Python script that can auto-annotate the images

Question

I am using the https://github.com/mdhmz1/Auto-Annotate repo. I have tried to custom train my own dataset which has it own COCO JSON format file.

When I try to run

python3 customTrain.py train --dataset=path/to/dir --weights=coco

I get the following error:

Traceback (most recent call last):
File "customTrain.py", line 279, in
train(model)
File "customTrain.py", line 179, in train
dataset_train.load_custom(args.dataset, "train")
File "customTrain.py", line 87, in load_custom
annotations = [a for a in annotations if a['regions']]
File "customTrain.py", line 87, in
annotations = [a for a in annotations if a['regions']]
TypeError: list indices must be integers or slices, not str

My customtrain.py looks like the following:

import os
import sys
import json
import datetime
import numpy as np
import skimage.draw

Root directory of the project
ROOT_DIR = "/home/hiwi/Auto-Annotate"

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 CustomConfig(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 = "custom"

IMAGES_PER_GPU = 1

# Number of classes (including background)
NUM_CLASSES = 1 + 2  # Background + 2 classes

# Number of training steps per epoch
STEPS_PER_EPOCH = 100

# Skip detections with < 90% confidence
DETECTION_MIN_CONFIDENCE = 0.9
############################################################

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

class CustomDataset(utils.Dataset):

def load_custom(self, dataset_dir, subset):
    """Load a subset of the Custom 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("custom", 0, "Primary_Track")
    self.add_class("custom", 1, "Secondary_Track")

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

    # Load annotations
    # VGG Image Annotator (up to version 1.6) saves each image in the form:
    # { 'filename': '28503151_5b5b7ec140_b.jpg',
    #   'regions': {
    #       '0': {
    #           'region_attributes': {},
    #           'shape_attributes': {
    #               'all_points_x': [...],
    #               'all_points_y': [...],
    #               'name': 'polygon'}},
    #       ... more regions ...
    #   },
    #   'size': 100202
    # }
    # We mostly care about the x and y coordinates of each region
    # Note: In VIA 2.0, regions was changed from a dict to a list.
    annotations1 = json.load(open(os.path.join(dataset_dir, "train.json")))
    annotations = list(annotations1.values())  # don't need the dict keys

    # The VIA tool saves images in the JSON even if they don't have any
    # annotations. Skip unannotated images.
    annotations = [a for a in annotations if a['regions']]

    # Add images
    for a in annotations:
        # Get the x, y coordinaets of points of the polygons that make up
        # the outline of each object instance. These are stores in the
        # shape_attributes (see json format above)
        # The if condition is needed to support VIA versions 1.x and 2.x.
        if type(a['regions']) is dict:
            polygons = [r['shape_attributes'] for r in a['regions'].values()]
        else:
            polygons = [r['shape_attributes'] for r in a['regions']]

        #labelling each class in the given image to a number 

        custom = [s['region_attributes'] for s in a['regions']]

        num_ids=[]
        #Add the classes according to the requirement
        for n in custom:
            try:
                if n['name']=="Primary_Track":
                    num_ids.append(0)
                elif n['name']=='Secondary_Track':
                    num_ids.append(1)
            except:
                pass

        # load_mask() needs the image size to convert polygons to masks.
        # Unfortunately, VIA doesn't include it in JSON, so we must read
        # the image. This is only managable since the dataset is tiny.
        image_path = os.path.join(dataset_dir, a['filename'])
        image = skimage.io.imread(image_path)
        height, width = image.shape[:2]

        self.add_image(
            "custom",
            image_id=a['filename'],  # use file name as a unique image id
            path=image_path,
            width=width, height=height,
            polygons=polygons,
            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 custom dataset image, delegate to parent class.
    image_info = self.image_info[image_id]
    if image_info["source"] != "custom":
        return super(self.__class__, self).load_mask(image_id)
    num_ids = image_info['num_ids']
    #print("Here is the numID",num_ids)

    # 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)
    for i, p in enumerate(info["polygons"]):
        if p['name'] == 'polygon':
        # 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'])
        else:
            rr, cc = skimage.draw.rectangle((p['y'], p['x']), extent=(p['height'], p['width']))

        rr[rr > mask.shape[0]-1] = mask.shape[0]-1
        cc[cc > mask.shape[1]-1] = mask.shape[1]-1
        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
    num_ids = np.array(num_ids, dtype=np.int32)
    return mask.astype(np.bool), num_ids.astype(np.bool), np.ones([mask.shape[-1]], dtype=np.int32)
    #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"] == "Railtrack":
        return info["path"]
    else:
        super(self.__class__, self).image_reference(image_id)
def train(model):
"""Train the model."""
# Training dataset.
dataset_train = CustomDataset()
dataset_train.load_custom(args.dataset, "train")
dataset_train.prepare()

# Validation dataset
dataset_val = CustomDataset()
dataset_val.load_custom(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=30,
            layers='heads')
############################################################

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

if name == 'main':
import argparse

# Parse command line arguments
parser = argparse.ArgumentParser(
    description='Train Mask R-CNN to detect custom objects.')
parser.add_argument("command",
                    metavar="<command>",
                    help="'train' or 'splash'")
parser.add_argument('--dataset', required=False,
                    metavar="/path/to/custom/dataset/",
                    help='Directory of the Custom 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 = CustomConfig()

# Create model
if args.command == "train":
    model = modellib.MaskRCNN(mode="training", 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)

# Train or evaluate
if args.command == "train":
    train(model)
else:
    print("'{}' is not recognized. "
          "Use 'train' or 'splash'".format(args.command))