MCG-NJU / AdaMixer

[CVPR 2022 Oral] AdaMixer: A Fast-Converging Query-Based Object Detector
MIT License
236 stars 24 forks source link

[BUG] params M's dimention shape mismatch #17

Closed Shiyang980713 closed 2 years ago

Shiyang980713 commented 2 years ago

In the code 'mmdet/models/roi_heads/bbox_heads/adaptive_mixing_operator.py' [line69] self.m_parameters = self.eff_in_dim self.eff_out_dim [line116-117] M, S = params.split([self.m_parameters, self.s_parameters], 2) M got a dim [..., self.eff_in_dim self.eff_out_dim].

However, M is reshaped to [..., self.eff_in_dim, self.eff_in_dim] in [line140-141] M = M.reshape(B*N, G, self.eff_in_dim, self.eff_in_dim)

Is that a bug or feature?

sebgao commented 2 years ago

Hi,

Thank you for your interest in our work and code. Actually this is a bug but does not have actual effects on the current AdaMixer setup since eff_in_dim = eff_out_dim in the current implementation. I'll fix it.