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.

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

single class training issus #113

Open
riyaj8888 opened this issue May 16, 2019 · 0 comments
Open

single class training issus #113

riyaj8888 opened this issue May 16, 2019 · 0 comments

Comments

@riyaj8888
Copy link

when i am training yolov2 for single class i am getting following error.
" net_utils.load_net(args.model, net)
File "/home/ubuntu/projects/lesiondetectlong/utils/network.py", line 63, in load_net
v.copy_(param)
RuntimeError: The expanded size of the tensor (30) must match the existing size (60) at non-singleton dimension 0
"
when i printed out the output channels of conv5 layers it has to show "out_channels = num_anchors * (num_classes + 5) "
for single class it must be 30 .
but i am getting 60 output channels

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant