https://github.com/lvis-dataset/lvis-api

Python API for LVIS Dataset
https://github.com/lvis-dataset/lvis-api

computer-vision object-detection

Last synced: 3 months ago
JSON representation

Python API for LVIS Dataset

• Host: GitHub
• URL: https://github.com/lvis-dataset/lvis-api
• Owner: lvis-dataset
• License: other
• Created: 2019-08-07T23:30:44.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2024-02-21T00:43:47.000Z (11 months ago)
• Last Synced: 2024-08-01T13:28:14.525Z (6 months ago)
• Topics: computer-vision, object-detection
• Language: Python
• Homepage: http://lvisdataset.org
• Size: 4.21 MB
• Stars: 402
• Watchers: 12
• Forks: 62
• Open Issues: 12
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
#  LVIS API

LVIS (pronounced ‘el-vis’): is a new dataset for Large Vocabulary Instance Segmentation.

When complete, it will feature more than 2 million high-quality instance segmentation masks for over 1200 entry-level object categories in 164k images. The LVIS API enables reading and interacting with annotation files, visualizing annotations, and evaluating results.



## LVIS v1.0

For this release, we have annotated 159,623 images (100k train, 20k val, 20k test-dev, 20k test-challenge). Release v1.0 is publicly available at [LVIS website](http://www.lvisdataset.org) and will be used in the second LVIS Challenge to be held at Joint COCO and LVIS Workshop at ECCV 2020.

## Setup

You can setup a virtual environment and then install `lvisapi` using pip:

```bash

python3 -m venv env               # Create a virtual environment

source env/bin/activate           # Activate virtual environment

# install COCO API. COCO API requires numpy to install. Ensure that you installed numpy.

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

# install LVIS API

pip install lvis

# Work for a while ...

deactivate  # Exit virtual environment

```

You can also clone the repo first and then do the following steps inside the repo:

```bash

python3 -m venv env               # Create a virtual environment

source env/bin/activate           # Activate virtual environment

# install COCO API. COCO API requires numpy to install. Ensure that you installed numpy.

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

# install LVIS API

pip install .

# test if the installation was correct

python test.py

# Work for a while ...

deactivate  # Exit virtual environment

```

## Citing LVIS

If you find this code/data useful in your research then please cite our [paper](https://arxiv.org/abs/1908.03195):

```

@inproceedings{gupta2019lvis,

  title={{LVIS}: A Dataset for Large Vocabulary Instance Segmentation},

  author={Gupta, Agrim and Dollar, Piotr and Girshick, Ross},

  booktitle={Proceedings of the {IEEE} Conference on Computer Vision and Pattern Recognition},

  year={2019}

}

```

## Credit

The code is a re-write of PythonAPI for [COCO](https://github.com/cocodataset/cocoapi).

The core functionality is the same with LVIS specific changes.