workersDetection1.py

import os
import sys
import json
import datetime
import numpy as np
import skimage.draw
from codecs import encode,decode
# Root directory of the project
ROOT_DIR = os.path.abspath("../../")

# Import Mask RCNN
sys.path.append(ROOT_DIR)  # To find local version of the library
from mrcnn.config import Config
from mrcnn import model as modellib, utils

# Path to trained weights file
COCO_WEIGHTS_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")

# Directory to save logs and model checkpoints, if not provided
# through the command line argument --logs
DEFAULT_LOGS_DIR = os.path.join(ROOT_DIR, "logs")

############################################################
#  Configurations
############################################################


class WorkersDetectionConfig(Config):
    """Configuration for training on the toy  dataset.
    Derives from the base Config class and overrides some values.
    """
    # Give the configuration a recognizable name
    NAME = "WorkersDetection"

    # We use a GPU with 12GB memory, which can fit two images.
    # Adjust down if you use a smaller GPU.
    IMAGES_PER_GPU = 1
    

    # Number of classes (including background)
    NUM_CLASSES = 1 + 5  # Background + Total classes(worker, hardhat, strap, hook, harness)

    # Number of training steps per epoch
    STEPS_PER_EPOCH = 100

    # Skip detections with < 60% confidence
    DETECTION_MIN_CONFIDENCE = 0.6


############################################################
#  Dataset
############################################################

class WorkersDetectionDataset(utils.Dataset):

    def load_workers(self, dataset_dir, subset):
        """Load a subset of the Workers dataset.
        dataset_dir: Root directory of the dataset.
        subset: Subset to load: train or val
        """
        # Add classes. We have only one class to add.
        self.add_class("Workers", 1, "worker")
        self.add_class("Workers", 2, "strap")
        self.add_class("Workers", 3, "hardhat")
        self.add_class("Workers", 4, "hook")
        self.add_class("Workers", 5, "harness")
   

        # Train or validation dataset?
        assert subset in ["train", "val"]
        dataset_dir = os.path.join(dataset_dir, subset)

        annot = json.load(open(os.path.join(dataset_dir, "training.json")))
                                #.encode().decode('utf-8-sig'))
        #annotations = list(annotations.values())  # don't need the dict keys

        
        img_ids = annot['images']
        class_ids=annot['categories']
        ann=annot['annotations']
        i=0
        name_dict ={"worker":1,"strap":2,"hardhat":3,"hook":4,"harness":5}
        for img in img_ids:
            polygon=[]
            classes=[]
            while i<len(ann):
                img_id=ann[i]['image_id']
                cat_id=ann[i]['category_id']
                p=ann[i]['segmentation'][0]
                
                #print(len(p))
                if img_id == img['id']:
                    d = {'name':"",'all_points_x':[],'all_points_y':[]}
                    d['name'] = class_ids[cat_id-1]['name']
                    classes.append(d['name'])
                    d['all_points_x'] = [p[j] for j in range(0,len(p),2)]
                    d['all_points_y'] = [p[j] for j in range(1,len(p)+1,2)]
                    polygon.append(d)
                    #if img_id == 546:
                       # print(d)
                       # print()
                    
                        #print()
                else:
                    break
                #print(polygon)
                i+=1
                
           
            num_ids = [name_dict[a] for a in classes]
            filename = img['file_name'].split('\\')
            image_path = os.path.join(dataset_dir, filename[-1])
            self.add_image(
                "Workers",
                image_id=filename[-1],  # use file name as a unique image id
                path=image_path,
                width=img['width'], height=img['height'],
                polygons=polygon,
                num_ids=num_ids
                )
                                                            
                   

    def load_mask(self, image_id):
        """Generate instance masks for an image.
       Returns:
        masks: A bool array of shape [height, width, instance count] with
            one mask per instance.
        class_ids: a 1D array of class IDs of the instance masks.
        """
        # If not a workers dataset image, delegate to parent class.
              
                                            

        image_info = self.image_info[image_id]
        if image_info["source"] != "Workers":
            return super(self.__class__, self).load_mask(image_id)

        # Convert polygons to a bitmap mask of shape
        # [height, width, instance_count]
        
        info = self.image_info[image_id]
        #print(info)
        num_ids = info['num_ids']
        mask = np.zeros([info["height"], info["width"], len(info["polygons"])],
                        dtype=np.uint8)
        #print(mask.shape[-1])
        #print(len(info['polygons']))
        for i, p in enumerate(info["polygons"]):
            if p['name']!='rect':
                rr, cc = skimage.draw.polygon(p['all_points_y'], p['all_points_x'])
                mask[rr, cc, i] = 1  
                    #class_id.append[]
            
        # Return mask, and array of class IDs of each instance.
        #print(mask.shape)
        num_ids = np.array(num_ids, dtype=np.int32)
        #return mask.astype(np.bool), np.ones([mask.shape[-1]], dtype=np.int32)
        return mask.astype(np.bool), num_ids

    def image_reference(self, image_id):
        """Return the path of the image."""
        info = self.image_info[image_id]
        if info["source"] == "Workers":
            return info["path"]
        else:
            super(self.__class__, self).image_reference(image_id)


def train(model):
    """Train the model."""
    # Training dataset.
    from imgaug import augmenters as iaa
    
    dataset_train = WorkersDetectionDataset()
    dataset_train.load_workers(args.dataset, "train")
    dataset_train.prepare()

    # Validation dataset
    dataset_val = WorkersDetectionDataset()
    dataset_val.load_workers(args.dataset, "val")
    dataset_val.prepare()

    # *** This training schedule is an example. Update to your needs ***
    # Since we're using a very small dataset, and starting from
    # COCO trained weights, we don't need to train too long. Also,
    # no need to train all layers, just the heads should do it.
    print("Training network heads")
    max_augs = 3
    """augmentation = iaa.SomeOf((0, max_augs), [
                    iaa.Fliplr(0.5),
                    iaa.Flipud(0.5),
                    iaa.OneOf([ iaa.Affine(rotate = 30 * i) for i in range(0, 12) ]),
                    iaa.Affine(scale={"x": (0.8, 1.2), "y": (0.8, 1.2)}),
                    iaa.Add((-40, 40)),
                    iaa.Multiply((0.8, 1.5)),
                    iaa.GaussianBlur(sigma=(0.0, 5.0))
                ])"""
    model.train(dataset_train, dataset_val,
                learning_rate=config.LEARNING_RATE,
                epochs=50,
                layers='heads')


def color_splash(image, mask):
    """Apply color splash effect.
    image: RGB image [height, width, 3]
    mask: instance segmentation mask [height, width, instance count]

    Returns result image.
    """
    # Make a grayscale copy of the image. The grayscale copy still
    # has 3 RGB channels, though.
    gray = skimage.color.gray2rgb(skimage.color.rgb2gray(image)) * 255
    # Copy color pixels from the original color image where mask is set
    if mask.shape[-1] > 0:
        # We're treating all instances as one, so collapse the mask into one layer
        mask = (np.sum(mask, -1, keepdims=True) >= 1)
        splash = np.where(mask, image, gray).astype(np.uint8)
    else:
        splash = gray.astype(np.uint8)
    return splash


def detect_and_color_splash(model, image_path=None, video_path=None):
    assert image_path or video_path

    # Image or video?
    if image_path:
        # Run model detection and generate the color splash effect
        print("Running on {}".format(args.image))
        # Read image
        image = skimage.io.imread(args.image)
        # Detect objects
        r = model.detect([image], verbose=1)[0]
        # Color splash
        splash = color_splash(image, r['masks'])
        # Save output
        file_name = "splash_{:%Y%m%dT%H%M%S}.png".format(datetime.datetime.now())
        skimage.io.imsave(file_name, splash)
    elif video_path:
        import cv2
        # Video capture
        vcapture = cv2.VideoCapture(video_path)
        width = int(vcapture.get(cv2.CAP_PROP_FRAME_WIDTH))
        height = int(vcapture.get(cv2.CAP_PROP_FRAME_HEIGHT))
        fps = vcapture.get(cv2.CAP_PROP_FPS)

        # Define codec and create video writer
        file_name = "splash_{:%Y%m%dT%H%M%S}.avi".format(datetime.datetime.now())
        vwriter = cv2.VideoWriter(file_name,
                                  cv2.VideoWriter_fourcc(*'MJPG'),
                                  fps, (width, height))

        count = 0
        success = True
        while success:
            print("frame: ", count)
            # Read next image
            success, image = vcapture.read()
            if success:
                # OpenCV returns images as BGR, convert to RGB
                image = image[..., ::-1]
                # Detect objects
                r = model.detect([image], verbose=0)[0]
                # Color splash
                splash = color_splash(image, r['masks'])
                # RGB -> BGR to save image to video
                splash = splash[..., ::-1]
                # Add image to video writer
                vwriter.write(splash)
                count += 1
        vwriter.release()
    print("Saved to ", file_name)


############################################################
#  Training
############################################################

if __name__ == '__main__':
    import argparse

    # Parse command line arguments
    parser = argparse.ArgumentParser(
        description='Train Mask R-CNN to detect balloons.')
    parser.add_argument("command",
                        metavar="<command>",
                        help="'train' or 'splash'")
    parser.add_argument('--dataset', required=False,
                        metavar="/path/to/balloon/dataset/",
                        help='Directory of the Balloon dataset')
    parser.add_argument('--weights', required=True,
                        metavar="/path/to/weights.h5",
                        help="Path to weights .h5 file or 'coco'")
    parser.add_argument('--logs', required=False,
                        default=DEFAULT_LOGS_DIR,
                        metavar="/path/to/logs/",
                        help='Logs and checkpoints directory (default=logs/)')
    parser.add_argument('--image', required=False,
                        metavar="path or URL to image",
                        help='Image to apply the color splash effect on')
    parser.add_argument('--video', required=False,
                        metavar="path or URL to video",
                        help='Video to apply the color splash effect on')
    args = parser.parse_args()

    # Validate arguments
    if args.command == "train":
        assert args.dataset, "Argument --dataset is required for training"
    elif args.command == "splash":
        assert args.image or args.video,\
               "Provide --image or --video to apply color splash"

    print("Weights: ", args.weights)
    print("Dataset: ", args.dataset)
    print("Logs: ", args.logs)

    # Configurations
    if args.command == "train":
        config = WorkersDetectionConfig()
    else:
        class InferenceConfig(WorkersDetectionConfig):
            # Set batch size to 1 since we'll be running inference on
            # one image at a time. Batch size = GPU_COUNT * IMAGES_PER_GPU
            GPU_COUNT = 1
            IMAGES_PER_GPU = 1
        config = InferenceConfig()
    config.display()

    # Create model
    if args.command == "train":
        model = modellib.MaskRCNN(mode="training", config=config,
                                  model_dir=args.logs)
    else:
        model = modellib.MaskRCNN(mode="inference", config=config,
                                  model_dir=args.logs)

    # Select weights file to load
    if args.weights.lower() == "coco":
        weights_path = COCO_WEIGHTS_PATH
        # Download weights file
        if not os.path.exists(weights_path):
            utils.download_trained_weights(weights_path)
    elif args.weights.lower() == "last":
        # Find last trained weights
        weights_path = model.find_last()
    elif args.weights.lower() == "imagenet":
        # Start from ImageNet trained weights
        weights_path = model.get_imagenet_weights()
    else:
        weights_path = args.weights

    # Load weights
    print("Loading weights ", weights_path)
    if args.weights.lower() == "coco":
        # Exclude the last layers because they require a matching
        # number of classes
        model.load_weights(weights_path, by_name=True, exclude=[
            "mrcnn_class_logits", "mrcnn_bbox_fc",
            "mrcnn_bbox", "mrcnn_mask"])
    else:
        model.load_weights(weights_path, by_name=True, exclude=[
            "mrcnn_class_logits", "mrcnn_bbox_fc",
            "mrcnn_bbox", "mrcnn_mask"])

    # Train or evaluate
    if args.command == "train":
        train(model)
    elif args.command == "splash":
        detect_and_color_splash(model, image_path=args.image,
                                video_path=args.video)
    else:
        print("'{}' is not recognized. "
              "Use 'train' or 'splash'".format(args.command))