NVIDIA-AI-IOT/deepstream_libraries
DeepStream Libraries offer CVCUDA, NvImageCodec, and PyNvVideoCodec modules as Python APIs for seamless integration into custom frameworks.
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.
Stars
79
Forks
2
Language
Python
License
—
Category
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.
Higher-rated alternatives
scikit-image/scikit-image
Image processing in Python
rerun-io/rerun
An open source SDK for logging, storing, querying, and visualizing multimodal and multi-rate data
rapidsai/cucim
cuCIM - RAPIDS GPU-accelerated image processing library
visioncortex/visioncortex
Core library for computer graphics & vision applications
imagej/ImageJ
Public domain software for processing and analyzing scientific images