Lvis API: Read and evaluate LVIS annotations

Understand the project

Practical overview

Use it when a Python computer-vision workflow needs to inspect LVIS annotations, visualize them, or evaluate results against them.

Computer-vision developers and researchers working with LVIS annotation files.
Teams that need annotation visualization or LVIS-based result evaluation in Python.

Before you choose

Installation uses pip and requires the COCO API dependency; the README notes that NumPy is needed to install that dependency.
The repository provides both package-install and local-clone installation instructions.
The documented API scope is LVIS annotation handling, visualization, and evaluation rather than a specified model framework.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the documented package and COCO API dependency in an isolated Python environment.

Create a virtual environment with the command below and activate it.
Documented command
```
python3 -m venv env
```

Install the COCO API with the command below.

Documented command

pip install 'git+https://github.com/cocodataset/cocoapi.git#subdirectory=PythonAPI'

Install the LVIS package with the command below.
Documented command
```
pip install lvis
```
Deactivate the environment when finished.

The documented installation sequence places the LVIS package and its COCO API dependency in the virtual environment.

The instructions cover installation, not a specific annotation-processing or evaluation run.
The repository also documents a clone-and-install route using pip install . and python test.py.

Evidence and transparency

Source record details

Source availability: Active
Sources checked: 18 October 2026
Original website title: lvis-dataset/lvis-api · Official homepage title · retained in its source language