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
def create_question_explain_dictionary(dataroot, thres):
dictionary = Dictionary()
counter = Counter()
question_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'
]
explain_files = [
'VQA-E_train_set.json',
'VQA-E_val_set.json',
]
for path in explain_files:
explain_path = os.path.join(dataroot, path)
es = json.load(open(explain_path))
for e in es:
counter.update(dictionary.word_token(e['explanation'][0]))
dictionary.add_word('<pad>')
dictionary.add_word('<start>')
dictionary.add_word('<end>')
dictionary.add_word('<unk>')
for word, cnt in counter.items():
if cnt >= thres:
dictionary.add_word(word)
for path in question_files:
question_path = os.path.join(dataroot, path)
qs = json.load(open(question_path))['questions']
for q in qs:
dictionary.tokenize(q['question'], True)
return dictionary
def create_dictionary2(dataroot):
dictionary = Dictionary()
questions = []
files = ['train/questions.txt', 'train/questions.txt']
for path in files:
question_path = os.path.join(dataroot, path)
qs = open(question_path)
qs = qs.read().split("\n")
for q in qs:
dictionary.tokenize(q, True)
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
questions = []
files = ['VQA_caption_traindataset.pkl', 'VQA_caption_valdataset.pkl']
for path in files:
question_path = os.path.join(dataroot, path)
dataset = cPickle.load(open(question_path, 'rb'))
for idx in range(len(dataset)):
captions = dataset[idx]['caption']
for cap in captions:
dictionary.tokenize(cap, True)
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
files = ['allwords4verbq1.json']
for path in files:
question_path = os.path.join(dataroot, path)
q_data = json.load(open(question_path))
for label, eng_name in q_data.items():
dictionary.tokenize(eng_name, True)
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
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)
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
questions = []
files = [
'OpenEnded_abstract_v002_test2015_questions.json',
'OpenEnded_abstract_v002_train2015_questions.json',
'OpenEnded_abstract_v002_val2015_questions.json',
'MultipleChoice_abstract_v002_test2015_questions.json',
'MultipleChoice_abstract_v002_train2015_questions.json',
'MultipleChoice_abstract_v002_val2015_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)
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
questions = []
files = ['vqacp_v2_train_questions.json',
'vqacp_v2_test_questions.json'
]
for path in files:
question_path = os.path.join(dataroot, path)
qs = json.load(open(question_path))
for q in qs:
dictionary.tokenize(q['question'], True)
if 'train' in path:
try:
dictionary.tokenize(q['orig_question'], True)
except:
continue
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
role_name_corrector = 'data/roles_namecorrected.json'
role_name_dict = json.load(open(role_name_corrector))
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 = role_name_dict[role]
dictionary.tokenize(question, True)
return dictionary
def create_dictionary(dataroot):
dictionary = Dictionary()
#general 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)
#tempalted words
with open(os.path.join(dataroot, 'role_abstracts.txt')) as f:
content = f.readlines()
verb_desc = [x.strip() for x in content]
for desc in verb_desc:
dictionary.tokenize(desc, True)
#labels
question_path = os.path.join(dataroot, 'all_label_mapping.json')
q_data = json.load(open(question_path))
for label, eng_name in q_data.items():
dictionary.tokenize(eng_name, True)
return dictionary
from dataset import Dictionary
if __name__ == '__main__':
d = Dictionary()
all_sent = d.get_all_sentence()
print all_sent[0], all_sent[1]
token1 = d.tokenize(all_sent[0], False)
token2 = d.tokenize(all_sent[1], False)
print token1, token2
def create_dictionary(question):
dictionary = Dictionary()
dictionary.tokenize(question, True)
return dictionary
