microsoft/LoRA

_conv_forward() error

likaiucas opened this issue · 0 comments

Exception has occurred: TypeError
_conv_forward() takes 3 positional arguments but 4 were given
File "/irsa/lk/BONAI2/mmdet/models/backbones/vit_lora.py", line 574, in forward
x = self.proj(x) # (1,3,1024,1024) -> (1,768,64,64)
File "/irsa/lk/BONAI2/mmdet/models/backbones/vit_lora.py", line 132, in sam_hq_forward
x = self.patch_embed(x)
File "/irsa/lk/BONAI2/mmdet/models/detectors/obm_hq_double.py", line 187, in forward_train
image_embeddings, interm_embeddings = self.image_encoder.sam_hq_forward(img)
File "/irsa/lk/BONAI2/mmdet/models/detectors/obm_hq_double.py", line 79, in forward
return self.forward_train(img, img_metas, **kwargs)
File "/irsa/lk/BONAI2/mmdet/models/detectors/base.py", line 237, in train_step
losses = self(**data)
File "/irsa/lk/BONAI2/mmdet/apis/train.py", line 143, in train_detector
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/irsa/lk/BONAI2/tools/train.py", line 161, in main
train_detector(
File "/irsa/lk/BONAI2/tools/train.py", line 172, in
main()
TypeError: _conv_forward() takes 3 positional arguments but 4 were given