In the DCN tutorial code (GitHub link), the loss function used is Root Mean Squared Error (RMSE). However, I believe thatBinary Cross-Entropy should be used instead.
In the original DCN paper, it specifically mentions that Binary Cross-Entropy was used as the loss function.
Could you explain why there is this difference between the tutorial and the paper?
In the DCN tutorial code (GitHub link), the loss function used is Root Mean Squared Error (RMSE). However, I believe thatBinary Cross-Entropy should be used instead.
In the original DCN paper, it specifically mentions that Binary Cross-Entropy was used as the loss function.
Could you explain why there is this difference between the tutorial and the paper?