#neural-network #tensorflow #onnx

tract-tensorflow

Tiny, no-nonsense, self contained, TensorFlow and ONNX inference

132 releases

0.21.7 Sep 23, 2024
0.21.6 Jul 24, 2024
0.21.5 May 11, 2024
0.21.2 Mar 29, 2024
0.1.1 Nov 2, 2018

#1071 in Machine learning

Download history 66/week @ 2024-07-01 8/week @ 2024-07-08 26/week @ 2024-07-15 148/week @ 2024-07-22 57/week @ 2024-07-29 7/week @ 2024-08-05 12/week @ 2024-08-12 2/week @ 2024-08-19 15/week @ 2024-08-26 4/week @ 2024-09-02 8/week @ 2024-09-09 22/week @ 2024-09-16 340/week @ 2024-09-23 73/week @ 2024-09-30 28/week @ 2024-10-07 14/week @ 2024-10-14

457 downloads per month
Used in 2 crates

MIT/Apache

1.5MB
14K SLoC

Tract TensorFlow module

Tiny, no-nonsense, self contained, portable inference.

Example

use tract_tensorflow::prelude::*;

// build a simple model that just add 3 to each input component
let tf = tensorflow();
let mut model = tf.model_for_path("tests/models/plus3.pb").unwrap();

// set input input type and shape, then optimize the network.
model.set_input_fact(0, f32::fact(&[3]).into()).unwrap();
let model = model.into_optimized().unwrap();

// we build an execution plan. default input and output are inferred from
// the model graph
let plan = SimplePlan::new(&model).unwrap();

// run the computation.
let input = tensor1(&[1.0f32, 2.5, 5.0]);
let mut outputs = plan.run(tvec![input]).unwrap();

// take the first and only output tensor
let mut tensor = outputs.pop().unwrap();

assert_eq!(tensor, rctensor1(&[4.0f32, 5.5, 8.0]));

Dependencies

~17–32MB
~566K SLoC