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

How to visualize the inputs and prediction during evaluation? #1

Open
yangxinhaosmu opened this issue Feb 10, 2022 · 3 comments
Open

Comments

@yangxinhaosmu
Copy link

Thanks for your work! Can you tell me how to visualize the inputs and results? I used tensorboard, but the visualization of inputs is strange.

@XBPFS
Copy link

XBPFS commented May 14, 2022

Sorry to bother, but have you found a way to visualize the result so far? I've tried to but failed, because the input image has been cropped and flipped, I don't know haow to match the original image. Could you please share the code if possible?

@yangxinhaosmu
Copy link
Author

Sorry to bother, but have you found a way to visualize the result so far? I've tried to but failed, because the input image has been cropped and flipped, I don't know haow to match the original image. Could you please share the code if possible?

Actually, I have the same problem as you. I don't know how to deal with it. Can you show me the results of your input images?

@XBPFS
Copy link

XBPFS commented May 19, 2022

Sorry to bother, but have you found a way to visualize the result so far? I've tried to but failed, because the input image has been cropped and flipped, I don't know haow to match the original image. Could you please share the code if possible?

Actually, I have the same problem as you. I don't know how to deal with it. Can you show me the results of your input images?

image
This is the test result of one image from PASCAL. Aside from mirroring and rotation, the image is square and the original is rectangle so I don't know how to match them.

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

2 participants