search

d-li14 / involution

[CVPR 2021] Involution: Inverting the Inherence of Convolution for Visual Recognition, a brand new neural operator
https://arxiv.org/abs/2103.06255
MIT License
1.31k stars 177 forks source link

raise error #35

Open huixiancheng opened 3 years ago

huixiancheng commented 3 years ago

Like this

File "/cloud/seg/modules/trainer2.py", line 426, in train_epoch loss_m.backward() File "/environment/python/versions/miniconda3-4.7.12/lib/python3.7/site-packages/torch/tensor.py", line 245, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs) File "/environment/python/versions/miniconda3-4.7.12/lib/python3.7/site-packages/torch/autograd/__init__.py", line 147, in backward allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag File "/environment/python/versions/miniconda3-4.7.12/lib/python3.7/site-packages/torch/autograd/function.py", line 89, in apply return self._forward_cls.backward(self, *args) # type: ignore File "/cloud/seg/modules/inovo.py", line 245, in backward assert grad_output.is_cuda and grad_output.is_contiguous() AssertionError

huixiancheng commented 3 years ago

try to solve by

if not grad_output.is_contiguous(): grad_output = grad_output.contiguous()
assert grad_output.is_cuda and grad_output.is_contiguous() Not sure if it will cause exception