Mask RCNN 1 class only

I've trained the same repo for sheeps. You have to do 2 things:

1. Change the train and inference class numbers as 1 + 1 ( bg and person ):

    class SheepsConfig(Config):
   
        NAME = "sheeps"
        NUM_CLASSES = 1 + 1 # background + sheep
   
    config = SheepsConfig()  # Don't forget to use this config while creating your model
    config.display()
   

2. You need to create dataset to train on. You can use coco as follows:

    import coco
    from pycocotools.coco import COCO
   
    ct = COCO("/YourPathToCocoDataset/annotations/instances_train2014.json")
    ct.getCatIds(['sheep']) 
    # Sheep class' id is 20. You should run for person and use that id
   
    COCO_DIR = "/YourPathToCocoDataset/"
    # This path has train2014, annotations and val2014 files in it
   
    # Training dataset
    dataset_train = coco.CocoDataset()
    dataset_train.load_coco(COCO_DIR, "train", class_ids=[20])
    dataset_train.prepare()
   
    # Validation dataset
    dataset_val = coco.CocoDataset()
    dataset_val.load_coco(COCO_DIR, "val", class_ids=[20])
    dataset_val.prepare()
   

And then simply create your model as:

# Create model in training mode
model = modellib.MaskRCNN(mode="training", config=config, model_dir=MODEL_DIR)
model.load_weights(COCO_MODEL_PATH, by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc", "mrcnn_bbox", "mrcnn_mask"])
# This COCO_MODEL_PATH is the path to the mask_rcnn_coco.h5 file in this repo

Then you can train it with this code:

model.train(dataset_train, dataset_val,
        learning_rate=config.LEARNING_RATE, 
        epochs=100, 
        layers='heads')#You can also use 'all' to train all network.

Don't forget to use tensorflow 1.x and keras 2.1.0 :) I can train with these versions.

I tried to follow what @dnl_anoj suggested "showing results of only person classes". I removed all classes but the person class from the predicted results . You can use the following code in run_on_opencv_image() function in the predictor.py file in https://github.com/matterport/Mask_RCNN.

predictions = self.coco_demo.compute_prediction(image)
top_predictions = self.coco_demo.select_top_predictions(predictions)

masks = top_predictions.get_field("mask")
boxes = top_predictions.bbox
label_indexs = top_predictions.get_field("labels").numpy()

x = np.where(label_indexs != 1) # get indexes of labels which are not person

#remove items which are not person class
masks = np.delete(masks,x, axis=0)
boxes = np.delete(boxes,x, axis=0)
label_indexs = np.delete(label_indexs,x)
labels = self.convert_label_index_to_string(label_indexs)

There is a balloon example made by the author of the github you linked which is very well written and contains only one class (balloons) you should follow this tutorial: https://engineering.matterport.com/splash-of-color-instance-segmentation-with-mask-r-cnn-and-tensorflow-7c761e238b46