ma-xu / Context-Cluster

[ICLR 2023 Oral] Image as Set of Points

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

FPN

KDAkasa opened this issue · comments

Hello, thank you for your contribution to science. I encountered the following problem while reproducing the object detection code:
Then I debugged and found that the input [5, 5] was two tensors, which should have been 4

File "/tmp/pycharm_project_887/mmdet/models/detectors/two_stage.py", line 84, in extract_feat
x = self.neck(x)
File "/opt/anaconda3/envs/py38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/opt/anaconda3/envs/py38/lib/python3.8/site-packages/mmcv/runner/fp16_utils.py", line 146, in new_func
output = old_func(*new_args, **new_kwargs)
File "/tmp/pycharm_project_887/mmdet/models/necks/fpn.py", line 172, in forward
assert len(inputs) == len(self.in_channels)
AssertionError