Questions on architecture design choices
Closed this issue · 2 comments
Hi I have a couple of question regarding your NN architecture design and I would like to ask if you could give the the motivation for these particular design choices (or if they are copied from some other work point me to it):
For both ResNet backbones you stopped at the 3rd block and did not use the 4th block:
Line 164 in be46f0e
Line 68 in be46f0e
What is the motivation for the use of instance normalization in the decoders?
Line 78 in be46f0e
Why did you not use activation functions for the up-sampling layers in the BEV grid?
Line 45 in be46f0e
Great questions.
3rd block: I think we did this so that the resolutions would match up with the EfficientNet versions (which came from FIERY).
Instance norm: This probably makes only a tiny difference in practice. In general I prefer instancenorm over batchnorm because instancenorm is friendlier to experiments with low batch sizes.
No activation in upsampling: copied from FIERY: https://github.com/wayveai/fiery/blob/master/fiery/layers/convolutions.py
Thanks.