Python Image Processing Cookbook

How to do it...

Go through the following steps to implement deep instance segmentation using opencv-python functions:

1. Define the following function to generate N random (bright) colors using the HSV colorspace:

def random_colors(N, bright=True): brightness = 1.0 if bright else 0.7 hsv = [(i / N, 1, brightness) for i in range(N)] colors = list(map(lambda c: colorsys.hsv_to_rgb(*c), hsv)) random.shuffle(colors) return 256*np.array(colors)

2. Initialize the model constants and the path that you have used to download the model:

model_path = 'models\\'conf = 0.5thresh = 0.3

3. Read the COCO class labels on which the mask R-CNN (pretrained) model was trained:

labels_path = os.path.sep.join([model_path, "object_detection_classes_coco.txt"])labels ...