Crate tract_tensorflow

Tensorflow Deploy, Tensorflow module

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

Example

use tract_core::*;

// build a simple model that just add 3 to each input component
let model = tract_tensorflow::for_path("tests/models/plus3.pb").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 = ndarray::arr1(&[1.0f32, 2.5, 5.0]);
let mut outputs = plan.run(tvec![input.into()]).unwrap();

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

// unwrap it as array of f32
let tensor = tensor.take_f32s().unwrap();
assert_eq!(tensor, ndarray::arr1(&[4.0, 5.5, 8.0]).into_dyn());

For a more serious example, see inception v3 example.

Re-exports

pub use self::model::for_path;

pub use self::model::for_reader;

Modules

model

ops

optim

tensor

tfpb

Generated protobuf codec for Tensorflow models, plus a handful of helper for writting tests.

Traits

ToTensorflow