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 preprocess the image on pretrained model #90

Open
mancomao opened this issue Mar 4, 2020 · 2 comments
Open

How to preprocess the image on pretrained model #90

mancomao opened this issue Mar 4, 2020 · 2 comments

Comments

@mancomao
Copy link

mancomao commented Mar 4, 2020

Hi

we can't get good result with preprocessing info on the pretrained model.
BGR mean values [103.94,116.78,123.68] are subtracted
scale: 0.017 is used as std values for image preprocessing

can anybody who can reproduce the good result tell us about the exact preprocessing flow?
the Paper also introduced to center crop the image into 224x224 on evaluation set.

many thanks in advance.

@aksenventwo
Copy link

Hi @mancomao , The prototxt of each model has the specified mean at the beginning, just minus the mean operation, and the label file is ILSVRC2017_val.txt

@mancomao
Copy link
Author

@aksenventwo thanks for your reply, looks we are using the different label files. awsome work,

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