Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

report a bug of DCN when batch_size / cur_im2col_step > 1 #818

Closed
jshilong opened this issue Feb 4, 2021 · 0 comments · Fixed by #819
Closed

report a bug of DCN when batch_size / cur_im2col_step > 1 #818

jshilong opened this issue Feb 4, 2021 · 0 comments · Fixed by #819

Comments

@jshilong
Copy link
Collaborator

jshilong commented Feb 4, 2021 •
edited
Loading

When set a batch_size / cur_im2col_step(defult as 32) > 1, such as

import mmcv 
from mmcv.ops import DeformConv2dPack 
de_conv = DeformConv2dPack(512, 512, (3, 3), stride=1, padding=1).cuda() 
import torch 
x = torch.rand(64, 512, 8, 32).cuda() 
y = de_conv(x)

In the

mmcv/mmcv/ops/csrc/pytorch/deform_conv_cuda.cu

Line 270 in 6c57b88

weight = weight.view({group, weight.size(0) / group, weight.size(1),

The operation view of weight would shape failed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

fix bug of DCN jshilong/mmcv
1 participant
@jshilong