-
Hello,
Thank you a lot for your work.
I'm wondering your network learns also features vector of each superpixel or it just learn the superpixels.
If yes, how can l get them otherwise you keep j…
-
Hi,
We are trying to arrive at positive and negative image explanation with a fixed heuristic that works for all kinds of image resolutions. In the sense, once the explanation is generated by LIME, i…
-
Hi - was getting acquainted with the package and ran into an error in the example code of the lime::lime vignette. When I ran:
```
library(keras)
library(abind)
# get some image
img_path
-
Dear Matthias,
I used 'python setup.py install' to install pytorch_geometric. The log of install is the following:
running install
running bdist_egg
running egg_info
writing dependency_links to t…
-
Thank you for the release of project, and it is a great work!
In your paper, there are a section on the optical flow using SSN_{deep}, which gives a good visual results, would you please give some …
-
I calculate some features in Qupath, like: coherence features, delaunay cluster features and smoothed features, but I'm not sure about the meaning of those features. Thank you so much!
-
Hi,
I have a keras model with two separate input and output in [0,1] (please see the model architecture below). The loss function used here is `mse`.
 article, particularly this part:
expla…
-
may I ask which optical flow network was used in the paper?
-
I am using keras with Tesorflow backend (using python 2.7) and I built two dense layer on top of pretrained vgg16 model with four classes. And I get a pretty decent results on my validation set. Now I…