microcnn 0.1.1

A minimal CNN framework in Rust with Quantization
Documentation
  • Coverage
  • 30.99%
    53 out of 171 items documented1 out of 91 items with examples
  • Size
  • Source code size: 92.4 kB This is the summed size of all the files inside the crates.io package for this release.
  • Documentation size: 10.68 MB This is the summed size of all files generated by rustdoc for all configured targets
  • Ø build duration
  • this release: 21s Average build duration of successful builds.
  • all releases: 22s Average build duration of successful builds in releases after 2024-10-23.
  • Links
  • fauzisho/microcnn
    1 0 0
  • crates.io
  • Dependencies
  • Versions
  • Owners
  • fauzisho

microcnn

A minimal CNN framework in Rust with INT8 and INT4 quantization.

Features

  • FP32, INT8, and INT4 inference
  • Post-training quantization with calibration
  • Reference LeNet-5 implementation for MNIST

Quick Start

[dependencies]
microcnn = "0.1"

use microcnn::lenet::lenet;

let mut net = lenet(false);
net.load("data/lenet.raw");

Running the Example

cargo run --example lenet_mnist

Requires MNIST data files in data/.

License

MIT