#bindings #tensorflow #machine-learning #ffi #cross-platform


A safe Rust wrapper of TensorFlow Lite C API supporting x86_64 and ARM (iOS, Android)

6 releases

0.4.1 Feb 1, 2022
0.4.0 Jan 31, 2022
0.3.3 Nov 25, 2021
0.3.2 Oct 4, 2021

#36 in Machine learning

Download history 52/week @ 2022-01-31 27/week @ 2022-02-07 3/week @ 2022-02-14 8/week @ 2022-02-21 34/week @ 2022-03-14 22/week @ 2022-03-21 1/week @ 2022-03-28 11/week @ 2022-04-04 7/week @ 2022-04-11 1/week @ 2022-04-18 42/week @ 2022-04-25 62/week @ 2022-05-02 42/week @ 2022-05-09

147 downloads per month

MIT license

944 lines

This crate is a safe Rust wrapper of TensorFlow Lite C API. Its API is very similar to that of TensorFlow Lite Swift API.

Supported Targets

Targets below are tested. However, others may work, too.

  • iOS: aarch64-apple-ios and x86_64-apple-ios
  • MacOS: x86_64-apple-darwin
  • Linux: x86_64-unknown-linux-gnu
  • Android: aarch64-linux-android and armv7-linux-androideabi
  • Windows (see details)

See compilation section to see build instructions for your target. Please read Optimized Build section carefully.


  • xnnpack - Compiles XNNPACK and allows you to use XNNPACK delegate. See details of XNNPACK on here.
  • xnnpack_qs8 - Compiles XNNPACK with additional build flags to accelerate inference of operators with symmetric quantization. See details in this blog post. Implies xnnpack.
  • xnnpack_qu8 - Similar to xnnpack_qs8, but accelerates few operators with asymmetric quantization. Implies xnnpack.

Note: xnnpack is already enabled for iOS, but xnnpack_qs8 and xnnpack_qu8 should be enabled manually.


The example below shows running inference on a TensorFlow Lite model.

use tflitec::interpreter::{Interpreter, Options};
use tflitec::tensor;
use std::path::MAIN_SEPARATOR;

// Create interpreter options
let mut options = Options::default();
options.thread_count = 1;

// Load example model which outputs y = 3 * x
let path = format!("tests{}add.bin", MAIN_SEPARATOR);
let interpreter = Interpreter::with_model_path(&path, Some(options))?;
// Resize input
let input_shape = tensor::Shape::new(vec![10, 8, 8, 3]);
interpreter.resize_input(0, input_shape)?;
// Allocate tensors if you just created Interpreter or resized its inputs

// Create dummy input
let input_element_count = 10 * 8 * 8 * 3;
let data = (0..input_element_count).map(|x| x as f32).collect::<Vec<f32>>();

let input_tensor = interpreter.input(0)?;
assert_eq!(input_tensor.data_type(), tensor::DataType::Float32);

// Copy input to buffer of first tensor (with index 0)
// You have 2 options:
// Set data using Tensor handle if you have it already
// Or set data using Interpreter:
assert!(interpreter.copy(&data[..], 0).is_ok());

// Invoke interpreter

// Get output tensor
let output_tensor = interpreter.output(0)?;

assert_eq!(output_tensor.shape().dimensions(), &vec![10, 8, 8, 3]);
let output_vector = output_tensor.data::<f32>().to_vec();
let expected: Vec<f32> = data.iter().map(|e| e * 3.0).collect();
assert_eq!(expected, output_vector);
# // The line below is needed for doctest, please ignore it
# Ok::<(), tflitec::Error>(())


Current version of the crate builds r2.6 branch of tensorflow project. Compiled dynamic library or Framework will be available under OUT_DIR (see cargo documentation) of tflitec. You won't need this most of the time, because the crate output is linked appropriately. For all environments and targets you will need to have:

Optimized Build

To build TensorFlow for your machine with native optimizations or pass other --copts to Bazel, set environment variable below:

BAZEL_COPTS="OPT1 OPT2 ..." # space seperated values will be passed as `--copt=OPTN` to bazel
BAZEL_COPTS="-march=native" # for native optimized build

Some OSs or targets may require additional steps.


  • Android NDK
  • Following environment variables should be set appropriately to build TensorFlow for android:
  • Bindgen needs extra arguments, so set the environment variable below:
# Set appropriate host tag and target name.
# see https://developer.android.com/ndk/guides/other_build_systems
HOST_TAG=darwin-x86_64 # as example
TARGET_TRIPLE=arm-linux-androideabi # as example
-I${ANDROID_NDK_HOME}/sources/cxx-stl/llvm-libc++/include/ \
-I${ANDROID_NDK_HOME}/sysroot/usr/include/ \
  • (Recommended) cargo-ndk simplifies cargo build process.


Windows support is experimental. It is tested on Windows 10. You should follow instructions in the Setup for Windows section on TensorFlow Build Instructions for Windows. In other words, you should install following before build:

  • Python 3.8.x 64 bit (the instructions suggest 3.6.x but this package is tested with 3.8.x)
  • Bazel, supported versions: [3.7.2, 3.99.0]
  • MSYS2
  • Visual C++ Build Tools 2019

Do not forget to add relevant paths to %PATH% environment variable by following the TensorFlow Build Instructions for Windows carefully (the only exception is the Python version).

No runtime deps