🔁 (Work in Progress Project) Full application for auto-rotating images using RotNet.

This repository came up after seeing the amazing work that Daniel Saez did with the RotNet model for predicting the rotation angle of an image to correct its orientation. I wanted to understand how it actually works and build a easier UI for running inference no matter the knowledge that you have about it to make this more accessible to the community.

Coming soon...

1. Python 3.7+.
2. docker.
3. docker-compose.

Usage of virtualenv is recommended for package library / runtime isolation.

To run the server, please execute the following from the root directory:

1. Change directory into the api folder.

cd api/

2. Setup virtual environment.

3. Install dependencies.

pip3 install -r requirements.lock

4. Run API server as a python module.

python3 -m src

Or just simply run the docker-compose script from the root directory.

docker-compose up -d --build

Rotate an image given its URL or the image itself.

curl -d '{"image_url": URL}' -H "Content-Type: application/json" -X POST https://public-endpoint.com/rotate

{
    "error": false,
    "response": {
        "image_base64": "IMAGE_RESULT_ENCODED_IN_BASE64"
    }
}

1. Run Auto Rotate locally.

2. Run tests from api module.

   python3 -m unittest discover -v
   

Create a new Python file called test_*.py in test.* (inside api folder) with the following structure:

import unittest


class NewTest(unittest.TestCase):

    def test_v0(self):
        expected = 5
        result = 2 + 3
        self.assertEqual(expected, result)

Again, kudos to Daniel Saez for this amazing model that he came up.

MIT © Auto Rotate