bhky/targetran
Python library for data augmentation in object detection or image classification model training
When training machine learning models for computer vision, like those that find objects in images or classify what's in a picture, you often need to create more training data. This tool takes your existing images and their corresponding bounding box labels, then generates transformed versions of them, outputting new images with correctly adjusted bounding boxes. It's for data scientists and machine learning engineers working on object detection or image classification projects.
No commits in the last 6 months. Available on PyPI.
Use this if you need to augment your image datasets with bounding box transformations for object detection or image classification, especially when working with TensorFlow or PyTorch and potentially using TPUs on platforms like Google Colab or Kaggle.
Not ideal if your computer vision task does not involve rectangular bounding boxes or if you require highly specialized, non-affine transformations not included in typical augmentation libraries.
Stars
21
Forks
2
Language
Python
License
MIT
Category
Last pushed
Jan 24, 2025
Commits (30d)
0
Dependencies
2
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/bhky/targetran"
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