fixed an issue in SQR-Deformable DETR 's inference pipeline

[Fangyi-Chen]

we found and fixed an unseen bug in SQR-Deformable-DETR:

The code logic of SQR-Deformable-DETR (and the original Deformable-DETR) is like:

1. calculate and update queries stage by stage in

   SQR/mmdet/models/utils/transformer.py

   Line 707 in ceb538f

   class QRDeformableDetrTransformerDecoder(DeformableDetrTransformerDecoder):

2. collect the calculated queries.

3. feed the collected queries to the cls branch and box branch in

   SQR/mmdet/models/dense_heads/QR_deformable_detr_head.py

   Line 17 in ceb538f

   class QRDeformableDETRHead(DETRHead):

4. for the original Deformable-DETR's training and inference, and for sqr's inference, we will have 6 queries and 6 lvl of corresponding cls branches and box branches. so the alignment is simply like

   SQR/mmdet/models/dense_heads/deformable_detr_head.py

   Line 161 in ceb538f

   outputs_class = self.cls_branches[lvl](hs[lvl])

But for sqr training, we will have to align the collected queries (32 queries) with the corresponding 6 lvl of cls branch and box branch

SQR/mmdet/models/dense_heads/QR_deformable_detr_head.py

Line 161 in ceb538f

elif qid < 1: # training mode sqr query-stage alignment

While this alignment should not be applied to sqr's inference pipeline, we accidentally applied it. However, for (SQR)Deformable-DETR, the cls branches and box branches are shared across all levels. So, this bug only exists logically, but did not actually affect anything.

We have added two lines of code to force SQR-Deformable-DETR to use the original pipeline, as in

SQR/mmdet/models/dense_heads/QR_deformable_detr_head.py

Line 158 in ceb538f

if not feat.requires_grad: # test mode