TinyML Compiler - Tiny Machine Learning Compiler
Project description
TinyMLC - Tiny Machine Learning Compiler
Automatic generation + optimization + deployment of MCU neural networks.
Features
- Automatic network generation (ANG)
- ONNX / TFLite model conversion
- 7 optimization passes (constant folding, DCE, CSE, Simplify, fusion, algebraic simplify, memory reuse)
- 31 pure-C operators (int8 quantization)
- Multi-backend support (Host / ARM / RISC-V)
- Qt6 GUI
- Accelerator library support (CMSIS-NN / NMSIS)
Quick Start
pip install -e . python main.py generate --task-type classification --max-macs 100000 cd TinyGUI/build && ./TinyGUI
Documentation
User guide: docs/guide_en.txt Porting: docs/porting_en.txt Operator status: docs/ops_en.txt
License
Apache License 2.0
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file tinymlc-0.1.0.tar.gz.
File metadata
- Download URL: tinymlc-0.1.0.tar.gz
- Upload date:
- Size: 1.7 MB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
027212e5e8d0f9b05c604b72cc4cd3821cf78a653f032d86040930871fb112aa
|
|
| MD5 |
3495e4221a3d7bda169cfc24d0229923
|
|
| BLAKE2b-256 |
d4f669af7225c762e0e59cda89c37852a4883c09c9654cc8824655ab7b20a8ff
|
File details
Details for the file tinymlc-0.1.0-py3-none-any.whl.
File metadata
- Download URL: tinymlc-0.1.0-py3-none-any.whl
- Upload date:
- Size: 98.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
fcf6c232f38fe2bc96d36b5fdb8049580c36c5b2e476359ee74a99aa5a690cae
|
|
| MD5 |
6b2e9661b5e136ebf0608c978cda3b4b
|
|
| BLAKE2b-256 |
f58b15b101b73293342a3772ee3337c7a9c88f7a44d18a231e3056b63205978f
|
