tf-explain for pre-trained (frozen) .pb models

sicara / tf-explain

Interpretability Methods for tf.keras models with Tensorflow 2.x

https://tf-explain.readthedocs.io

MIT License

1.02k stars 111 forks source link

tf-explain for pre-trained (frozen) .pb models #137

Open SelComputas opened 4 years ago

SelComputas commented 4 years ago

Hi,

I am looking for a way to implement these explainability features for my pre-trained .pb TensorFlow model, but it seems like the majority of the examples are for .h5 Keras models.

So I was wondering if you are planning to implement the functionality for these types of models (.pb) as well?