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

Support for loading tensorflow model #18

Closed
Ramsonjehu opened this issue Jan 11, 2022 · 4 comments
Closed

Support for loading tensorflow model #18

Ramsonjehu opened this issue Jan 11, 2022 · 4 comments
Labels
enhancement New feature or request

Comments

@Ramsonjehu
Copy link

Hi Team,

Great work, It would be great if its possible to load tensorflow models as well. Hoping to see the feature soon.

Thanks and Regards,
Ramson Jehu K

@Ramsonjehu Ramsonjehu added the enhancement New feature or request label Jan 11, 2022
@MLRichter
Copy link
Owner

Hi,
TensorFlow should actually be much easier to integrate, since TF actually has a compote graph that you can somewhat easily access.
It will likely be the first major update after some minor fixes.

@MLRichter
Copy link
Owner

Looked a little bit into it.
As far as I see, this likely has to be split up into different encoders.
By far, the lowest hanging fruit in that regard would be support for Keras-Models.
For this reason, I opened a separate feature request here: #22
For native tensorflow-models some other approach needs to found.

@MLRichter
Copy link
Owner

Since release https://github.com/MLRichter/receptive_field_analysis_toolbox/releases/tag/v1.2.0 this toolbox supports keras.Model-objects of Tensorflow.

@MLRichter
Copy link
Owner

since TensorFlow seems to rely today mostly on these types of models I will be closing this for now. Please reopen a new feature request if some different type of Tensorflow-Model support is needed.
Thank you for your suggestion.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants