This demo shows how to perform instance segmentation 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
boxeswith normalized in [0, 1] range bounding box coordinates
confwith confidence scores for each class for all boxes
maskwith fixed-size mask channels for all boxes.
protowith fixed-size segmentation heat maps prototypes for all boxes.
As input, the demo application accepts a path to a single image file, a video file or a numeric ID of a web camera specified with a command-line argument
The demo workflow is the following:
im_infoinput blob passes resulting resolution and scale of a pre-processed image to the network to perform inference if network has
--show_scoresarguments, bounding boxes and confidence scores are also shown.
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 the
--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.
For demo input image or video files, refer to the section Media Files Available for Demos in the Open Model Zoo Demos Overview. The list of models supported by the demo is in
<omz_dir>/demos/instance_segmentation_demo/python/models.lst file. This file can be used as a parameter for Model Downloader and Converter to download and, if necessary, convert models to OpenVINO Inference Engine format (*.xml + *.bin).
An example of using the Model Downloader:
An example of using the Model Converter:
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.
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:
>NOTE: If you provide a single image as an input, the demo processes and renders it quickly, then exits. To continuously visualize inference results on the screen, apply the
loop option, which enforces processing a single image in a loop.
You can save processed results to a Motion JPEG AVI file or separate JPEG or PNG files using the
aviextension, for example:
pngextension, for example:
-o output_%03d.jpg. The actual file names are constructed from the template at runtime by replacing regular expression
%03dwith the frame number, resulting in the following:
output_001.jpg, and so on. To avoid disk space overrun in case of continuous input stream, like camera, you can limit the amount of data stored in the output file(s) with the
limitoption. The default value is 1000. To change it, you can apply the
-limit Noption, where
Nis the number of frames to store.
>NOTE: Windows* systems may not have the Motion JPEG codec installed by default. If this is the case, you can download OpenCV FFMPEG back end using the PowerShell script provided with the OpenVINO ™ install package and located at
<INSTALL_DIR>/opencv/ffmpeg-download.ps1. The script should be run with administrative privileges if OpenVINO ™ is installed in a system protected folder (this is a typical case). Alternatively, you can save results as images.
The application uses OpenCV to display resulting instance segmentation masks and current inference performance.