R2Inference - ONNXRT ACL Examples
< R2Inference | Examples
![]() | Make sure you also check R2Inference's companion project: GstInference |
R2Inference |
---|
![]() |
Introduction |
Getting started |
Supported backends |
Examples |
Model Zoo |
Contact us |
![]() |
Contents
R2Inference provides several examples to highlight its usage with different architectures and frameworks. The models used for these examples can be downloaded from our Model Zoo.
Preparation
To test the ONNXRT example you will need a ONNX compatible model file of the InceptionV1 architecture. You can obtain the model from the Model Zoo.
Inception v1
This example is located in r2inference/examples/r2i/onnxrt_acl
.
To use this example run:
./inception -i [JPG input Image] -m [ONNX Model] -s [Model Input Size]
For example evaluating this image:
Should produce the following output:
./inception -i Plane_example_input.jpg -m graph_inceptionv1.onnx -s 224
Loading Model: graph_inceptionv1.onnx
Setting model to engine
Configuring ONNXRT session parameters
Loading image: Plane_example_input.jpg
Configuring frame
Starting engine
Predicting...
Highest probability is label 405 (0.656891)
Stopping engine
According to the ImageNet labels, 405 corresponds to an 'airship'.