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

shape not match #34

Closed
seefun opened this issue Oct 20, 2018 · 7 comments
Closed

shape not match #34

seefun opened this issue Oct 20, 2018 · 7 comments

Comments

@seefun
Copy link

seefun commented Oct 20, 2018

PyramidBox/layers/modules/multibox_loss.py", line 105, in forward
loss_c[pos] = 0 # filter out pos boxes for now
RuntimeError: The shape of the mask [4, 34125] at index 0 does not match the shape of the indexed tensor [136500, 1] at index 0

I set the batchsize to 4 and I use my own dataset. When i run train.py I occur this problem. why does it happen?

@xxlei
Copy link

xxlei commented Nov 13, 2018

hei, i meet the same problem, do you sloved it ?

@seefun seefun closed this as completed Dec 5, 2018
@abcdvzz
Copy link

abcdvzz commented Dec 10, 2018

hei, i meet the same problem, do you sloved it ?

Did u solve the problem?

@abcdvzz
Copy link

abcdvzz commented Dec 10, 2018

PyramidBox/layers/modules/multibox_loss.py", line 105, in forward
loss_c[pos] = 0 # filter out pos boxes for now
RuntimeError: The shape of the mask [4, 34125] at index 0 does not match the shape of the indexed tensor [136500, 1] at index 0

I set the batchsize to 4 and I use my own dataset. When i run train.py I occur this problem. why does it happen?

Did u solve the problem?

@Tianlock
Copy link

@seefun hello, have you solved the problem? i met the same problem.

@Tianlock
Copy link

@xxlei Hi, have you solved it, i met the same problem, thanks

@seefun
Copy link
Author

seefun commented Dec 25, 2018

@abcdvzz @Tianlock I give up using this codes. And I try to use the official pyramidbox codes which you can find in PaddlePaddle/models

@NarcissusInMirror
Copy link

I think this repo is modified on the pytorch version of SSD, the original repo has the related issue. All you need is to change few lines of code in multibox_loss.py and train.py as described in
this and this issue. It works well for me.

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

5 participants