table.py

"""
Mask R-CNN
Configurations and data loading code for MS COCO.

Copyright (c) 2017 Matterport, Inc.
Licensed under the MIT License (see LICENSE for details)
Written by Waleed Abdulla

------------------------------------------------------------

Usage: import the module (see Jupyter notebooks for examples), or run from
       the command line as such:

    # Train a new model starting from pre-trained COCO weights
    python3 coco.py train --dataset=/path/to/coco/ --model=coco

    # Train a new model starting from ImageNet weights. Also auto download COCO dataset
    python3 coco.py train --dataset=/path/to/coco/ --model=imagenet --download=True

    # Continue training a model that you had trained earlier
    python3 coco.py train --dataset=/path/to/coco/ --model=/path/to/weights.h5

    # Continue training the last model you trained
    python3 coco.py train --dataset=/path/to/coco/ --model=last

    # Run COCO evaluatoin on the last model you trained
    python3 coco.py evaluate --dataset=/path/to/coco/ --model=last
"""

import os
import sys
import time
import pandas as pd
import numpy as np
import imgaug  # https://github.com/aleju/imgaug (pip3 install imgaug)
import skimage
import glob
# Download and install the Python COCO tools from https://github.com/waleedka/coco
# That's a fork from the original https://github.com/pdollar/coco with a bug
# fix for Python 3.
# I submitted a pull request https://github.com/cocodataset/cocoapi/pull/50
# If the PR is merged then use the original repo.
# Note: Edit PythonAPI/Makefile and replace "python" with "python3".
# from pycocotools.coco import COCO
# from pycocotools.cocoeval import COCOeval
# from pycocotools import mask as maskUtils
from collections import defaultdict
import zipfile
import urllib.request
import shutil

# 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_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
# print(COCO_MODEL_PATH)
# 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")
DEFAULT_DATASET_YEAR = "2014"
print(ROOT_DIR)
############################################################
#  Configurations
############################################################


class TableConfig(Config):
    """Configuration for training on Table dataset.
    Derives from the base Config class and overrides values specific
    to the Table dataset.
    """
    # Give the configuration a recognizable name
    NAME = "table"

    # We use a GPU with 12GB memory, which can fit two images.
    # Adjust down if you use a smaller GPU.
    IMAGES_PER_GPU = 2

    # Uncomment to train on 8 GPUs (default is 1)
    # GPU_COUNT = 8

    # Number of classes (including background)
    NUM_CLASSES = 1 + 1  # Background and Table

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

class TableDataset(utils.Dataset):

    def load_table(self, dataset_dir, subset):
        """Load a subset of the table 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("table", 1, "table")

        # Train or validation dataset?
        assert subset in ["train", "val"]
        dataset_dir = os.path.join(dataset_dir, subset)
        #print(subset)
        # Load annotations
        annotations = pd.read_csv(os.path.join(dataset_dir,subset+".csv"))
        all_x_values= list()
        all_y_values= list()
        
        for index,row in annotations.iterrows(): #ierating train.csv by rows
            all_x_values.clear()
            all_y_values.clear()

            image_path = os.path.join(dataset_dir, row[0])
            image = skimage.io.imread(image_path)
            image = skimage.color.gray2rgb(image, alpha=None)
            height, width = image.shape[:2]
            #Preprocessing with the bounding boxes, inorder to cover more area of the tables
            all_x_values.append(row[1])
            all_x_values.append(row[1])
            all_x_values.append(row[3])
            all_x_values.append(row[3])
            all_y_values.append(row[4])
            all_y_values.append(row[2])
            all_y_values.append(row[2])
            all_y_values.append(row[4])

           

            polygons = {
            'name' : 'table',
            'all_points_x' : [x for x in all_x_values],
            'all_points_y': [x for x in all_y_values]
            }
            self.add_image(
                "table",
                image_id=row[0],  # use file name as a unique image id
                path=image_path,
                width=width, height=height,
                polygons=polygons)
    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 table dataset image, delegate to parent class.
        image_info = self.image_info[image_id]
        #print('working',image_info)
        if image_info["source"] != "table":
            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]
        mask = np.zeros([info["height"], info["width"], len(info["polygons"])],
                        dtype=np.uint8)
        #print(info["polygons"]['all_points_y'], info["polygons"]['all_points_x'])
        rr, cc = skimage.draw.polygon(info["polygons"]['all_points_y'], info["polygons"]['all_points_x'])

        #print(rr,cc)
        mask[rr, cc,1] = 1
            # for i, p in enumerate(info["polygons"]):
            # print('value of polygon ',p)
            # # Get indexes of pixels inside the polygon and set them to 1
            # rr, cc = skimage.draw.polygon(p['all_points_y'], p['all_points_x'])
            # mask[rr, cc, i] = 1

        # Return mask, and array of class IDs of each instance. Since we have
        # one class ID only, we return an array of 1s
        return mask.astype(np.bool), np.ones([mask.shape[-1]], dtype=np.int32)

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


def train(model):
    """Train the model."""
    # Training dataset.
    dataset_train = TableDataset()
    dataset_train.load_table(args.dataset, "train")
    dataset_train.prepare()

    # Validation dataset
    dataset_val = TableDataset()
    dataset_val.load_table(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")
    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)) * 60
    mask = (np.sum(mask, -1, keepdims=True) >= 1)
    # Copy color pixels from the original color image where mask is set
    if mask.shape[0] > 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
        images_path =args.image
        os.chdir(images_path)
        for file in glob.glob("*.png"):
            image = skimage.io.imread(file)
            # Detect objects
            image = skimage.color.gray2rgb(image, alpha=None)
            print("image value :",[image.shape])

            r = model.detect([image], verbose=1)[0]
            
            # Color splash
            splash = color_splash(image, r['masks'])
            # Save output
            file_name = file.split('.')[0]+"_best_model.png"
            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 tables.')
    parser.add_argument("command",
                        metavar="<command>",
                        help="'train' or 'splash'")
    parser.add_argument('--dataset', required=False,
                        metavar="/path/to/table/dataset/",
                        help='Directory of the table 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 = TableConfig()
    else:
        class InferenceConfig(TableConfig):
            # 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 = ROOT_DIR+"mask_rcnn_coco.h5"
        # 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)

    # 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))