Description
I am trying to understand the code and the design decisions made while designing this model.
In this regard, I have two doubts as below:
- The correlation
max_displacement
is kept constant at 4 for all the levels of feature maps.
back2future.pytorch/back2future.py
Line 73 in a3b619a
In your opinion, do you think we have to have different max_displacement
for different levels of the network?
- I would like to get an intuition regarding the multiplication factors used for flow:
0.625 for level-6 flow
back2future.pytorch/back2future.py
Lines 178 to 179 in a3b619a
1.25 for level-5 flow
back2future.pytorch/back2future.py
Lines 196 to 197 in a3b619a
2.5 for level-4 flow
back2future.pytorch/back2future.py
Lines 213 to 214 in a3b619a
5 for level-3 flow
back2future.pytorch/back2future.py
Lines 230 to 231 in a3b619a
Could you please let me know why do we need these multiplicative factors?
I am sorry if this is a basic question to be asked. As the network is learnable, isn't it possible that the network learns this multiplicative factor automatically as well?
Thanks in advance!