-
@yaroslavvb Have you tried to create grad cam or saliency maps after using `memory_saving_gradients`? Mine look very odd (columnar). I'm doing the Udacity program, and my `keras-vis` `grad-cam` plots…
ghost updated
5 years ago
-
Like the 111.mp4,it has 1050 frames,but has 1203 GT saliency maps in your dataset.
-
I am a novice. Can I ask how to draw the PR curves and F-measure curves in the paper, and do I need to reproduce the method you compare one by one? Or if there's an easier way?
-
Both cases are about mdb.
(1)
![fruit3-fr](https://user-images.githubusercontent.com/3723126/27935808-40812e08-627b-11e7-820f-31ab7785a686.jpg)
Traceback (most recent call last):
File ".../d…
-
Hello,
Thank you for your very interesting work ! I'm currently trying to replicate your results with your provided codebase and I was wondering whether you also tested a Vision Transformer archit…
-
Hi,
I am trying to use your toolkit in Google Colaboratory starting from the example [Attention on ResNet50 (Saliency and grad-CAM)](https://github.com/raghakot/keras-vis/blob/master/examples/resnet/…
-
The size of my input image is 49*41*40, and I can get the saliency output of my CNN model.
But the attention map size is 49*41, not the original 3-dimension size.
I want to know how can I get the 3D…
-
Hi, thanks for the release. I'm currently working on context-aware video encoding which aims at setting different QPs for different area within frame to be encoded according to grayscale saliency map …
-
The saliency map size on ECSSD and HKU-IS are inconsistent with the original images. How to resize back?
-
Could you provide the saliency map on the SOD test datasets?such as ECSSD/DUT-TE/DUT-OMRON/PASCAL/HKU-IS? Thank you for your contribute to SOD field.