deeplift

deeplift copied to clipboard

Data feeding into the CNN model should be normalised or not?

3

Hello there, I have checked the notebook examples, such as the MNIST example. The test data set you feed into the CNN model is not normalised (it is still between...

Yanjiayork

Deal with keras embedding layers

2

I was trying to use DeepLIFT to analyse my text classification model but it will throw key error about embedding layers since there is no key about embedding in layer_name_to_conversion_function...

zkysfls

Support for ELU and tanh Activation Functions

2

Hi Avanti, as far as I can tell from the README and Code, DeepLIFT does currently not support the ELU and tanh activations. Are there any plans to add these...

LeaE

Improve handling of model parameters

1

Hi Avanti, I modified how DeepLIFT handles model parameters. The current behaviour is to store them as numpy arrays. I converted them to tensorflow variables. This change resulted in a...

berleon

Zero contrib for MaxPool2D

1

Hi Avanti, for my paper [[1]](https://arxiv.org/abs/1912.09818), I computed the cosine similarity using the values of `self._target_contrib_vars` as it includes both positive and negative contributions. However for the MaxPool2D, `self._target_contrib_vars` was...

berleon

TF2.0 Support

1

Has anyone been able to successfully run on Tensorflow 2.0?

tvykruta

AttributeError: 'MaxPool2D' object has no attribute 'set_scoring_mode'

3

I am using a VGG16 model with "include_top=False" i.e. having Maxpool2D as its last layer. Is Maxpool2D as the target layer not possible or it is just not implemented?

MuskaanJain

KeyError: 'batchnormalizationv1'

3

Hey :) I'm trying to use kc.convert_model_from_saved_files but I have this keyerror : ``` File "C:\Users\XXXXXXX\Anaconda3\lib\site-packages\deeplift\conversion\kerasapi_conversion.py", line 349, in layer_name_to_conversion_function return name_dict[layer_name.lower()] KeyError: 'batchnormalizationv1' ``` The model is not complicated...

Gasp34

getting non zero prediction difference

7

Hi, When applying deeplift over the dataset of "cats and dogs" with the same architecture as provided in Mnist examples. The difference in predictions is coming to be a non-zero...

MuskaanJain

How to make DeepLIFT support customized keras layer?

10

Hi, I was trying to use DeepLIFT to interpret my CNN model. I don't know how to convert my model because I built a customized layer. My model is built...

KeLanhhh