An Agnostic Computer Vision Framework.
Project description
An Agnostic Object Detection Framework
Note: "We Need Your Help" If you find this work useful, please let other people know by starring it, and sharing it. Thank you!
Contributors
Installation
pip install icevision[all]
pip install pycocotools@https://github.com/lgvaz/cocoapi/archive/master.zip#subdirectory=PythonAPI&egg=pycocotools-2.0
pip install omegaconf effdet@https://github.com/rwightman/efficientdet-pytorch/archive/master.zip#egg=effdet-0.1.4
For more installation options, check our docs.
Important: We currently only support Linux/MacOS.
Quick Example: How to train the PETS Dataset
The Problem We Are Solving
- Object dectection datasets come in different sizes and most impotantly have different annotations formats ranging from the stanndard formarts such COCO and VOC to more self-tailored formats
- When new object detection models are released with some source code, the latter is very often written in non-portable way: The source code is difficult to use for other datasets because of some hard-coded parts coupled with self developed tweaks
- Both researchers and DL coders have to deploy a lot of effort to use many SOTA models for their own use-cases and/or to craft an enhanced model based on those already published
Our Solution
IceVision library provides some elegant solutions in those 2 fundamental components:
1- A Unified Data API
Out of the box, we offer several annotation parsers that translates different annotation formats into a very flexibe parser:
- By default, we offer differents standard format parsers such as COCO and VOC.
- We host a community curated parsers where community contributors publish their own parsers to be shared, and therefore save time and energy in creating similar parsers over and over.
- We provide some intuitive tutorials that walk you through the steps of creating your own parser. Please, consider sharing it with the whole community.
2- A Universal Adapter to different DL Libraries
- IceVision provides a universal adapter that allows you to hook up your dataset to the DL library of your choice (fastai, Pytorch Lightning and Pytorch), and train your model using a familiar API.
- Our library allows you to choose one of the public implementations of a given model, plug it in icevision model adapter, and seamlessly train your model.
- As a bonus, our library even allows to experiment with another DL library. Our tutorials have several examples showing you how to train a given model using both fastai and Pytorch Lightning libraries side by side.
Happy Learning!
If you need any assistance, feel free to:
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
icevision-0.1.1rc2.tar.gz
(55.8 kB
view hashes)
Built Distribution
icevision-0.1.1rc2-py3-none-any.whl
(105.1 kB
view hashes)
Close
Hashes for icevision-0.1.1rc2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | c101fdfda75ff73baacfaa76782b89e022a93d1d4794f14d4683a2201622be0f |
|
MD5 | 5faa2b913e86916aced22199e08ff417 |
|
BLAKE2b-256 | 96db34121576a3e61352902f6aebc2fef73abbc465a6423ab418a6901aef2822 |