This topic demonstrates how to run the Object Detection demo application, which does inference using object detection networks like Faster R-CNN on Intel® Processors and Intel® HD Graphics.
VGG16-Faster-RCNN is a public CNN that can be easily obtained from GitHub:
test.prototxt
from https://raw.githubusercontent.com/rbgirshick/py-faster-rcnn/master/models/pascal_voc/ZF/faster_rcnn_end2end/test.prototxt
https://dl.dropboxusercontent.com/s/o6ii098bu51d139/faster_rcnn_models.tgz?dl=0
VGG16_faster_rcnn_final.caffemodel
file.For correct converting the source model you should run the Model Optimizer. You can use the following command to convert the source model:
For documentation on how to convert Caffe models, refer to Converting a Caffe Model.
Running the application with the -h
option yields the following usage message:
Running the application with the empty list of options yields the usage message given above and an error message.
You can use the following command to do inference on Intel® Processors on an image using a trained Faster R-CNN network:
NOTE: Before running the sample with a trained model, make sure the model is converted to the Inference Engine format (*.xml + *.bin) using the Model Optimizer tool.
The application outputs an image (out_0.bmp
) with detected objects enclosed in rectangles. It outputs the list of classes of the detected objects along with the respective confidence values and the coordinates of the rectangles to the standard output stream.
Upon the start-up the demo application reads command line parameters and loads a network and an image to the Inference Engine plugin. When inference is done, the application creates an output image and outputs data to the standard output stream.