MCPcopy Index your code
hub / github.com/AliaksandrSiarohin/cuda-gridsample-grad2

github.com/AliaksandrSiarohin/cuda-gridsample-grad2 @main

Chat with this repo
repository ↗ · DeepWiki ↗ · + Follow
61 symbols 124 edges 6 files 0 documented · 0% updated 3y ago★ 902 open issues
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

Cuda-based grid sample implimentation with second order derivative support.

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)

Core symbols most depended-on inside this repo

Shape

Method 44
Function 9
Class 8

Languages

Python95%
C++5%

Modules by API surface

test3d.py17 symbols
test2d.py17 symbols
cuda_gridsample.py14 symbols
stylegan_gridsample.py8 symbols
gridsample_cuda.cpp3 symbols
naive_gridsample.py2 symbols

For agents

$ claude mcp add cuda-gridsample-grad2 \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact

Ask about this repo answers extend the page