Byte
Byte
First of all thanks for providing the awesome code. Under which license is it being published? I.g. is it allowed to use it (or parts of it) for research, as...
Hi, I am trying to understand the Fast BEV projection code. I noticed that in the NuScenesMultiView_Map_Dataset2 , or more precisely in the NuScenesMultiViewDataset the camera intrinsics are overritten with...
Hello, I am trying to use M2BEV / Fast-BEV or at least the m2BEV projection step for image features to BEV. This does seem to work and I do get...
Hello, how can I use your code to very simply project a single set of image features e.g. of shape [batch_size, 6, 256, width, height] to the BEV space? I...
Hello, I just noticed that you pillar based centerpoint configs have the wrong number of PFE layers. Your have only a single [64] layer. This is correct for PointPillars, however...
If I see it correct, you actually do not use any MultiQueryAttention, but just normal self-attention?