We’re thrilled to announce the release of Savant version 0.2.4, a cutting-edge computer vision and video analytics framework optimized for Nvidia hardware! Here’s what’s new:
News
🚀 Savant: v0.2.3 is out: Pythonic Computer Vision And Video Analytics Framework For Nvidia Hardware
We’re thrilled to announce the release of Savant version 0.2.3, a cutting-edge computer vision and video analytics framework optimized for Nvidia hardware! Here’s what’s new:
Building a High-Performance Car Classification Pipeline With Savant
Savant, a new open-source product that simplifies the use of Nvidia DeepStream for ML engineers. It is a framework that handles the heavy lifting, allowing you to focus on building optimized inference pipelines with declarative syntax and Python functions.
With Savant, you can easily handle multiple streams simultaneously, deliver reliable, production-ready inference pipelines quickly and achieve top-notch performance with TensorRT. Visit the website to know more.
In the current article, we introduce you to a classification pipeline that uses a detector model, a tracker, and three classifier models to perform a pretty common task related to car traffic profiling: car detection, tracking, and classification. The pipeline is a remake of one of Nvidia’s earliest test applications.
The source for the current pipeline is in Savant’s samples/nvidia_car_classificiation directory.
Read the full article on Medium.
The Release Of Savant: v0.2.1 - Python Video Analytics Framework On Nvidia DeepStream
Savant, a new open-source product that simplifies the use of Nvidia DeepStream for ML engineers. It is a framework that handles the heavy lifting, allowing you to focus on building optimized inference pipelines with declarative syntax and Python functions.
With Savant, you can easily handle multiple streams simultaneously, deliver reliable, production-ready inference pipelines quickly and achieve top-notch performance with TensorRT. Visit the website to know more.
0.2.1 Release Information
In 0.2.1, we fixed several bugs, created 2 more demos, and implemented multiple features to make it more developer friendly. With 0.2.1, you can easily develop pipelines with PyCharm Professional + Docker Runtime (docs in progress).
- New demo: Efficient City Traffic Metering With PeopleNet/YOLOv8, Savant, And Grafana At Scale;
- New adapter: Video Loop Adapter;
- Developer documentation: link;
- Release Information;
- Discord.
Savant articles and tutorials
With Savant, you can easily handle multiple streams simultaneously, deliver reliable, production-ready inference pipelines quickly and achieve top-notch performance with TensorRT. Visit the website to know more.
Up until this point, we published three articles on Savant demonstrating how to use it to solve detection, tracking, and classification tasks efficiently: