# image_vision v0.3.0 - Table of Contents

> Simple image classification, embedding, object detection,
segmentation, background removal, captioning, and zero-shot
classification for the `image` library. Powered by Bumblebee and
Ortex with strong, permissively-licensed defaults — no ML
expertise required.

## Guides

- [ImageVision](readme.md)
- [License](license.md)
- [Changelog](changelog.md)

- Guides
  - [Computer-vision tasks at a glance](overview.md)
  - [Image Classification](classification.md)
  - [Image Segmentation](segmentation.md)
  - [Object Detection](detection.md)
  - [Face Detection](face_detection.md)
  - [Background Removal](background.md)
  - [Image Captioning](captioning.md)
  - [Zero-Shot Classification](zero_shot.md)

## Modules

- [Image.Background](Image.Background.md): Foreground/background separation — "remove the background from
this image".
- [Image.Captioning](Image.Captioning.md): Image captioning — generates a natural-language description of an
image.
- [Image.Classification](Image.Classification.md): Image classification — what's in this image?
- [Image.Detection](Image.Detection.md): Object detection — where are the objects in this image?
- [Image.FaceDetection](Image.FaceDetection.md): Face detection — where are the faces in this image?
- [Image.Segmentation](Image.Segmentation.md): Image segmentation — which pixels belong to which object?
- [Image.ZeroShot](Image.ZeroShot.md): Zero-shot image classification — classify an image against
arbitrary labels you supply at call time, without retraining.
- [ImageVision](ImageVision.md): `ImageVision` provides simple, opinionated image vision operations
that sit alongside the [`image`](https://hex.pm/packages/image)
library
- [ImageVision.ModelCache](ImageVision.ModelCache.md): On-disk cache for ONNX model weights downloaded from
[HuggingFace](https://huggingface.co).

## Mix Tasks

- [mix image_vision.download_models](Mix.Tasks.ImageVision.DownloadModels.md): Pre-downloads the default models used by `Image.Classification`,
`Image.Segmentation`, `Image.Detection`, `Image.Background`,
`Image.Captioning`, and `Image.ZeroShot` so that first-call latency
is eliminated and the application can run fully offline.

