-
It would be nice to support the [Benchopt](https://github.com/benchopt/benchopt) problem suite, which is also available in Python:
- [ ] Ordinary Least Squares
- [ ] Non-Negative Least Squares
- …
-
Right now all monsters at the same, but it would be good to have monster variations
We have 2 options for the monster variations:
1. Do only 1~2 monster variations for very specific things (ex: 1/…
-
It's a nice work!
And after reading your paper, I wonder what is the total variation regularizer which you have mentioned in Sec3.2. Could you provide some explanations about that?
![image](https://…
-
The total variation (l2 version) is calculated here as `sqrt(sum(d_w**2 + d_h**2))`. Shouldn't it be `sum(sqrt(d_w**2 + d_h**2))` instead? See
https://github.com/photosynthesis-team/piq/blob/26d044e…
-
In order to find the best value for K (the number of clusters), it would be nice to get the variance of the distance of clustered points to their cluster's centroid.
Inspired by https://www.youtube…
-
Hey, I get these results after I've added Total Variation loss (https://discuss.pytorch.org/t/yet-another-post-on-custom-loss-functions/14552).
What can cause this problem?
-
I'd like to use second-order total variation, as described in for example these couple of papers:
https://www.ipol.im/pub/art/2013/40/article.pdf
http://www.franklenzen.de/pdf/lenzen_et_al_ssvm2013.…
-
I know tensorflow support it (tf.image.total_variation). But I can't find it in mxnet's APIs. I wonder if total variation is also supported in mxnet?
-
Need to write and add a Total Variation filter for ndimages
-
## What is your suggestion, and why should it be implemented?
Currently, the combo numbers are cropped inconsistently. This leads to variation in the placement of the numbers on the combo display.
…