def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
python类load()的实例源码
def __init__(self, batchsize=64, max_length=config.MAX_WORDS_IN_QUESTION, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.mode = mode
#self.max_length, self.qdic, self.adic = VQADataProvider.load_data(mode)
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/vdict.json','r') as f:
self.vdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
# self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
# self.glove_dict = {} # word -> glove vector
def load_vqa_json(data_split):
"""
Parses the question and answer json files for the given data split.
Returns the question dictionary and the answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS[data_split]['ques_file'], 'r') as f:
qdata = json.load(f)['questions']
for q in qdata:
qdic[data_split + QID_KEY_SEPARATOR + str(q['question_id'])] = \
{'qstr': q['question'], 'iid': q['image_id']}
if 'test' not in data_split:
with open(config.DATA_PATHS[data_split]['ans_file'], 'r') as f:
adata = json.load(f)['annotations']
for a in adata:
adic[data_split + QID_KEY_SEPARATOR + str(a['question_id'])] = \
a['answers']
write_log('parsed ' + str(len(qdic)) + ' questions for ' + data_split, 'log.txt')
return qdic, adic
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
def __init__(self, batchsize=64, max_length=config.MAX_WORDS_IN_QUESTION, max_w_length=config.LENGTH_OF_LONGEST_WORD, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.max_w_length = max_w_length
self.mode = mode
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/cdict.json','r') as f:
self.cdict = json.load(f)
with open('./result/vdict.json','r') as f:
self.vdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
#self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
#self.glove_dict = {} # word -> glove vector
def load_vqa_json(data_split):
"""
Parses the question and answer json files for the given data split.
Returns the question dictionary and the answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS[data_split]['ques_file'], 'r') as f:
qdata = json.load(f)['questions']
for q in qdata:
qdic[data_split + QID_KEY_SEPARATOR + str(q['question_id'])] = \
{'qstr': q['question'], 'iid': q['image_id']}
if 'test' not in data_split:
with open(config.DATA_PATHS[data_split]['ans_file'], 'r') as f:
adata = json.load(f)['annotations']
for a in adata:
adic[data_split + QID_KEY_SEPARATOR + str(a['question_id'])] = \
a['answers']
write_log('parsed ' + str(len(qdic)) + ' questions for ' + data_split, 'log.txt')
return qdic, adic
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
def __init__(self, batchsize=64, max_length=config.MAX_WORDS_IN_QUESTION, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.mode = mode
# self.max_length, self.qdic, self.adic = VQADataProvider.load_data(mode)
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/vdict.json','r') as f:
self.vdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
# self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
# self.glove_dict = {} # word -> glove vector
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
def __init__(self, batchsize=64, max_length=config.MAX_WORDS_IN_QUESTION, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.mode = mode
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/vdict.json','r') as f:
self.vdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
# self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
# self.glove_dict = {} # word -> glove vector
def load_vqa_json(data_split):
"""
Parses the question and answer json files for the given data split.
Returns the question dictionary and the answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS[data_split]['ques_file'], 'r') as f:
qdata = json.load(f)['questions']
for q in qdata:
qdic[data_split + QID_KEY_SEPARATOR + str(q['question_id'])] = \
{'qstr': q['question'], 'iid': q['image_id']}
if 'test' not in data_split:
with open(config.DATA_PATHS[data_split]['ans_file'], 'r') as f:
adata = json.load(f)['annotations']
for a in adata:
adic[data_split + QID_KEY_SEPARATOR + str(a['question_id'])] = \
a['answers']
write_log('parsed ' + str(len(qdic)) + ' questions for ' + data_split, 'log.txt')
return qdic, adic
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
def __init__(self, batchsize=64, max_length=config.MAX_WORDS_IN_QUESTION, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.mode = mode
#self.max_length, self.qdic, self.adic = VQADataProvider.load_data(mode)
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/vdict.json','r') as f:
self.vdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
# self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
# self.glove_dict = {} # word -> glove vector
def load_vqa_json(data_split):
"""
Parses the question and answer json files for the given data split.
Returns the question dictionary and the answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS[data_split]['ques_file'], 'r') as f:
qdata = json.load(f)['questions']
for q in qdata:
qdic[data_split + QID_KEY_SEPARATOR + str(q['question_id'])] = \
{'qstr': q['question'], 'iid': q['image_id']}
if 'test' not in data_split:
with open(config.DATA_PATHS[data_split]['ans_file'], 'r') as f:
adata = json.load(f)['annotations']
for a in adata:
adic[data_split + QID_KEY_SEPARATOR + str(a['question_id'])] = \
a['answers']
write_log('parsed ' + str(len(qdic)) + ' questions for ' + data_split, 'log.txt')
return qdic, adic
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
def __init__(self, batchsize=64, max_length=config.MAX_WORDS_IN_QUESTION, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.mode = mode
#self.max_length, self.qdic, self.adic = VQADataProvider.load_data(mode)
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/vdict.json','r') as f:
self.vdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
# self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
# self.glove_dict = {} # word -> glove vector
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
def __init__(self, batchsize=64, max_length=config.MAX_CHARS_IN_QUESTION, mode='train'):
self.batchsize = batchsize
self.d_vocabulary = None
self.batch_index = None
self.batch_len = None
self.rev_adict = None
self.max_length = max_length
self.mode = mode
self.qdic, self.adic = VQADataProvider.load_data(mode)
with open('./result/cdict.json','r') as f:
self.cdict = json.load(f)
with open('./result/adict.json','r') as f:
self.adict = json.load(f)
self.n_ans_vocabulary = len(self.adict)
#self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
#self.glove_dict = {} # word -> glove vector
def load_vqa_json(data_split):
"""
Parses the question and answer json files for the given data split.
Returns the question dictionary and the answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS[data_split]['ques_file'], 'r') as f:
qdata = json.load(f)['questions']
for q in qdata:
qdic[data_split + QID_KEY_SEPARATOR + str(q['question_id'])] = \
{'qstr': q['question'], 'iid': q['image_id']}
if 'test' not in data_split:
with open(config.DATA_PATHS[data_split]['ans_file'], 'r') as f:
adata = json.load(f)['annotations']
for a in adata:
adic[data_split + QID_KEY_SEPARATOR + str(a['question_id'])] = \
a['answers']
write_log('parsed ' + str(len(qdic)) + ' questions for ' + data_split, 'log.txt')
return qdic, adic
def load_genome_json():
"""
Parses the genome json file. Returns the question dictionary and the
answer dictionary.
"""
qdic, adic = {}, {}
with open(config.DATA_PATHS['genome']['genome_file'], 'r') as f:
qdata = json.load(f)
for q in qdata:
key = 'genome' + QID_KEY_SEPARATOR + str(q['id'])
qdic[key] = {'qstr': q['question'], 'iid': q['image']}
adic[key] = [{'answer': q['answer']}]
write_log('parsed ' + str(len(qdic)) + ' questions for genome', 'log.txt')
return qdic, adic
