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

About pre-processing #50

Open
sibadakesi opened this issue Apr 27, 2020 · 3 comments
Open

About pre-processing #50

sibadakesi opened this issue Apr 27, 2020 · 3 comments

Comments

@sibadakesi
Copy link

sibadakesi commented Apr 27, 2020

ResNet18, preprocess_input = Classifiers.get('resnet18')

This funcition which name "preprocess_input" doing nothing, What pre-processing did you used to ? I want use this deep feature to do my work, so i think must use the same pre-processing , thinks.

@AlexandreBourrieau
Copy link

Good question, do you found an answser on how to preprocess image for the resnet18 in keras ?

@aristotelisballas
Copy link

aristotelisballas commented Feb 6, 2022

Hello, did you ever find an answer? I am also trying to use the pretrained Resnet18. So far I've tried using the preprocess_input function of the Resnet50 model, which is provided by Tensorflow (https://www.tensorflow.org/api_docs/python/tf/keras/applications/resnet50/preprocess_input) but I'm not getting the same results as Pytorch's pretrained Resnet18 model.

@AlexandreBourrieau
Copy link

AlexandreBourrieau commented Apr 16, 2022

Need only be uint8 at input after image loaded with keras. That works 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

3 participants