Jamesswiz

HI, @experiencor thanks for help! Well the correct way is: inp=model.input outp=model.layers[-2].output model1=keras.models.Model(inp,outp) but again it doesn't works with your code and I get the error: The name 'dense_2_13/BiasAdd:0' refers...

@experiencor No problem, I think I have figured it out. Going to test it on various examples to check if things are right. Anyway, It will be good if you...

@experiencor Hi, well I am new to git so not sure how pull request works. Actually the error was due to the saved model files in /tmp/ directory because of...

Hi @experiencor , I need clarification for the operation of getting the output "self.imported_y" for computing gradients in guided_backprop.py i.e., self.imported_y = self.guided_graph.get_tensor_by_name(model.output.name)[0][output_index] By default output_index is set to 0....

Hey ! Thanks again for a quick response. I will try your shared implementation. I am also working on CNN filter visualization with raw speech as input. It will be...

Hi @kenmikanmi I am also getting a similar error: 'list' object has no attribute 'gradInput' I have a saved model which dosen't have a name: print(model) [nn.Sequential { [input ->...

@kenmikanmi Yes I get the same error. another thing which i tried was to replace the whole 'if' statement itself with just model=model[0]. The code ran (not sure correctly) but...