talentCODE

Results 4 comments of talentCODE

where is mimic score? In the paper Equation(5), author mentioned mimic score as an transformation of distillation loss. However I can't find it in the code.

ok, I find the mimic score loss, this loss isn't used combined with less forgetloss and marginrank loss

validation yields very high crowd counts on the pretrained model

did you solve the problem? I also find the pretrained model not works well. I'm new at the crowd counting field

"AttributeError: 'numpy.int64' object has no attribute 'intersects'" occurs in Eval VAD with 1 GPU.

I met the same problem as you. Have you solved this issue?

"AttributeError: 'numpy.int64' object has no attribute 'intersects'" occurs in Eval VAD with 1 GPU.

for i, pline in enumerate(gt_lines_shapely): for o in tree.query(pline): if tree.geometries[o].intersects(pline): pred_id = index_by_id[id(tree.geometries[o])] you can modify the code like above