This sample demonstrates how to run Instance Segmentation models from Detectron
or 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_data
for input image and im_info
for meta-information about the image (actual height, width and scale).boxes
with absolute bounding box coordinates of the input imagescores
with confidence scores for all bounding boxesclasses
with object class IDs for all bounding boxesraw_masks
with fixed-size segmentation heat maps for all classes of all bounding boxesAs input, the demo application takes:
--images
--video
The demo workflow is the following:
im_data
) keeping the original image aspect ratio.im_info
input blob passes resulting resolution and scale of a pre-processed image to the network to perform inference.--show_boxes
and --show_scores
arguments, bounding boxes and confidence scores are also shown.--video
option, 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, Inference Engine samples and 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 sample or demo application or reconvert your model using the Model Optimizer tool with
--reverse_input_channels
argument 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.
To run the demo, you can use public or pre-trained models. To download the pre-trained models, use the OpenVINO Model Downloader or go to https://download.01.org/opencv/.
NOTE: Before running the demo with a trained model, make sure the model is converted to the Inference Engine format (
*.xml
+*.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.