This Repository Is Deprecated
This library has been renamed and moved to wasmedge_tensorflow_interface
. Please follow the resulting new wasmedge_tensorflow_interface crate for further development. No further development will take place in this repository.
SSVM Tensorflow Interface
A Rust library that provides Rust to WebAssembly developers with syntax for using tensorflow functionality when their Wasm is being executed on SecondState's SSVM.
From a high-level overview here, we are essentially building a tensorflow interface that will allow the native operating system (which SSVM is running on) to play a part in the runtime execution. Specifically, play a part in using tensorflow with graphs and input and output tensors as part of Wasm execution.
How to use this library
Rust dependency
Developers will add the ssvm_interface_interface
crate as a dependency to their Rust -> Wasm
applications. For example, add the following line to the application's Cargo.toml
file.
[dependencies]
ssvm_tensorflow_interface = "^0.1.3"
Developers will bring the functions of ssvm_tensorflow_interface
into scope within their Rust -> Wasm
application's code. For example, adding the following code to the top of their `main.rs
use ssvm_process_interface;
Image Loading And Conversion
let mut file_img = open.unwrap;
let mut img_buf = Vec new;
file_img.read_to_end.unwrap;
let flat_img = load_jpg_image_to_rgb32f;
// The flat_img is a vec<f32> which contains normalized image in rgb32f format and resized to 224x224.
Create Session
// The mod_buf is a vec<u8> which contains model data.
let mut session = new;
Or use the ssvm_tensorflow_interface::ModelType::TensorFlowLite
to specify the tflite
models.
Prepare Input Tensors
// The flat_img is a vec<f32> which contains normalized image in rgb32f format.
session.add_input
.add_output;
Run TensorFlow Models
session.run;
Convert Output Tensors
let res_vec: = session.get_output;
Build And Execution
The output WASM file will be at target/wasm32-wasi/debug/
or target/wasm32-wasi/release
.
Please refer SSVM with tensorflow extension for WASM execution.
Crates.io
The official crate is available at crates.io.