wasi-nn-safe

Introduction

This library provides some convenient and safe wrapper APIs for wasi-nn system calls, which can replace the unsafe [wasi-nn] APIs.

toml [dependencies] wasi-nn-safe = "0.1"

Quick Start

```rust use wasinnsafe::{ExecutionTarget, GraphBuilder, GraphEncoding, TensorType};

fn test(modelpath: &'static str) -> Result<(), wasinnsafe::Error> { // prepare input and output buffer. let input = vec![0f32; 224 * 224 * 3]; let inputdim = vec![1, 224, 224, 3]; // the input and output buffer can be any sized type, such as u8, f32, etc. let mut output_buffer = vec![0f32; 1001];

// build a tflite graph from file.
let graph = GraphBuilder::new(GraphEncoding::TensorflowLite, ExecutionTarget::CPU)
    .build_from_files([model_path])?;
// init graph execution context for this graph.
let mut ctx = graph.init_execution_context()?;
// set input
ctx.set_input(0, TensorType::F32, &input_dim, &input)?;
// do inference
ctx.compute()?;
// copy output to buffer
let output_bytes = ctx.get_output(0, &mut output_buffer)?;

assert_eq!(output_bytes, output_buffer.len() * std::mem::size_of::<f32>());
Ok(())

} ```

Note

This crate is experimental and will change to adapt the upstream [wasi-nn specification].

Now version is based on git commit 0f77c48ec195748990ff67928a4b3eef5f16c2de

Related Links

• [wasi-nn specification]
• [wasi-nn]

License

This project is licensed under the Apache 2.0 license. See [LICENSE] for more details.