tokenizer

# convert a dictionary of clean descriptions to a list of descriptions
def to_lines(descriptions):
	all_desc = list()
	for key in descriptions.keys():
		[all_desc.append(d) for d in descriptions[key]]
	return all_desc

# fit a tokenizer given caption descriptions
def create_tokenizer(descriptions):
	lines = to_lines(descriptions)
	tokenizer = Tokenizer()
	tokenizer.fit_on_texts(lines)
	return tokenizer

# prepare tokenizer
tokenizer = create_tokenizer(train_descriptions)
vocab_size = len(tokenizer.word_index) + 1
print('Vocabulary Size: %d' % vocab_size)