This demo showcases Image Inpainting with GMCNN. The task is to estimate suitable pixel information to fill holes in images.
Running the application with the -h option yields the following usage message:
usage: image_inpainting_demo.py [-h] -m MODEL [-i INPUT] [-d DEVICE]
[-p PARTS] [-mbw MAX_BRUSH_WIDTH]
[-ml MAX_LENGTH] [-mv MAX_VERTEX] [--no_show]
Options:
-h, --help Show this help message and exit.
-m MODEL, --model MODEL
Required. Path to an .xml file with a trained model.
-i INPUT, --input INPUT
path to image.
-d DEVICE, --device DEVICE
Optional. Specify the target device to infer on; CPU,
GPU, FPGA, HDDL or MYRIAD is acceptable. The demo will
look for a suitable plugin for device specified.
Default value is CPU
-p PARTS, --parts PARTS
Optional. Number of parts to draw mask.
-mbw MAX_BRUSH_WIDTH, --max_brush_width MAX_BRUSH_WIDTH
Optional. Max width of brush to draw mask.
-ml MAX_LENGTH, --max_length MAX_LENGTH
Optional. Max strokes length to draw mask.
-mv MAX_VERTEX, --max_vertex MAX_VERTEX
Optional. Max number of vertex to draw mask.
--no_show Optional. Don't show output
To run the demo, you can use public or pretrained models. You can download the pretrained models with the OpenVINO™ Model Downloader.
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.
The demo uses OpenCV to display the resulting image and image with mask applied and reports performance in the format of summary inference FPS.