yu4u/cutout-random-erasing
Cutout / Random Erasing implementation, especially for ImageDataGenerator in Keras
This tool helps machine learning engineers improve the accuracy and robustness of their image classification models. By randomly masking parts of training images, it creates more diverse training data. You provide your existing image datasets, and it outputs augmented versions for better model training.
168 stars. No commits in the last 6 months.
Use this if you are training convolutional neural networks for image tasks and want to apply advanced data augmentation techniques like Cutout or Random Erasing.
Not ideal if you are working with non-image data or if your machine learning framework does not easily integrate with Keras's ImageDataGenerator.
Stars
168
Forks
38
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Aug 26, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yu4u/cutout-random-erasing"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TencentARC/GFPGAN
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
bamos/dcgan-completion.tensorflow
Image Completion with Deep Learning in TensorFlow
MathiasGruber/PConv-Keras
Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions"....
leehomyc/Faster-High-Res-Neural-Inpainting
High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis
alexandre01/deepsvg
[NeurIPS 2020] Official code for the paper "DeepSVG: A Hierarchical Generative Network for...