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

Issues with training #61

Open
stopcharlaCapillary opened this issue Feb 6, 2018 · 2 comments
Open

Issues with training #61

stopcharlaCapillary opened this issue Feb 6, 2018 · 2 comments

Comments

@stopcharlaCapillary
Copy link

Hey, I have tight bounded face images, the sizes vary from(80x80 to 220x220). I am trying to fine tune inception v3. I have trained with around 8000 images. The data is not that biased too. But once I try to test it out the output is either male or all the images in folder or female for all images with probability of 1. I'm not sure what mistake I'm doing here. Can you please help me with this.
I'm using your prepoc.py , train.py and guess.py as is.
@stopcharlaCapillary
Copy link
Author

I gave the labels as 0 and 1 in train.txt

@dpressel
Copy link
Owner

dpressel commented May 4, 2018

Cannot replicate. Would need more information about your data. Works fine for me

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

No branches or pull requests
2 participants
@dpressel @stopcharlaCapillary