Product Description

GstInference is an open-source project from RidgeRun Engineering that provides a framework for integrating deep learning inference into GStreamer. Either use one of the included elements to do out-of-the box inference using the most popular deep learning architectures, or leverage the base classes and utilities to support your own custom architecture.

TensorFlow™ is an open source software library for high performance numerical computation. Its flexible architecture allows easy deployment of computation across a variety of platforms (CPUs, GPUs, TPUs). It is originally developed by researchers and engineers from the Google Brain team within Google’s AI organization. Tensorflow it is widely used to develop machine learning, deep learning applications.

Models available

GoogleNet Inception is an image classification convolutional neural network. It was designed to participate at the ImageNet challenge, a competition where research teams evaluate classification algorithms on the ImageNet data set, and compete to achieve the higher accuracy.
TinyYOLO (also called tiny Darknet) is the light version of the YOLO(You Only Look Once) real-time object detection deep neural network.
MobileNet, by Google, is suitable for Mobile devices, or any devices with low computational power.
Inception-ResNet is a variation of Inception V3 model which borrows some ideas from Microsoft's ResNet papers.
FaceNet is based in Inceptionv1, it is a face detection convolutional neural network. It was designed for face recognition and clustering.

TensorFlow for GstInference