This demo demonstrates how to run Instance Segmentation models from
maskrcnn-benchmark using OpenVINO™.
NOTE: Only batch size of 1 is supported.
The demo application expects an instance segmentation model in the Intermediate Representation (IR) format with the following constraints:
im_datafor input image and
im_infofor meta-information about the image (actual height, width and scale).
boxeswith absolute bounding box coordinates of the input image
scoreswith confidence scores for all bounding boxes
classeswith object class IDs for all bounding boxes
raw_maskswith fixed-size segmentation heat maps for all classes of all bounding boxes
As input, the demo application takes:
The demo workflow is the following:
im_data) keeping the original image aspect ratio.
im_infoinput blob passes resulting resolution and scale of a pre-processed image to the network to perform inference.
--show_scoresarguments, bounding boxes and confidence scores are also shown.
--videooption, the demo shows the same object instance with the same color throughout the whole video using simple tracking. It assumes more or less static scene with instances in two frames being a part of the same track if intersection over union of the masks is greater than the 0.5 threshold.
NOTE: By default, Open Model Zoo demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the demo application or reconvert your model using the Model Optimizer tool with
--reverse_input_channelsargument specified. For more information about the argument, refer to When to Reverse Input Channels section of Converting a Model Using General Conversion Parameters.
Run the application with the
-h option to see the following usage message:
Running the application with an empty list of options yields the short version of the usage message and an error message.
NOTE: Before running the demo with a trained model, make sure the model is converted to the Inference Engine format (
*.bin) using the Model Optimizer tool.
To run the demo, please provide paths to the model in the IR format, to a file with class labels, and to an input video, image, or folder with images:
The application uses OpenCV to display resulting instance segmentation masks and current inference performance.