This repository is an official implementation of the ICCV 2021 paper "Conditional DETR for Fast Training Convergence". (https://arxiv.org/abs/2108.06152)
First and foremost, thank you for your great work. I have one question. The encoder (using default settings) seems to terminate with two nn.LayerNorm . One is within TransformerEncoderLayer and the other within TransformerEncoder. Is this intentional?
Hey,
First and foremost, thank you for your great work. I have one question. The encoder (using default settings) seems to terminate with two
nn.LayerNorm
. One is withinTransformerEncoderLayer
and the other withinTransformerEncoder
. Is this intentional?Best regards, Joakim