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_explain_dictionary(dataroot, thres):
dictionary = Dictionary()
counter = Counter()
files = [
'VQA-E_train_set.json',
'VQA-E_val_set.json',
]
for path in 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)
return dictionary
def create_caption_dictionary(dataroot, thres):
dictionary = Dictionary()
counter = Counter()
files = [
'captions_train2014.json',
'captions_val2014.json',
]
for path in files:
caption_path = os.path.join(dataroot, path)
qs = json.load(open(caption_path))['annotations']
for q in qs:
counter.update(dictionary.word_token(q['caption']))
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)
return dictionary
def create_VQAX_explain_dictionary(dataroot, thres):
dictionary = Dictionary()
counter = Counter()
files = [
'train_exp_anno.json',
'val_exp_anno.json',
'test_exp_anno.json',
]
for path in files:
explain_path = os.path.join(dataroot, path)
es = json.load(open(explain_path))
for e in es.items():
for E in e[1]:
counter.update(dictionary.word_token(E))
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)
return dictionary
