NVIDIA-AI-IOT/deepstream_libraries

DeepStream Libraries offer CVCUDA, NvImageCodec, and PyNvVideoCodec modules as Python APIs for seamless integration into custom frameworks.

42
/ 100
Emerging

This project helps developers build high-performance image and video processing applications using Python. It takes raw image and video data and processes it with GPU acceleration for tasks like classification, object detection, segmentation, resizing, and video encoding/decoding. It's ideal for developers creating computer vision solutions that require efficient handling of media data.

Use this if you are a Python developer building custom computer vision applications that need to leverage NVIDIA GPUs for accelerated image and video processing.

Not ideal if you need a pre-built, end-user application or if your primary development environment is not Python with NVIDIA hardware.

computer-vision video-analytics image-processing machine-learning-engineering gpu-acceleration
No Package No Dependents
Maintenance 13 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 4 / 25

How are scores calculated?

Stars

79

Forks

2

Language

Python

License

Last pushed

Mar 18, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVIDIA-AI-IOT/deepstream_libraries"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.