-
[The format of the issue]
Paper name/title:
Paper link:
Code link:
amusi updated
8 months ago
-
Greetings, and many thanks for the contribution as well as for sharing the implementation!
I'm trying to make sense of which hyper-parameters have been used for the different settings, and hope you…
-
Hi there, I wanted to bring to your attention a potential memory leak in the BatchNorm implementation. I am not familiar with the mathematics behind equivariant neural networks and so I can't say if t…
-
Just wanted to check whether the 3D model, made for videos can be repurposed to 3D structural transformer with frame = z?
Is there a fundamental difference between x,y,z if I use it like so, or is …
-
Hi,
I am trying to run the code referred to in the paper but am facing two issues in the following code:
### define a coarse grid
coarse_grid = g. grid ([4 ,4 ,4 ,4] , g . double )
### load …
-
Implent G-conv $D_2$ equivariant version
-
## Background
Generalized CNNs (often called "Group Equivariant CNNs") are CNNs that build non-Euclidean geometric priors into their architecture. Recently, these generalized CNNs have been success…
-
Hi all,
To evaluate the model performance, I need to compute the log probability of a new set of data positions inside the main training loop. Calling `batch_network = constants.pmap(batch_network)…
-
Hi,
Great results! Is there code to test on own images? Or should I work off of the demo code?
I noticed that this has cv2 and scilearn functions for the feature extraction. I see that KeyNet…
-
Hi Gabriele, thanks again for the great library!
I apologize in advance if the answer to this can be found in the docs/paper/thesis, I couldn't find it there.
My question is rather soft: what is…