Hi, thanks for your great work. When I train bevf_pp_cam model on nuScene dataset, I load mask_rcnn_dbswin-t_fpn_3x_nuim_cocopre.pth pretrained weight on nuImage into img_backbone and img_neck. But I found that the img_neck in bevf_pp_cam model has a adp_layer to concat multi-scale feature into a single feature map, and the parameters in this adp_layer are not contained in mask_rcnn_dbswin-t_fpn_3x_nuim_cocopre.pth, and you just simply freeze the whole img_neck when training, the parameters in adp_layer will never update right? I wonder why you freeze this adp_layer, can you give some explanations about it?
Hi, thanks for your great work. When I train
bevf_pp_cammodel on nuScene dataset, I loadmask_rcnn_dbswin-t_fpn_3x_nuim_cocopre.pthpretrained weight on nuImage intoimg_backboneandimg_neck. But I found that theimg_neckinbevf_pp_cammodel has a adp_layer to concat multi-scale feature into a single feature map, and the parameters in this adp_layer are not contained inmask_rcnn_dbswin-t_fpn_3x_nuim_cocopre.pth, and you just simply freeze the wholeimg_neckwhen training, the parameters in adp_layer will never update right? I wonder why you freeze thisadp_layer, can you give some explanations about it?