Closed yyccli closed 2 years ago
Our design aims to be consistent with the positional encoding of image features. as shown in https://github.com/IDEA-opensource/DAB-DETR/blob/main/models/DAB_DETR/position_encoding.py#L58, the order is pos_y
followed by pos_x
.
Hi, thank you for your reply. I understand now.
Hi, first thanks for your great work to improve DETR-like detectors! I have a question on the cat() operation when we want to get query pos embedding using func
gen_sineembed_for_position()
in filemodels/DAB_DETR/transformer.py
line 51 and 61. Why here useshould
x
come first thany
?