coco.py

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

Based on the work of Waleed Abdulla (Matterport)
Modified by github.com/GustavZ

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

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
    python3 coco.py train --dataset=/path/to/coco/ --model=imagenet

    # 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

    # OWN TRAINING START
    python coco.py train --model=imagenet --classes='person'
"""
# py2/3 compability
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import os
import sys
import time
import numpy as np
import imgaug  # https://github.com/aleju/imgaug (pip3 install imageaug)

# 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

import zipfile
from six.moves import urllib # py2/3 compability
import shutil

# Root directory of the project
ROOT_DIR = os.getcwd()

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

# Directory to save logs and model checkpoints, if not provided
# through the command line argument --logs
DEFAULT_WEIGHTS_DIR = os.path.join(ROOT_DIR, "weights")
DEFAULT_LOGS_DIR = os.path.join(ROOT_DIR, "logs")
DEFAULT_DATASET_DIR = os.path.join(ROOT_DIR, "data/coco")
DEFAULT_DATASET_YEAR = "2017" #"2014"

# Path to trained weights file
COCO_MODEL_PATH = os.path.join(DEFAULT_WEIGHTS_DIR, "mobile_mask_rcnn_cocoperson.h5")

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


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

    ## GPU
    IMAGES_PER_GPU = 1
    GPU_COUNT = 2

    ## Number of classes (including background)
    NUM_CLASSES = 1 + 80

    ## Backbone Architecture
    BACKBONE = "mobilenetv1"
    BACKBONE_STRIDES = [4, 8, 16, 32, 64]

    ## Resolution
    RES_FACTOR = 2
    IMAGE_MAX_DIM = 1024 // RES_FACTOR
    RPN_ANCHOR_SCALES = tuple(np.divide((32, 64, 128, 256, 512),RES_FACTOR))

    ## Losses
    LOSS_WEIGHTS = {
        "rpn_class_loss": 1.,
        "rpn_bbox_loss": 1.,
        "mrcnn_class_loss": 1.,
        "mrcnn_bbox_loss": 1.,
        "mrcnn_mask_loss": 1.
    }

    ## Steps
    STEPS_PER_EPOCH = 10000
    VALIDATION_STEPS = 50

    ## Additions
    TRAIN_BN = True
    POST_NMS_ROIS_INFERENCE = 100


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

class CocoDataset(utils.Dataset):
    def load_coco(self, dataset_dir, subset, year=DEFAULT_DATASET_YEAR, class_names=None,
                  class_map=None, return_coco=False, auto_download=False):
        """Load a subset of the COCO dataset.
        dataset_dir: The root directory of the COCO dataset.
        subset: What to load (train, val, minival, valminusminival)
        year: What dataset year to load (2014, 2017) as a string, not an integer
        class_names: If provided, only loads images that have the given classes.
        class_map: TODO: Not implemented yet. Supports maping classes from
            different datasets to the same class ID.
        return_coco: If True, returns the COCO object.
        auto_download: Automatically download and unzip MS-COCO images and annotations
        """
        if auto_download is True:
            self.auto_download(dataset_dir, subset, year)

        coco = COCO("{}/annotations/instances_{}{}.json".format(dataset_dir, subset, year))
        class_ids = coco.getCatIds(catNms=class_names)

        if subset == "minival" or subset == "valminusminival":
            subset = "val"
        image_dir = "{}/{}{}".format(dataset_dir, subset, year)

        # Load all classes or a subset?
        if not class_ids:
            # All classes
            class_ids = sorted(coco.getCatIds())

        # All images or a subset?
        if class_ids:
            image_ids = []
            for id in class_ids:
                image_ids.extend(list(coco.getImgIds(catIds=[id])))
            # Remove duplicates
            image_ids = list(set(image_ids))
        else:
            # All images
            image_ids = list(coco.imgs.keys())

        self.dataset_size = len(image_ids)

        # Add classes
        for i in class_ids:
            self.add_class("coco", i, coco.loadCats(i)[0]["name"])

        # Add images
        for i in image_ids:
            self.add_image(
                "coco", image_id=i,
                path=os.path.join(image_dir, coco.imgs[i]['file_name']),
                width=coco.imgs[i]["width"],
                height=coco.imgs[i]["height"],
                annotations=coco.loadAnns(coco.getAnnIds(
                    imgIds=[i], catIds=class_ids, iscrowd=None)))

        print ("> {} images of classes {} from coco subset-{} loaded".format(self.dataset_size, class_names, subset))

        if return_coco:
            return coco

    def auto_download(self, dataDir, dataType, dataYear):
        """Download the COCO dataset/annotations if requested.
        dataDir: The root directory of the COCO dataset.
        dataType: What to load (train, val, minival, valminusminival)
        dataYear: What dataset year to load (2014, 2017) as a string, not an integer
        Note:
            For 2014, use "train", "val", "minival", or "valminusminival"
            For 2017, only "train" and "val" annotations are available
        """

        # Setup paths and file names
        if dataType == "minival" or dataType == "valminusminival":
            imgDir = "{}/{}{}".format(dataDir, "val", dataYear)
            imgZipFile = "{}/{}{}.zip".format(dataDir, "val", dataYear)
            imgURL = "http://images.cocodataset.org/zips/{}{}.zip".format("val", dataYear)
        else:
            imgDir = "{}/{}{}".format(dataDir, dataType, dataYear)
            imgZipFile = "{}/{}{}.zip".format(dataDir, dataType, dataYear)
            imgURL = "http://images.cocodataset.org/zips/{}{}.zip".format(dataType, dataYear)
        # print("Image paths:"); print(imgDir); print(imgZipFile); print(imgURL)

        # Create main folder if it doesn't exist yet
        if not os.path.exists(dataDir):
            os.makedirs(dataDir)

        # Download images if not available locally
        if not os.path.exists(imgDir):
            os.makedirs(imgDir)
            print("> Downloading images to " + imgZipFile + " ...")
            with urllib.urlopen(imgURL) as resp, open(imgZipFile, 'wb') as out:
                shutil.copyfileobj(resp, out)
            print("... done downloading.")
            print("> Unzipping " + imgZipFile)
            with zipfile.ZipFile(imgZipFile, "r") as zip_ref:
                zip_ref.extractall(dataDir)
            print("... done unzipping")
        print("> Will use images in " + imgDir)

        # Setup annotations data paths
        annDir = "{}/annotations".format(dataDir)
        if dataType == "minival":
            annZipFile = "{}/instances_minival2014.json.zip".format(dataDir)
            annFile = "{}/instances_minival2014.json".format(annDir)
            annURL = "https://dl.dropboxusercontent.com/s/o43o90bna78omob/instances_minival2014.json.zip?dl=0"
            unZipDir = annDir
        elif dataType == "valminusminival":
            annZipFile = "{}/instances_valminusminival2014.json.zip".format(dataDir)
            annFile = "{}/instances_valminusminival2014.json".format(annDir)
            annURL = "https://dl.dropboxusercontent.com/s/s3tw5zcg7395368/instances_valminusminival2014.json.zip?dl=0"
            unZipDir = annDir
        else:
            annZipFile = "{}/annotations_trainval{}.zip".format(dataDir, dataYear)
            annFile = "{}/instances_{}{}.json".format(annDir, dataType, dataYear)
            annURL = "http://images.cocodataset.org/annotations/annotations_trainval{}.zip".format(dataYear)
            unZipDir = dataDir
        # print("Annotations paths:"); print(annDir); print(annFile); print(annZipFile); print(annURL)

        # Download annotations if not available locally
        if not os.path.exists(annDir):
            os.makedirs(annDir)
        if not os.path.exists(annFile):
            if not os.path.exists(annZipFile):
                print("> Downloading zipped annotations to " + annZipFile + " ...")
                with urllib.urlopen(annURL) as resp, open(annZipFile, 'wb') as out:
                    shutil.copyfileobj(resp, out)
                print("... done downloading.")
            print("> Unzipping " + annZipFile)
            with zipfile.ZipFile(annZipFile, "r") as zip_ref:
                zip_ref.extractall(unZipDir)
            print("... done unzipping")
        print("> Will use annotations in " + annFile)

    def load_mask(self, image_id):
        """Load instance masks for the given image.

        Different datasets use different ways to store masks. This
        function converts the different mask format to one format
        in the form of a bitmap [height, width, instances].

        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 COCO image, delegate to parent class.
        image_info = self.image_info[image_id]
        if image_info["source"] != "coco":
            return super(CocoDataset, self).load_mask(image_id)

        instance_masks = []
        class_ids = []
        annotations = self.image_info[image_id]["annotations"]
        # Build mask of shape [height, width, instance_count] and list
        # of class IDs that correspond to each channel of the mask.
        for annotation in annotations:
            class_id = self.map_source_class_id(
                "coco.{}".format(annotation['category_id']))
            if class_id:
                m = self.annToMask(annotation, image_info["height"],
                                   image_info["width"])
                # Some objects are so small that they're less than 1 pixel area
                # and end up rounded out. Skip those objects.
                if m.max() < 1:
                    continue
                # Is it a crowd? If so, use a negative class ID.
                if annotation['iscrowd']:
                    # Use negative class ID for crowds
                    class_id *= -1
                    # For crowd masks, annToMask() sometimes returns a mask
                    # smaller than the given dimensions. If so, resize it.
                    if m.shape[0] != image_info["height"] or m.shape[1] != image_info["width"]:
                        m = np.ones([image_info["height"], image_info["width"]], dtype=bool)
                instance_masks.append(m)
                class_ids.append(class_id)

        # Pack instance masks into an array
        if class_ids:
            mask = np.stack(instance_masks, axis=2).astype(np.bool)
            class_ids = np.array(class_ids, dtype=np.int32)
            return mask, class_ids
        else:
            # Call super class to return an empty mask
            return super(CocoDataset, self).load_mask(image_id)

    def image_reference(self, image_id):
        """Return a link to the image in the COCO Website."""
        info = self.image_info[image_id]
        if info["source"] == "coco":
            return "http://cocodataset.org/#explore?id={}".format(info["id"])
        else:
            super(CocoDataset, self).image_reference(image_id)

    # The following two functions are from pycocotools with a few changes.

    def annToRLE(self, ann, height, width):
        """
        Convert annotation which can be polygons, uncompressed RLE to RLE.
        :return: binary mask (numpy 2D array)
        """
        segm = ann['segmentation']
        if isinstance(segm, list):
            # polygon -- a single object might consist of multiple parts
            # we merge all parts into one mask rle code
            rles = maskUtils.frPyObjects(segm, height, width)
            rle = maskUtils.merge(rles)
        elif isinstance(segm['counts'], list):
            # uncompressed RLE
            rle = maskUtils.frPyObjects(segm, height, width)
        else:
            # rle
            rle = ann['segmentation']
        return rle

    def annToMask(self, ann, height, width):
        """
        Convert annotation which can be polygons, uncompressed RLE, or RLE to binary mask.
        :return: binary mask (numpy 2D array)
        """
        rle = self.annToRLE(ann, height, width)
        m = maskUtils.decode(rle)
        return m


############################################################
#  COCO Evaluation
############################################################

def build_coco_results(dataset, image_ids, rois, class_ids, scores, masks):
    """Arrange resutls to match COCO specs in http://cocodataset.org/#format
    """
    # If no results, return an empty list
    if rois is None:
        return []

    results = []
    for image_id in image_ids:
        # Loop through detections
        for i in range(rois.shape[0]):
            class_id = class_ids[i]
            score = scores[i]
            bbox = np.around(rois[i], 1)
            mask = masks[:, :, i]

            result = {
                "image_id": image_id,
                "category_id": dataset.get_source_class_id(class_id, "coco"),
                "bbox": [bbox[1], bbox[0], bbox[3] - bbox[1], bbox[2] - bbox[0]],
                "score": score,
                "segmentation": maskUtils.encode(np.asfortranarray(mask))
            }
            results.append(result)
    return results


def evaluate_coco(model, dataset, coco, eval_type="bbox", limit=0, image_ids=None):
    """Runs official COCO evaluation.
    dataset: A Dataset object with valiadtion data
    eval_type: "bbox" or "segm" for bounding box or segmentation evaluation
    limit: if not 0, it's the number of images to use for evaluation
    """
    # Pick COCO images from the dataset
    image_ids = image_ids or dataset.image_ids

    # Limit to a subset
    if limit:
        image_ids = image_ids[:limit]

    # Get corresponding COCO image IDs.
    coco_image_ids = [dataset.image_info[id]["id"] for id in image_ids]

    t_prediction = 0
    t_start = time.time()

    results = []
    for i, image_id in enumerate(image_ids):
        # Load image
        image = dataset.load_image(image_id)

        # Run detection
        t = time.time()
        r = model.detect([image], verbose=0)[0]
        t_prediction += (time.time() - t)

        # Convert results to COCO format
        # Cast masks to uint8 because COCO tools errors out on bool
        image_results = build_coco_results(dataset, coco_image_ids[i:i + 1],
                                           r["rois"], r["class_ids"],
                                           r["scores"],
                                           r["masks"].astype(np.uint8))
        results.extend(image_results)

    # Load results. This modifies results with additional attributes.
    print (results)
    coco_results = coco.loadRes(results)

    # Evaluate
    cocoEval = COCOeval(coco, coco_results, eval_type)
    cocoEval.params.imgIds = coco_image_ids
    cocoEval.evaluate()
    cocoEval.accumulate()
    cocoEval.summarize()

    print("> Prediction time: {}. Average {}/image".format(
        t_prediction, t_prediction / len(image_ids)))
    print("> Total time: ", time.time() - t_start)


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


if __name__ == '__main__':
    import argparse

    # Parse command line arguments
    parser = argparse.ArgumentParser(
        description='Train Mask R-CNN on MS COCO.')
    parser.add_argument("command",
                        metavar="<command>",
                        help="'train' or 'evaluate' on MS COCO")
    parser.add_argument('--dataset', required=False,
                        default = DEFAULT_DATASET_DIR,
                        metavar="/path/to/coco/",
                        help='Directory of the MS-COCO dataset')
    parser.add_argument('--year', required=False,
                        default=DEFAULT_DATASET_YEAR,
                        metavar="<year>",
                        help='Year of the MS-COCO dataset (2014 or 2017) (default=2014)')
    parser.add_argument('--model', 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('--limit', required=False,
                        default=500,
                        metavar="<image count>",
                        help='Images to use for evaluation (default=500)')
    parser.add_argument('--download', required=False,
                        default=False,
                        metavar="<True|False>",
                        help='Automatically download and unzip MS-COCO files (default=False)',
                        type=bool)
    parser.add_argument('--classes', required=False,
                        default=None,
                        metavar="<class names>",
                        help='classes that should be trained on. Default are all')
    args = parser.parse_args()
    print("Command: ", args.command)
    print("Model: ", args.model)
    print("Dataset: ", args.dataset)
    print("Year: ", args.year)
    print("Logs: ", args.logs)
    print("Auto Download: ", args.download)
    print("Classes (None means all):", args.classes)

    # classes must be a list
    args.classes = list(args.classes)

    # Configurations
    if args.command == "train":
        config = CocoConfig()
    else:
        class InferenceConfig(CocoConfig):
            # 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
            DETECTION_MIN_CONFIDENCE = 0
        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.model.lower() == "coco":
        model_path = COCO_MODEL_PATH
    elif args.model.lower() == "last":
        # Find last trained weights
        model_path = model.find_last()[1]
    elif args.model.lower() == "imagenet":
        # Start from ImageNet trained weights
        model_path = model.get_imagenet_weights()
    else:
        model_path = args.model

    # Load weights
    print("> Loading weights from {} ".format(model_path))
    model.load_weights(model_path, by_name=True)

    # Train or evaluate
    if args.command == "train":
        # Training dataset. Use the training set and 35K from the
        # validation set, as as in the Mask RCNN paper.
        dataset_train = CocoDataset()
        dataset_train.load_coco(args.dataset, "train", year=args.year, class_names=args.classes, auto_download=args.download)
        if args.year is "2014":
            dataset_train.load_coco(args.dataset, "valminusminival", year=args.year, class_names=args.classes, auto_download=args.download)
        dataset_train.prepare()

        # Validation dataset
        dataset_val = CocoDataset()
        if args.year is "2014":
            dataset_val.load_coco(args.dataset, "minival", year=args.year, class_names=args.classes, auto_download=args.download)
        else:
            dataset_val.load_coco(args.dataset, "val", year=args.year, class_names=args.classes, auto_download=args.download)
        dataset_val.prepare()

        # Image Augmentation
        # Right/Left flip 50% of the time
        augmentation = imgaug.augmenters.Fliplr(0.5)

        # *** This training schedule is an example. Update to your needs ***

        # Training - Stage 1
        print("> Training network heads")
        model.train(dataset_train, dataset_val,
                    learning_rate=config.LEARNING_RATE,
                    epochs=40,
                    layers='heads',
                    augmentation=augmentation)

        # Training - Stage 2
        # Finetune layers from ResNet stage 4 and up
        print("> Fine tune {} stage 4 and up".format(config.BACKBONE))
        model.train(dataset_train, dataset_val,
                    learning_rate=config.LEARNING_RATE,
                    epochs=120,
                    layers='4+',
                    augmentation=augmentation)

        # Training - Stage 3
        # Fine tune all layers
        print("> Fine tune all layers")
        model.train(dataset_train, dataset_val,
                    learning_rate=config.LEARNING_RATE / 10,
                    epochs=160,
                    layers='all',
                    augmentation=augmentation)

    elif args.command == "evaluate":
        # Validation dataset
        dataset_val = CocoDataset()
        if args.year is "2014":
            coco = dataset_val.load_coco(args.dataset, "minival", year=args.year, class_names=args.classes, return_coco=True, auto_download=args.download)
        else:
            coco = dataset_val.load_coco(args.dataset, "val", year=args.year, class_names=args.classes, return_coco=True, auto_download=args.download)
        dataset_val.prepare()
        print("> Running COCO evaluation on {} images.".format(args.limit))
        evaluate_coco(model, dataset_val, coco, "bbox", limit=int(args.limit))
    else:
        print("> '{}' is not recognized. "
              "Use 'train' or 'evaluate'".format(args.command))