-
Thank for your work.
If I run de.explain multiple times, it becomes slower and slower.
This problem has not been solved in v0.2.
-
Hello,
I have a question about the whether the current DeepExplain implementation recompiles the graph every time the run() method is called. Currently, every call to run() appears to include a cal…
-
I just have a normal MNIST CNN and get the following error when running DeepLIFT
```
---------------------------------------------------------------------------
TypeError …
-
Tried running the embedded motif interaction code for my own dataset (simulated as per the guidelines in the supplementary paper) and encountered the following error:
**Traceback (most recent call …
-
I believe there is a **code correction** necessary in [DeepLIFTWrapper](https://github.com/albermax/innvestigate/blob/master/innvestigate/analyzer/deeplift.py)
If I understand this correctly (jump…
-
We should define various abstract classes for model postprocessing here: https://github.com/kipoi/kipoi/tree/master/kipoi/postprocessing
A user should implement various postprocessing classess (inh…
-
Is there any way to use deeplift on a model that has been trained with an embedding layer? I use an embedding layer that is essentially just a lookup and the input is a matrix of indices. When I try…
-
how can we use deep explain for 3 channel images with **keras** backend?
-
I'm using the Keras 1.2 w/ TF (dev-tf branch) functional API & updated to use `kc.convert_functional_model`.
Here's the error:
```
----------------------------------------------------------------…
-
Hi,
I'm trying to got through an example using a simple API keras model. I've loaded the model in e.g.,
deeplift_model = kc.convert_model_from_saved_files('Model.h5',
…
cap76 updated
6 years ago