Yasuhiro Kubota comments

Results 92 comments of


                                            Yasuhiro Kubota

Activation maximization with InceptionV3

InceptionV3 said "It's 100% this is a website(class:916)" when it predicted the meaningless image (Of course the right answer is ozel). Maybe, this means that ActivationMaximization is using unfit value...

Can I generate an input that maximizes the activity of the convolution filter over time series?

Hi @konnyaku256 . > Currently, I am challenging activation maximization of the convolution filter of recurrent neural network. The generated image is the input value for maxmizing the convolution filer's...

Can I generate an input that maximizes the activity of the convolution filter over time series?

Would you please email me? The address is found in my profile.

Can I generate an input that maximizes the activity of the convolution filter over time series?

Okay, I got it. I write my idea down here. I hope it help you. (I can tell you more detail in **YOUR LANGUAGE** if you have a time and...

Possible miscalculation within grad-cam

I've run your code. But I could not reproduce the same result. ``` In [1]: import numpy as np In [2]: a = np.array([1.0, -1.0]) In [3]: np.maximum(a, 0) Out[3]:...

"tensorflow.python.framework.errors_impl.InvalidArgumentError: The first dimension of paddings must be the rank of inputs[4,2] [1,512,512] [[{{node zero_padding2d_1_1/Pad}}]]"

Hi, @ArpithaFAU . For reproducing the issue, could you provide a code snippet to here or Gist?

backprop_modifier error

Hi, @jinchenglee . Thank you for your reporting. Could you try below way? I think this solution is so smart if it's able to solve your problem. https://github.com/raghakot/keras-vis/issues/80#issuecomment-423529695

3D saliency implementation

Thank you for the PR. I don't think we should merge this change. Because currently keras-vis (i.e., master branch) is able to visualize cam in 3-dims. https://github.com/raghakot/keras-vis/blob/9821aeab1f9396dba5e9137d0c3bcf4e6dee52bd/vis/visualization/saliency.py#L187-L188

3D saliency implementation

Can you show us the detail of minor bug ?

3D saliency implementation

> I don't have the error anymore, but if you run the code on a 3D model with > 1 channel (batch_size, d1, d2, d3, channel=1), the error will appear....