Yasuhiro Kubota

Hi, @eyaler . Thank you for your proposal. But the name was named by the paper that proposed Grad-CAM, so we aren't going to rename. https://arxiv.org/pdf/1610.02391.pdf We'll close this issue,...

Hi, @eyaler , Thank you for your great easy to understand example! I got it, so I reopened this in your stead. I believe that we should add explanation how...

Sorry for the inconvenience. I have something to discuss with you guys. We need to update the package on PyPI as @nandantumu said, but I don't have the permission to...

I created an example with VGG 16. Please refer to below. It is executable. ``` from keras.applications import VGG16 from keras.models import Model from keras.layers import Input from keras import...

Thank you for this PR! Before we merge this PR, could you improve something that is to keep comatibility with Keras that is original, not tf.keras. As following page, Keras...

Hi @MatthiasRathbun . Probably, You used keras-vis 0.4.1 which was installed via PiPY, didn't you. The version has some problems, so please try to re-install keras-vis again such as below:...

Hi there. `visualize_class_saliency` and `visualize_regression_saliency` don't exist. (I think, at first of developing keras-vis, there was possibility that they was created. I don't know the details, but, at least, they...

Do you mean you need to find and visualize the filter outputing max values from all layers?

Yes, of course! However, you have to adjust some parameters for one dimensional data, because, in default, the parameters of ActivationMaximization is tuned for 2D-CNN model. 1. Modify `input_range`, `input_modifiers`...

Hi, @marieff587 . Thank you for your good question. I think that the size of two inputs of your model are the same. Please imagine that they are different. The...