Icevision

<div align="center"> <img src="images/icevision-logo-slogan.png" alt="logo" width="535px" style="display: block; margin-left: auto; margin-right: auto"/> <h2><b>An Agnostic Computer Vision Framework</b></h2> </div>

---

</div>

---

IceVision is the first agnostic computer vision framework to offer a curated collection with hundreds of high-quality pre-trained models from Torchvision, Open MMLab's MMDetection, Ultralytic's YOLOv5, Ross Wightman's EfficientDet and soon PyTorch Image Models. It orchestrates the end-to-end deep learning workflow allowing to train networks with easy-to-use robust high-performance libraries such as PyTorch-Lightning and Fastai.

IceVision Unique Features:

• Data curation/cleaning with auto-fix

• Access to an exploratory data analysis dashboard

• Pluggable transforms for better model generalization

• Access to hundreds of neural net models

• Access to multiple training loop libraries

• Multi-task training to efficiently combine object detection, segmentation, and classification models

<!-- Not included in docs - start -->

Installation

pip install icevision[all]

For more installation options, check our docs.

Important: We currently only support Linux/MacOS.

<!-- Not included in docs - end -->

Quick Example: How to train the Fridge Objects Dataset

<a href="https://colab.research.google.com/github/airctic/icevision/blob/master/notebooks/getting_started_object_detection.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>

Happy Learning!

If you need any assistance, feel free to:

Join our Forum