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

ValueError: Dimension 1 in both shapes must be equal, but are 324 and 8 #1

Open
Abduoit opened this issue Mar 24, 2018 · 4 comments
Open

Comments

@Abduoit
Copy link

Abduoit commented Mar 24, 2018

Hi

Thanks for your effort, I used visualize_cv.py it works properly. But when I change the file mask_rcnn_coco.h5 with my own .h5 that I trained, it gives me the following error.

any help please ??

ValueError: Dimension 1 in both shapes must be equal, but are 324 and 8. Shapes are [1024,324] and [1024,8]. for 'Assign_682' (op: 'Assign') with input shapes: [1024,324], [1024,8].

@markjay4k
Copy link
Owner

I'm not sure why that is. I haven't tried training a mask RCNN model before

@anburiyan
Copy link

I have the similar issue when i using pre-trained coco model. I know we should change the image input size but am not sure in config file where i have to change to resolve the issue

@Abduoit
Copy link
Author

Abduoit commented Jun 11, 2018

@anburiyan did you solve your issue ?

@anburiyan
Copy link

@Abduoit - not yet. But, I used existing model which worked well. For my own trained model still getting.

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

3 participants