14] has the confidence of classes.
https://github.com/AI-liu/Complex-YOLO/blob/master/eval.py#L59-L68

But, some element has negative value. So, I don't understand this reason.

abhigoku10 commented 5 years ago

@atinfinity thanks for the inputs, yes negatives even i observed it and had one query does the prediction of the classes are proper

abhigoku10 commented 5 years ago

@atinfinity where you able to get correct prediction of the classes . even i am getting negative values in the tensors

abhigoku10 commented 5 years ago

@atinfinity i was able to solve the issue let me know if you have not solved it .

siliconvalleypilot commented 5 years ago

@abhigoku10 How did you solve the problem? I see negative values and np.argmax does not give the correct label position

abhigoku10 commented 5 years ago

@qiaosongwang please take the updated code from the repo and train it you shall get correct values or i have forked the repo and made the corrections you can also take it fromthere

siliconvalleypilot commented 5 years ago

@abhigoku10 Great! Thanks

imdsafi09 commented 4 years ago

I train the model till 158 epochs and then eval on different epoch but the detection is only for car which is not correct enough and the results here contain the class labels also but in my case no labels either..can someone please guide me whats the problem

abhigoku10 commented 4 years ago

@imdsafi09 i would suggest you look into https://github.com/ghimiredhikura/Complex-YOLOv3 this is currently updated and the current repo is not by the author and is not updated also

imdsafi09 commented 4 years ago

@abhigoku10 thanks for your reply. I am already working on your mentioned repo but i want to use it with vlp-16 and that case i dont know how to train it for my own data because the KITTI data set you know is based on vlp-64