load_description

# extract descriptions for images
def load_descriptions(doc):
	mapping = dict()
	# process lines
	for line in doc.split('\n'):
		# split line by white space
		tokens = line.split()
		if len(line) < 2:
			continue
		# take the first token as the image id, the rest as the description
		image_id, image_desc = tokens[0], tokens[1:]
		# remove filename from image id
		image_id = image_id.split('.')[0]
		# convert description tokens back to string
		image_desc = ' '.join(image_desc)
		# create the list if needed
		if image_id not in mapping:
			mapping[image_id] = list()
		# store description
		mapping[image_id].append(image_desc)
	return mapping
 
# parse descriptions
descriptions = load_descriptions(doc)
print('Loaded: %d ' % len(descriptions))