オブジェクト検出 Python* デモ#

usage: object_detection_demo.py [-h] -m MODEL -at 
                                {centernet,detr,ctpn,faceboxes,nanodet,nanodet-plus,retinaface,retinaface-pytorch,ssd,ultra_lightweight_face_detection,yolo,yolov4,yolof,yolox,yolov3-onnx} 
                                -i INPUT [--adapter {openvino,ovms}] 
                                [-d DEVICE] [--labels LABELS] [-t PROB_THRESHOLD] 
                                [--resize_type {standard,fit_to_window,fit_to_window_letterbox}] 
                                [--input_size INPUT_SIZE INPUT_SIZE] [--anchors ANCHORS [ANCHORS ...]]
                                [--masks MASKS [MASKS ...]][--layout LAYOUT] 
                                [--num_classes NUM_CLASSES][-nireq NUM_INFER_REQUESTS] [-nstreams NUM_STREAMS] 
                                [-nthreads NUM_THREADS] [--loop] [-o OUTPUT] [-limit OUTPUT_LIMIT] [--no_show] 
                                [--output_resolution OUTPUT_RESOLUTION] [-u UTILIZATION_MONITORS] 
                                [--reverse_input_channels] [--mean_values MEAN_VALUES MEAN_VALUES MEAN_VALUES] 
                                [--scale_values SCALE_VALUES SCALE_VALUES SCALE_VALUES] [-r] 

Options: 
  -h, --help            Show this help message and exit.
  -m MODEL, --model MODEL 
                        Required. Path to an .xml file with a trained model or 
                        address of model inference service if using OVMS adapter.
  -at, --architecture_type Required.Specify model' architecture type. Valid values are {centernet,detr,ctpn,faceboxes,nanodet,nanodet-plus,retinaface,retinaface-pytorch,ssd,ultra_lightweight_face_detection,yolo,yolov4,yolof,yolox,yolov3-onnx}.
  -i INPUT, --input INPUT 
                        Required. An input to process.The input must be a 
                        single image, a folder of images, video file or camera id. 
  --adapter {openvino,ovms} 
                        Optional. Specify the model adapter.Default is openvino.
  -d DEVICE, --device DEVICE 
                        Optional. Specify the target device to infer on; CPU or 
                        GPU is acceptable.The demo 
                        will look for a suitable plugin for device specified.
                        Default value is CPU.

Common model options: 
  --labels LABELS       Optional.Labels mapping file.
  -t PROB_THRESHOLD, --prob_threshold PROB_THRESHOLD 
                        Optional. Probability threshold for detections filtering.
  --resize_type {standard,fit_to_window,fit_to_window_letterbox} 
                        Optional. A resize type for model preprocess.By default used model predefined type.
  --input_size INPUT_SIZE INPUT_SIZE 
                        Optional. The first image size used for CTPN model 
                        reshaping. Default: 600 600. Note that submitted 
                        images should have the same resolution, otherwise 
                        predictions might be incorrect.
  --anchors ANCHORS [ANCHORS ...]
                        Optional. A space separated list of anchors. By default used default anchors for model.
                        Only for YOLOV4 architecture type.
  --masks MASKS [MASKS ...]
                        Optional. A space separated list of mask for anchors. By default used default masks for model.
                        Only for YOLOV4 architecture type.
  --layout LAYOUT       Optional. Model inputs layouts.Ex.NCHW or 
                        input0:NCHW,input1:NC in case of more than one input.
  --num_classes NUM_CLASSES 
                        Optional. Number of detected classes. Only for NanoDet, NanoDetPlus 
                        architecture types.Inference options: 
  -nireq NUM_INFER_REQUESTS, --num_infer_requests NUM_INFER_REQUESTS 
                        Optional. Number of infer requests 
  -nstreams NUM_STREAMS, --num_streams NUM_STREAMS 
                        Optional. Number of streams to use for inference on 
                        the CPU or/and GPU in throughput mode (for HETERO and 
                        MULTI device cases use format 
                        <device1>:<nstreams1>,<device2>:<nstreams2> or just 
                        <nstreams>).
  -nthreads NUM_THREADS, --num_threads NUM_THREADS 
                        Optional. Number of threads to use for inference on 
                        CPU (including HETERO cases).

Input/output options: 
  --loop                Optional.Enable reading the input in a loop.-o OUTPUT, --output OUTPUT 
                        Optional. Name of the output file(s) to save.Frames of odd width or height can be truncated.See https://github.com/opencv/opencv/pull/24086 
  -limit OUTPUT_LIMIT, --output_limit OUTPUT_LIMIT 
                        Optional. Number of frames to store in output.If 0 is set, all frames are stored.
  --no_show             Optional.Don't show output.
  --output_resolution OUTPUT_RESOLUTION 
                        Optional. Specify the maximum output window resolution 
                        in (width x height) format.Example: 1280x720.
                        Input frame size used by default.
  -u UTILIZATION_MONITORS, --utilization_monitors UTILIZATION_MONITORS 
                        Optional. List of monitors to show initially.

Input transform options: 
  --reverse_input_channels REVERSE_CHANNELS 
                        Optional. Switch the input channels order from 
                        BGR to RGB.
  --mean_values MEAN_VALUES 
                        Optional.Normalize input by subtracting the mean 
                        values per channel.Example: 255.0 255.0 255.0 
  --scale_values SCALE_VALUES 
                        Optional. Divide input by scale values per channel.
                        Division is applied after mean values subtraction.
                        Example: 255.0 255.0 255.0 

Debug options: 
  -r, --raw_output_message 
                        Optional.Output inference results raw values showing.