IntegratedGradients
IntegratedGradients copied to clipboard
hiranumn
Python/Keras implementation of integrated gradients presented in "Axiomatic Attribution for Deep Networks" for explaining any model defined in Keras framework.
``` AttributeError Traceback (most recent call last) in () ----> 1 ig = integrated_gradients(model) /content/IntegratedGradients/IntegratedGradients.py in __init__(self, model, outchannels, verbose) 33 #load model supports keras.Model and keras.Sequential 34 if isinstance(model,...
The model can only get gradient for embedding layer. If the input of the model is word id and use Embedding Layer, the Integrated-Gradients return an error. ``` ValueError Traceback...
I tried to run the example you provided with iris dataset with keras. But I am getting AttributeError: 'int' object has no attribute 'op' error. My TensorFlow version is 2.2....
Thank you for implementing Integrated Gradient. Currently, my CNN model is based on Theano. May I ask you how I can implement Integrated Gradient with Theano backend? Thanks.
Hi i have an LSTM model for ECG classification. when i used integrated_gradient(model), this error came up. how should i resolve this issue?
The error log is below: ``` TypeError Traceback (most recent call last) in () ----> 1 ig = integrated_gradients(model) /home/ubuntu/GA/IntegratedGradients-master/IntegratedGradients.py in __init__(self, model, outchannels, verbose) 73 gradients = self.model.optimizer.get_gradients(self.model.output[:, c],...
HI, I'm still receiving error output (enclosed error log and model) Thank you --------------------------------------------------------------------------- MissingInputError Traceback (most recent call last) in () ----> 1 plot_roc( t_valores, t_grupos, t_conservation, 'model_used_to_paper.hdf5') in...
