Home/Computer Vision/icevision

icevision

airctic/icevision

Agnostic Computer Vision Framework

GraphCanon updated Sep 23, 2026 · GitHub synced Sep 23, 2026

43views this month

868 stars145 forksLast push Nov 26, 2024 Python Apache-2.0

Decision brief

IceVision is an agnostic computer vision framework that supports integration with multiple training libraries including Fast.ai and PyTorch-Lightning.

Good fit when

Use IceVision if you are working on Linux or MacOS environments, as the project only supports these operating systems.
If your project requires flexibility in terms of using various training libraries like Fast.ai and PyTorch-Lightning, without needing to switch frameworks during development.

Avoid when

Do not use IceVision if you are working on Windows, because the framework does not support this operating system.
Avoid IceVision in scenarios where there is a strict dependency on a third-party tool or library that is incompatible with Fast.ai and PyTorch-Lightning.

Observed Jul 16, 2026 · Source: enrich:decision_facts

icevision alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Dormant (665d since push); As of Sep 23, 2026
Provenance: Not a fork · Organization account; As of Sep 23, 2026
Security (OSV): No lockfile; As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

pip install icevision

How it fits your stack(1)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Integrates

IceVision enables agnostic computer vision and supports various models including YOLO, so it could potentially integrate with Ultralytics' YOLO models for different detection tasks.

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

segment-anything

Provides code for running inference with the SegmentAnything Model (SAM), including model checkpoints and example notebooks.

pytorch-lightning

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

A tool for launching, training, and using PyTorch models with ease on various devices, configurations, including mixed precision support.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

IceVision is a flexible computer vision framework that supports integration with different training libraries like Fast.ai and PyTorch-Lightning.

Capability facts

Languages: python
Source: github.language · Sep 23, 2026

Categories

Computer Vision

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Sep 23, 2026)

pip install icevision[all]

Tags

ai annotation-parsers coco-dataset deep-learning object-detection pytorch tutorials voc-dataset

README

Installation For more installation options, check our docs. Important: We currently only support Linux/MacOS.

For agents

This page has a .md twin and JSON over the API.

/tools/airctic-icevision.md GET /api/graphcanon/tools/airctic-icevision GET /api/graphcanon/graph?tool=airctic-icevision

Was this helpful?

Anonymous feedback helps us improve pages and translations.