Metadata-Version: 2.1
Name: micromind
Version: 0.0.3
Summary: MicroMind
Keywords: feed,reader,tutorial
Author-email: Francesco Paissan & others <francescopaissan@gmail.com>
Requires-Python: >=3.9
Description-Content-Type: text/markdown
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3
Requires-Dist: torch
Requires-Dist: torchinfo
Requires-Dist: huggingface_hub
Requires-Dist: onnx
Requires-Dist: onnx_tf==1.10.0
Requires-Dist: onnx-simplifier==0.4.13
Requires-Dist: onnxruntime==1.13.1
Requires-Dist: openvino-dev==2022.3.0
Requires-Dist: openvino2tensorflow==1.34.0
Requires-Dist: tensorflow_datasets==4.8.1
Requires-Dist: tensorflow==2.11.0
Requires-Dist: tensorflow_probability
Requires-Dist: black ; extra == "dev"
Requires-Dist: bumpver ; extra == "dev"
Requires-Dist: flake8 ; extra == "dev"
Requires-Dist: isort ; extra == "dev"
Requires-Dist: pip-tools ; extra == "dev"
Requires-Dist: pytest ; extra == "dev"
Project-URL: Homepage, https://github.com/fpaissan/micromind
Provides-Extra: dev

<div align="center">    
 
[![Paper](http://img.shields.io/badge/paper-arxiv.1001.2234-B31B1B.svg)](https://arxiv.org/abs/2110.00337)

</div>

This repository is a collection of our efforts towards the design, implementation and evaluation of ML techniques in the field of tinyML. 

Here is a list of things you can do with the `phinet` package:
 - [image classification](recipes/image_classification)

## To install the package 

```setup
pip install git+https://github.com/fpaissan/phinet
```

## Cite us
```
@article{10.1145/3510832,
	author = {Paissan, Francesco and Ancilotto, Alberto and Farella, Elisabetta},
	title = {PhiNets: A Scalable Backbone for Low-Power AI at the Edge},
	year = {2022},
	publisher = {Association for Computing Machinery},
	address = {New York, NY, USA},
	url = {https://doi.org/10.1145/3510832},
	doi = {10.1145/3510832},
	journal = {ACM Trans. Embed. Comput. Syst.},
}
```
<!---

## Pre-trained Models

You can download pretrained models here:

- [My awesome model](https://drive.google.com/mymodel.pth) trained on ImageNet using parameters x,y,z. 

>📋  Give a link to where/how the pretrained models can be downloaded and how they were trained (if applicable).  Alternatively you can have an additional column in your results table with a link to the models.

## Results

Our model achieves the following performance on :

### [Image Classification on ImageNet](https://paperswithcode.com/sota/image-classification-on-imagenet)

| Model name         | Top 1 Accuracy  | Top 5 Accuracy |
| ------------------ |---------------- | -------------- |
| My awesome model   |     85%         |      95%       |

> Include a table of results from your paper, and link back to the leaderboard for clarity and context. If your main result is a figure, include that figure and link to the command or notebook to reproduce it. 

--->

