so many bugs in the code!!!

[fyw1999]

I run this code with torch 1.6.0 and cuda 10.2. I have successfully trained the Headhunter, and now I try to get the track results. After I fixed a lot of bugs, I still stucked in the error "ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (7,) + inhomogeneous part.". This error is triggered by "f_all_scores = np.array(f_all_scores)", because the lens of array in list f_all_scores is different, but I have no idea with the reason.