Vanditha Rao

@GianlucaCerilli Did you figure out the structure of the repository? If yes, please do share with us. I am facing the same issue. I would like to understand the code...

Hi @sujay-pandit, it seems that you have figured out the code. If yes, then it would be great if you could help me. I think it is a great repository,...

@AshishGusain17 Please check the issue #138

> @rao208 You might want to reduce the patch size: a patch size of 20 means you only apply 3 patches along the x axis. Among the 9 patches, the...

@RaphaelMeudec The link to the dataset in Kaggle is https://www.kaggle.com/prasunroy/synthetic-digits? There are two folders: imgs_train and imgs_valid each of these contains 10 more folders. I, first, put all the training...

@RaphaelMeudec Update: I have observed a similar pattern when I use Albumentation image augmentation technique.

@RaphaelMeudec Please help me. Do you think there is any bug in my code? I tried different preprocessing techniques (like albumentation data augmentation, standardization, normalization, brightening and sharpening the image)

@RaphaelMeudec What is the use of grid_display function? I went through your code on occlusion sensitivity. I get the use of everything except for the grid_display function. I was wondering...

> > Hi, thanks for your reply @matheushent . > > Still no luck. I changed it and I still get the black image... > > Try to plot _grayscale_integrated_gradients_...

@matheushent So, basically grid_display is required only 1. if we use callbacks instead of core i.e. IntegratedGradientsCallback(Callback) instead of IntegratedGradients > grid_display function only concatenates all images into one 2....