Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/hayashi-yudai/ml_models
Implementation of machine learning models by Python with Tensorflow. ArcFace/UNet/ACoL
https://github.com/hayashi-yudai/ml_models
image-processing keras-tensorflow machine-learning pipenv python python3 tensorflow
Last synced: 2 months ago
JSON representation
Implementation of machine learning models by Python with Tensorflow. ArcFace/UNet/ACoL
- Host: GitHub
- URL: https://github.com/hayashi-yudai/ml_models
- Owner: Hayashi-Yudai
- License: mit
- Created: 2019-04-21T11:52:01.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2023-05-01T08:28:13.000Z (over 1 year ago)
- Last Synced: 2023-05-01T10:03:47.994Z (over 1 year ago)
- Topics: image-processing, keras-tensorflow, machine-learning, pipenv, python, python3, tensorflow
- Language: Python
- Homepage:
- Size: 95 MB
- Stars: 4
- Watchers: 3
- Forks: 6
- Open Issues: 9
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ML Models
[](https://opensource.org/licenses/MIT)
This repository implements various machine learning models with Python/Tensorflow. I treat mainly "Image processing" in it.
| Model | Paper | Status |
| :-----: | :------------------------------: | :----------------: |
| U-Net | https://arxiv.org/abs/1505.04597 | :white_check_mark: |
| ACoL | https://arxiv.org/abs/1804.06962 | :white_check_mark: |
| Arcface | https://arxiv.org/abs/1801.07698 | :white_check_mark: |
You can use these models for training or validation.
## Requirements
- Python 3.6>=
- Tensorflow 2.4.0>=
- PIL
- Imgaug
- Numpy
- Scipy
- Matplotlib
I am managing these libraries with pipenv. If you do not have pipenv, install with pip
```bash
pip install pipenv
```
You can see [latest document](https://docs.pipenv.org/en/latest/) to understand the usage more
To install all libraries, you run
```
$ pipenv install
```
## Usage
How to use each model is written in README in the each model. Basically you can training with
```
$ pipenv run python -m $(MODEL_NAME)/train $(options)
```
## Future Plans
- Modularize this repository to enable users to import whole models
## Licence
"ML models" is licenced under the MIT licence.
(C) Copyright 2023, Yudai Hayashi