RidgeRun Project and Products
Deep Learning has revolutionized classic computer vision techniques to enable even more intelligent and autonomous systems. Multimedia frameworks, such as GStreamer, are a basic component of automatic recognition and classification systems. GstInference is an ongoing open-source project from RidgeRun that allows easy integration of deep learning networks into your existing pipeline using the CPU for computation. Hardware accelerated support is also available from RidgeRun.
Latest version v0.4.0 includes:
Load pre-trained modelsMultiple supported architecturesGoogleNet's Inception V1, V2, V3 and V4 classification architectureTinyYolo V2 detection architectureFaceNet V1 recognition architectureResNet50 V1 classification architectureGraphic debugging overlay elementsSupported back-ends:TensorFlow (CPU)TensorFlow (GPU)NCSDK
Supported architectures:
x86
TX1
TX2
Xavier
Nano - Free Trial Version Available
i.MX8 (in progress)
See our developer's wiki for more information
Go to our online store for hardware accelerated support