stratospark/keras-multiprocess-image-data-generator
Accelerating Deep Learning with Multiprocess Image Augmentation in Keras
This project dramatically speeds up the process of generating diverse image variations for deep learning models. By taking your existing image datasets, it quickly creates augmented versions (rotations, flips, zooms, etc.), which are then used to train your image classification or object detection models faster. This is invaluable for deep learning researchers and practitioners who need to train models efficiently with limited datasets.
319 stars. No commits in the last 6 months.
Use this if you are training deep learning models with Keras and find that generating augmented images is a bottleneck in your workflow.
Not ideal if your deep learning models are not built with Keras or if you don't typically use image augmentation.
Stars
319
Forks
65
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jun 19, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stratospark/keras-multiprocess-image-data-generator"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TorchIO-project/torchio
Medical imaging processing for AI applications.
aleju/imgaug
Image augmentation for machine learning experiments.
makcedward/nlpaug
Data augmentation for NLP
mdbloice/Augmentor
Image augmentation library in Python for machine learning.
BloodAxe/pytorch-toolbelt
PyTorch extensions for fast R&D prototyping and Kaggle farming