Introduce keras-aug
: a library that includes Keras 3 preprocessing & augmentation layers
#20050
james77777778
started this conversation in
Show and tell
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Repository: https://github.com/james77777778/keras-aug
If you are looking for a
torchvision
-like preprocessing & augmentation pipeline, check out this repo.A demo app is available here:
Feel free to contact me if you have any ideas or encounter any issues.
Description
KerasAug is a library that includes Keras 3 preprocessing and augmentation layers, providing support for various data types such as images, labels, bounding boxes, segmentation masks, and more.
Note
See
docs/*.py
for the GIF generation. YOLOV8-like pipeline for bounding boxes and segmentation masks.KerasAug aims to provide fast, robust and user-friendly preprocessing and augmentation layers, facilitating seamless integration with Keras 3 and
tf.data
.The APIs largely follow
torchvision
, and the correctness of the layers has been verified through unit tests.Why KerasAug
tf.data
, offering a performant and scalable data pipeline.torchvision
.Quickstart
Rock, Paper and Scissors Image Classification
The above example runs with all backends (JAX, TensorFlow, Torch).
More Examples
YOLOV8 object detection pipeline
YOLOV8 semantic segmentation pipeline
Beta Was this translation helpful? Give feedback.
All reactions