The service for the demonstration of transforms in Albumentations library
This service is created to demonstrate abilities of the Albumentations - a library for efficient image augmentations. Link to my article about augmentations selection and why this service can be useful
I don't actively support this tool anymore but you can run it locally or use one of the deployed instances.
If you would like to run the service locally follow the installation instruction.
You can find the online version of this tool here: https://albumentations-demo.herokuapp.com/ (it will be stopped soon).
It is also deployed as a Hugging Face space: https://huggingface.co/spaces/ilarchenko/albumentations-demo
As alternative you can use the fork supported and deployed by the Albumentations team https://demo.albumentations.ai/
git clone https://github.com/IliaLarchenko/albumentations-demo
cd albumentations-demo
pip install -r requirements.txt
streamlit run src/app.py
If you want to work with you own images just replace the last line with:
streamlit run src/app.py -- --image_folder PATH_TO_YOUR_IMAGE_FOLDER
If your images have some unusual proportions you can use image_width
parameter to set the width in pixels of the original image to show. The width of the transformed image and heights of both images will be computed automatically. Default value of width is 400
.
streamlit run src/app.py -- --image_width INT_VALUE_OF_WIDTH
In your terminal you will see the link to the running local service similar to :
You can now view your Streamlit app in your browser.
Network URL: http://YOUR_LOCAL_IP:8501
External URL: http://YOUR_GLOBAL_IP:8501
Just follow the local link to use the service.
You can run the service in docker:
docker-compose up
It will be available at http://DOCKER_HOST_IP:8501
The interface is very simple and intuitive:
In the professional mode you can:
Be aware that in Professional mode some combination of parameters of different transformations can be invalid. You should control it.