augvid 0.0.3

A collection of video augmentation layers

AugVid

AugVid is a collection of augmentation layers for videos, inspired by the corresponding image preprocessing layers from tf.keras.

demo

Installation

pip install augvid

Getting Started

The augmentation layers can be added during the model construction:

import tensorflow as tf
from augvid import RandomVideoBrightness, RandomHorizontalVideoFlip


model = tf.keras.Sequential([
    RandomVideoBrightness(max_delta=0.1),
    RandomHorizontalVideoFlip(),
    # add more layers here
])

Demo

To generate demo video, first install the required dependencies:

pip install 'augvid[dev]'

Then run:

python demo.py --video <PATH_TO_VIDEO>