不能正常的推理 about varifocalnet HOT 5 OPEN

ModuleAttributeError Traceback (most recent call last)
in ()
4 CONFIG_FILE = './work_dirs/vf_r2_base/vfnet_r2_101_fpn_mdconv_c3-c5_mstrain_2x_coco.py'
5 CHECKPOINT_PATH = './work_dirs/vf_r2_base/epoch_20.pth'
----> 6 model = init_detector(CONFIG_FILE, CHECKPOINT_PATH)
7 img1='./data/coco/train2017/train_29635.jpg'
8 # img1='./normal/train_1.jpg'

8 frames
/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py in getattr(self, name)
770 return modules[name]
771 raise ModuleAttributeError("'{}' object has no attribute '{}'".format(
--> 772 type(self).name, name))
773
774 def setattr(self, name: str, value: Union[Tensor, 'Module']) -> None:

ModuleAttributeError: 'Bottle2neck' object has no attribute 'conv2'

from varifocalnet.

Commenting delattr(self, 'conv2') in res2net.py can solve this issue.

from varifocalnet.

是这个位置的报的错。但是该如何解决

from varifocalnet.

Comment delattr(self, 'conv2') <=> # delattr(self, 'conv2')

from varifocalnet.

thank success

from varifocalnet.