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

Any example for trainning&validating the model on own dataset? #2

Open
paulcx opened this issue Mar 22, 2017 · 2 comments
Open

Any example for trainning&validating the model on own dataset? #2

paulcx opened this issue Mar 22, 2017 · 2 comments

Comments

@paulcx
Copy link

paulcx commented Mar 22, 2017

No description provided.

@vsoch
Copy link
Member

vsoch commented Mar 22, 2017

This is intended to run our model (built from a checkpoint), but it's using basic tensorflow resnet, afaik. I would start with something like this:

https://github.com/tensorflow/models/tree/master/resnet

and general tensorflow tutorials if you are interested in building models from scratch. In our experience, it works out better to start with something over nothing (eg a model provided by google even if it's trained on non medical entities). I'll leave other comments to @mchen17

@paulcx
Copy link
Author

paulcx commented Mar 23, 2017

@vsoch Thanks. I wonder if there will be some basic descriptions e.g. how to train on own bone-age dataset, which model you used for extracting the bone features and the accuracy of the model.

@paulcx paulcx changed the title Any hint for trainning own data? Any hint for trainning on own data? Mar 23, 2017
@paulcx paulcx changed the title Any hint for trainning on own data? Any example for trainning&validating the model on own dataset? Mar 23, 2017
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