lartpang/tta.pytorch
Test-Time Augmentation library for Pytorch
This library helps improve the reliability of your deep learning models for image analysis. It takes raw image data, applies various transformations (like flips or resizing), and then combines the results from your model's predictions on these transformed images. Scientists, medical professionals, or quality control engineers who use deep learning for image classification or segmentation will find this useful.
No commits in the last 6 months.
Use this if you need to boost the robustness and accuracy of your image classification or segmentation model predictions by accounting for slight variations in input images.
Not ideal if you are not working with PyTorch for image classification or segmentation tasks, or if your primary goal is data augmentation during model training rather than inference.
Stars
83
Forks
6
Language
Python
License
—
Category
Last pushed
Jan 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lartpang/tta.pytorch"
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