Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/smallstepman/ic-mnist
`dfx new --type=rust` + burn-rs MNIST web inference example
https://github.com/smallstepman/ic-mnist
Last synced: 5 days ago
JSON representation
`dfx new --type=rust` + burn-rs MNIST web inference example
- Host: GitHub
- URL: https://github.com/smallstepman/ic-mnist
- Owner: smallstepman
- Created: 2023-05-25T12:27:50.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-05-25T15:40:11.000Z (over 1 year ago)
- Last Synced: 2024-08-02T06:19:20.568Z (3 months ago)
- Language: Rust
- Size: 1.42 MB
- Stars: 7
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-internet-computer - ic-mnist - MNIST (considered to be `hello world` of machine learning) running on IC using [burn](https://github.com/tracel-ai/burn) crate. [Try it here](https://jsi2g-jyaaa-aaaam-abnia-cai.icp0.io/). (Decentralized AI / Solana)
README
# ic-mnist
1. The frontend provides a canvas where users can draw a digit.
2. The drawn digit is then sent to the backend canister running `burn-rs` for inference using a pretrained MNIST model.
3. The backend performs the inference and returns the predicted digit to the frontend.# Installation
To set up the project, follow these steps:
0. Have Rust and Nodejs installed.
1. Installl [IC-SDK](https://github.com/dfinity/sdk/) (building from `master` branch because we need `gzip` feature which is not available in the latest release)
``` bash
git clone https://github.com/dfinity/sdk.git ./ic-sdk
cargo build --manifest-path=ic-sdk/Cargo.toml -p dfx
```
2. Clone and deploy this project
``` bash
git clone https://github.com/smallstepman/ic-mnist.git ./ic-mnist
cd ic-mnist
../ic-sdk/target/debug/dfx start --background --clean
../ic-sdk/target/debug/dfx deploy
```# License
The code in this repository is licensed under the MIT License.# Acknowledgements
Based on `burn` (https://burn-rs.github.io), backend and frontend implementation copied from this example https://github.com/burn-rs/burn/tree/main/examples/mnist-inference-web,