def create_dictionary(dataroot):
dictionary = Dictionary()
questions = []
files = [
'v2_OpenEnded_mscoco_train2014_questions.json',
'v2_OpenEnded_mscoco_val2014_questions.json',
'v2_OpenEnded_mscoco_test2015_questions.json',
'v2_OpenEnded_mscoco_test-dev2015_questions.json'
]
for path in files:
question_path = os.path.join(dataroot, path)
qs = json.load(open(question_path))['questions']
for q in qs:
dictionary.tokenize(q['question'], True)
print('words coming from vqa ', dictionary.__len__())
#add all collected words from imsitu. contains both overlaps with vqa as well as new words
imsitu_words_path = os.path.join(
dataroot, 'allnverbs_imsitu_words_nl2vqamatching.json')
imsitu_words = json.load(open(imsitu_words_path))
for label, eng_name in imsitu_words.items():
dictionary.tokenize(eng_name, True)
print(' with words coming from imsitu ', dictionary.__len__())
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
questions = []
files = ['imsitu_questions_prev.json']
for path in files:
question_path = os.path.join(dataroot, path)
q_data = json.load(open(question_path))
for verb, values in q_data.items():
roles = values['roles']
for role, info in roles.items():
question = info['question']
dictionary.tokenize(question, True)
#add all collected words from imsitu. contains both overlaps with vqa as well as new words
imsitu_words_path = os.path.join(
dataroot, 'allnverbsall_imsitu_words_nl2glovematching.json')
imsitu_words = json.load(open(imsitu_words_path))
for label, eng_name in imsitu_words.items():
dictionary.tokenize(eng_name, True)
print(' with words coming from imsitu ', dictionary.__len__())
return dictionary