airsplay/py-bottom-up-attention

predict 10~100 bbxes in feature extraction

RubickH opened this issue · 0 comments

Thanks for your codes and models!
I notice that you have provided the model trained with 10-100 bbxes.
I wonder how I can use this model to predict 10-100 bbxes in feature extraction.
It seems that the number of features is closely related to the hyperparameter 'NUM_OBJECTS'.
I don't know how to set it in the adaptive feature extraction mode.
Thanks!