Colorization Demo

This demo demonstrates an example of using neural networks to colorize a grayscale image or video.

How It Works

On startup, the application reads command-line parameters and loads a model to OpenVINO™ Runtime plugin for execution. Once the program receives an image, it performs the following steps:

  1. Converts the frame into the LAB color space.

  2. Uses the L-channel to predict A and B channels.

  3. Restores the image by converting it into the BGR color space.

Preparing to Run

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/colorization_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 IR format (*.xml + *.bin).

An example of using the Model Downloader:

omz_downloader --list models.lst

An example of using the Model Converter:

omz_converter --list models.lst

Supported Models

  • colorization-v2

  • colorization-siggraph

NOTE: Refer to the tables Intel’s Pre-Trained Models Device Support and Public Pre-Trained Models Device Support for the details on models inference support at different devices.

Running the Demo

Running the application with the -h option yields the following usage message:

usage: colorization_demo.py [-h] -m MODEL [-d DEVICE] -i INPUT [--loop] [-o OUTPUT] [-limit OUTPUT_LIMIT] [--no_show] [-u UTILIZATION_MONITORS]

Options:
  -h, --help            Help with the script.
  -m MODEL, --model MODEL
                        Required. Path to .xml file with pre-trained model.
  -d DEVICE, --device DEVICE
                        Optional. Specify a device to infer on (the list of available devices is shown below). Use '-d HETERO:<comma-separated_devices_list>' format to specify HETERO plugin. Use '-d MULTI:<comma-separated_devices_list>'
                        format to specify MULTI plugin. Default is CPU
  -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.
  --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.
  -u UTILIZATION_MONITORS, --utilization_monitors UTILIZATION_MONITORS
                        Optional. List of monitors to show initially.

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, and to an input video or image(s):

python colorization_demo.py \
    -i <path_to_image>/<image_name>.jpg \
    -m <path_to_model>/colorization-v2.xml

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 -o option:

  • To save processed results in an AVI file, specify the name of the output file with avi extension, for example: -o output.avi.

  • To save processed results as images, specify the template name of the output image file with jpg or png extension, for example: -o output_%03d.jpg. The actual file names are constructed from the template at runtime by replacing regular expression %03d with the frame number, resulting in the following: output_000.jpg, 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 limit option. The default value is 1000. To change it, you can apply the -limit N option, where N is 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.

Demo Output

The demo uses OpenCV to display the colorized frame. The demo reports

  • FPS: average rate of video frame processing (frames per second).

  • Latency: average time required to process one frame (from reading the frame to displaying the results). You can use both of these metrics to measure application-level performance.