which utilizes the last feature map, and combines it with an additional input projection, from the feature maps obtained from ResNet.
Do I understand this correctly?
Why exactly did you add this "artificial" feature map?
Why did you choose this over using earlier feature maps, like layer1 or even the layer before the maxpool? (Which are part of the code, but commented out):
Hello,
I am currently slightly confused about the number of feature maps used in the deformable DETR code.
In the ArgumentParser you define that you will use 4 feature maps:
https://github.com/fundamentalvision/Deformable-DETR/blob/11169a60c33333af00a4849f1808023eba96a931/main.py#L64
however, in the code you "only" return 3 feature maps from resnet:
https://github.com/fundamentalvision/Deformable-DETR/blob/11169a60c33333af00a4849f1808023eba96a931/models/backbone.py#L76
so you generate an additional "artificial" feature map in the code:
https://github.com/fundamentalvision/Deformable-DETR/blob/11169a60c33333af00a4849f1808023eba96a931/models/deformable_detr.py#L140-L152
which utilizes the last feature map, and combines it with an additional input projection, from the feature maps obtained from ResNet.
layer1
or even the layer before themaxpool
? (Which are part of the code, but commented out):https://github.com/fundamentalvision/Deformable-DETR/blob/11169a60c33333af00a4849f1808023eba96a931/models/backbone.py#L75
Thanks for the great model!