Cuda implementation for gridsample with second derivative support
License: MIT License
For the forward and backward pass it uses the pytorch version of grid sample. Only the second backward is implimented here.
Tested only with Pytorch 10.1 and 10.2
Reflection padding is not supported
Usage:
import cuda_gridsample as cu
cu.grid_sample_2d(image, optical, padding_mode='border', align_corners=True)
cu.grid_sample_3d(volume, optical, padding_mode='border', align_corners=True)
Hi, Siarohin. I'm using cuda_gridsample in my code to calculate the second backward of gridsample, but whenever i'm trying to save my torch model, an unexpected error always occur, i have tried torch.save() and dill.dump(), but neither of them ran successfully, do you have any idea what happened, any suggestions will be helpful.
Below are the error i encounted while running my code. I'm using python 3.9.13 and torch 1.10.0+cu113.
Hi @AliaksandrSiarohin,
thank you for this great project and your efforts on this! I was wondering under which license your code is available, since I could not find any information on this in the repo. Would you care to share any info on this and add a license to the repo?
Thanks for your work! It really works on my single GPU!!! However, I found it can't converage in multi-gpus. Have you tested this code on multi-gpus?
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 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.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
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.