Skip to content

Latest commit

 

History

History
33 lines (23 loc) · 1.15 KB

README.md

File metadata and controls

33 lines (23 loc) · 1.15 KB

MiniGo

This is an implementation of MiniGo using Swift for TensorFlow. The implementation is adapted from the MLPerf reference model.

Note: Due to temporary limitations, we only support inference (self-play) for now. We hope to soon lift these restrictions.

Parameters like "board size" and "simulations per move" are defined as constants at the top of Sources/MiniGo/main.swift and can be modified.

Getting started

Install Swift for TensorFlow

Building MiniGo requires a Swift for TensorFlow toolchain. To get a toolchain, you can:

  1. Download a pre-built package.
  2. Compile a toolchain from source.

Usage

# Run inference (self-plays).
cd swift-models
swift run -c release MiniGoDemo