Skip to content
Fabian Fichter edited this page Apr 26, 2022 · 11 revisions

Note: This page is under construction

1. Check that your GPU supports CUDA

https://developer.nvidia.com/cuda-gpus

2. Install CUDA

https://developer.nvidia.com/cuda-downloads

3. Download training data generator

https://github.com/ianfab/variant-nnue-tools/releases

4. Generate training data

5. Install git

6. Clone training data generator

https://github.com/ianfab/variant-nnue-pytorch.git

7. Install dependencies

8. Apply code changes

9. Compile training data loader

compile_data_loader.bat

10. Convert existing network (optional)

11. Run train.py

12. Convert checkpoint to NNUE network

Clone this wiki locally