-
I came back to this and realized the notebooks don't run with tensorflow 2. Sad!
-
Hi,
It appears the opacity parameter settings in heatmap_display are causing gradCAM to not properly superimpose on original images. This is specifically being seen when using CIFAR10 and small siz…
ksasi updated
4 years ago
-
Hi, thanks for great project. It works very well.
I have technical question about preprocessing the image for the cnn.
I looked into your examples, but normally every image which is input to VGG…
-
TF 2.1, tf-explain 0.2.0
------
Hello,
I'm using tf-explain (callbacks) on about 70.000 images, 56*56*3, and two labels (0: 13%, 1: 87%), in order to explain class 0 classification. Whereas Gr…
-
Hello, I was experimenting with Captum and I was wondering if there was any way to trace/script an attribution model in order to just obtain the final heatmap as output of the serialized file.
I d…
-
I was looking at the code in grad_cam.py for LayerGradCam.attribute() and noticed that there is no Relu operation applied after computing the summed_grads * layer_eval here: https://github.com/pytorch…
-
Hi,
I have a question about the CAM method in tensorflow implementation.
Although you mentioned in the paper that you employed CAM [63], I don't see it is actually functional. The code only allow…
-
Hello,
I'm working with the GradCam function and I need to see activation on Train and test also. Validation and Test set but the default option is Validation here:
```
im,cl = self.learn.data.dl(D…
-
*The following peer review was solicited as part of the Distill review process. The review was formatted by the editor to help with readability.*
*The reviewer chose to keep anonymity. Distill offe…
-
Hello,
I am trying to work on an Intepretable AI solution for Image classification. Our work is based on Smooth Grad CAM plus plus. I had a perfectly working code until I installed pytorch in my …