Comments (2)
Hi and thanks for your interest!
k_i
refers to the kernel size/the number of basis functions in dimension i
(0 < i < d
). This results in product_i(k_i)
overall basis functions/trainable parameters.
When talking about uniform knot vectors, we mean that knot vectors are placed uniformly inside each kernel. For example, in case you have a one-dimensional kernel with kernel size = 5, knot vectors are placed at [-1, -0.5, 0, 0.5, 1]
. Each knot vector refers to a single basis function/kernel weight, it is not dependent on the number of vertices.
from pytorch_spline_conv.
thank you for your answer! this helped a lot!
from pytorch_spline_conv.
Related Issues (20)
- Possibility of creating a tutorial? HOT 6
- Tutorial Segmentation Fault HOT 2
- Performing Spline Convolution for evaluating Spline Surface HOT 1
- Only datatype float excepted HOT 8
- Installation issues HOT 1
- Use pseudo coordinates with gradients HOT 4
- Using spline_conv to approximate gradients on a graph HOT 3
- graph preprocessing for SplineConv layer HOT 2
- Cannot import torch-spline-conv when installed from pip wheel in Torch 1.9.0 HOT 19
- Error importing CPU wheel on machine with CUDA HOT 1
- ImportError occurs in Google Colab HOT 2
- CUDA libraries not generated when building pytorch-spline-conv HOT 7
- Cannot install pyg without pytorch_spline_conv in conda HOT 3
- Plotting Learned Filters HOT 2
- ImportError: cannot import name 'SplineConv' from 'torch_spline_conv' HOT 1
- CUDA error: an illegal memory access HOT 6
- Question: Similiar to Receptive Field HOT 4
- GLIBC incompatibility issue on RHEL8 HOT 5
- is:issue is:open SplineConv issue with 1024 x 1024 x 3 image HOT 14
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch_spline_conv.