Random Augmentation

This project is deploying web demo of IMGAUG [option: Random augment] for who want to augment images easily.

Description

Random Augmentation helps you with augmenting images for your machine learning projects. It converts a set of input images into a new, much larger set of slightly altered images.

Features

• Mix many augmentation techniques.
• affine transformations, gausian noise, dropout, blurring, contrast changes, cropping/padding, ...
• Optimized for high performance.
• Easy to use.

Run on your Local

Using Docker

$ git clone https://github.com/Wook-2/RandomAugmentation.git

$ cd RandomAugmentation

$ docker build -t {your_image_name} .

$ docker run -it --rm -p 8000:8000 {your_image_name}

then visit : localhost:8000

Using Curl

$ curl -X POST "https://master-random-augmentation-wook-2.endpoint.ainize.ai/augment" \
-H "accept: application/octet-stream" -H "Content-Type: multipart/form-data" \
-F "file=@{your_image_path};type=image/jpeg" \
-F "number={numbers of augmented images}" -o {output_file_name}.zip

Fill in {your_image_path, numbers of augmented images, output_file_name} to suit your situation.

REFERENCE

• IMGAUG : https://github.com/aleju/imgaug

• Ainize : https://ainize.ai/