def __init__(self, **kwargs):
dataset = kwargs.get('dataset')
splitBy = kwargs.get('splitBy')
split = kwargs.get('split')
data_json = osp.join('cache/prepro', dataset + "_" + splitBy,
split + '.json')
with open(data_json, 'r') as f:
self.data = json.load(f)
#only use the questinos having 1 bbox as answer
datanew = []
for ent in self.data:
gtbox = ent['gtbox']
if len(gtbox[0]) != 0 and len(gtbox) == 1:
datanew.append(ent)
self.data = datanew
dictfile = kwargs.get('dictionaryfile')
self.dictionary = Dictionary.load_from_file(dictfile)
if kwargs.get('testrun'):
self.data = self.data[:32]
self.spatial = True
self.image_features_path_coco = kwargs.get('coco_bottomup')
self.coco_id_to_index = self.id_to_index(self.image_features_path_coco)
print("Dataset [{}] loaded....".format(dataset, split))
print("Split [{}] has {} ref exps.".format(split, len(self.data)))
def __init__(self, **kwargs):
file = kwargs.get('file')
self.isnms = kwargs.get('isnms')
self.trainembd = kwargs.get('trainembd')
#6 postion encoded vectors as used by irls
self.spatial = True
with open(file, 'rb') as f:
self.data = pickle.load(f)
if self.trainembd:
self.dictionary = Dictionary.load_from_file(
kwargs.get('dictionaryfile'))
if kwargs.get('testrun'):
self.data = self.data[:32]
self.pool_features_path_coco = kwargs.get('coco_pool_features')
self.pool_features_path_genome = kwargs.get('genome_pool_features')
self.poolcoco_id_to_index = self._poolcreate_coco_id_to_index(
self.pool_features_path_coco)
self.poolcoco_id_to_index_gen = self._poolcreate_coco_id_to_index(
self.pool_features_path_genome)
self.image_features_path_coco = kwargs.get('coco_bottomup')
self.coco_id_to_index = self.id_to_index(self.image_features_path_coco)
self.image_features_path_genome = kwargs.get('genome_bottomup')
self.genome_id_to_index = self.id_to_index(
self.image_features_path_genome)
def __init__(self, **kwargs):
dataset = kwargs.get('dataset')
splitBy = kwargs.get('splitBy')
split = kwargs.get('split')
data_json = osp.join('cache/prepro', "vqd" + "_" + splitBy,
split + '.json')
with open(data_json, 'r') as f:
self.data = json.load(f)
#only use 1 or more gt bos
if dataset == 'vqd1':
print('VQDv1 1box loaded .......')
#only use the questinos having 1 bbox as answer
datanew = []
for ent in self.data:
gtbox = ent['gtbox']
if len(gtbox[0]) != 0 and len(gtbox) == 1:
datanew.append(ent)
self.data = datanew
dictfile = kwargs.get('dictionaryfile')
self.dictionary = Dictionary.load_from_file(dictfile)
if kwargs.get('testrun'):
self.data = self.data[:32]
self.spatial = True
self.image_features_path_coco = kwargs.get('vqd_detfeats').format(
split)
self.coco_id_to_index = self.id_to_index(self.image_features_path_coco)
print("Dataset [{}] loaded....".format(dataset, split))
print("Split [{}] has {} ref exps.".format(split, len(self.data)))
cocoids = set(self.coco_id_to_index)
if kwargs.get('istrain'):
cocoids.remove(81768)
#some qid doesnot exist
datanew = []
for ent in self.data:
#some image ids are not in the dataset
if ent['image_id'] in cocoids:
datanew.append(ent)
self.data = datanew
def __init__(self,**kwargs):
dataset = kwargs.get('dataset')
splitBy = kwargs.get('splitBy')
split = kwargs.get('split')
data_json = osp.join('cache/prepro', dataset +"_"+ splitBy , split +'.json')
with open(data_json,'r') as f:
self.data = json.load(f)
dictfile = kwargs.get('dictionaryfile')
self.dictionary = Dictionary.load_from_file(dictfile)
if kwargs.get('testrun'):
self.data = self.data[:32]
self.spatial = True
print ("Dataset [{}] loaded....".format(dataset,split))
print ("Split [{}] has {} ref exps.".format(split,len(self.data)))
def __init__(self, **kwargs):
dataset = kwargs.get('dataset')
splitBy = kwargs.get('splitBy')
split = kwargs.get('split')
data_json = osp.join('cache/prepro', dataset + "_" + splitBy,
split + '.json')
with open(data_json, 'r') as f:
self.data = json.load(f)
dictfile = kwargs.get('dictionaryfile')
self.dictionary = Dictionary.load_from_file(dictfile)
if kwargs.get('testrun'):
self.data = self.data[:32]
self.spatial = True
feats_use = '{}_{}_det_feats.h5'.format(dataset, splitBy)
self.image_features_path_coco = osp.join(kwargs.get('refcoco_frcnn'),
feats_use)
self.coco_id_to_index = self.id_to_index(self.image_features_path_coco)
print("Dataset [{}] loaded....".format(dataset, split))
print("Split [{}] has {} ref exps.".format(split, len(self.data)))
def create_glove_embedding_init(idx2word, glove_file):
word2emb = {}
with open(glove_file, 'r') as f:
entries = f.readlines()
emb_dim = len(entries[0].split(' ')) - 1
print('embedding dim is %d' % emb_dim)
weights = np.zeros((len(idx2word), emb_dim), dtype=np.float32)
for entry in entries:
vals = entry.split(' ')
word = vals[0]
vals = [float(val) for val in vals[1:]]
word2emb[word] = np.array(vals)
for idx, word in enumerate(idx2word):
if word not in word2emb:
continue
weights[idx] = word2emb[word]
return weights, word2emb
if __name__ == '__main__':
ds = 'Ourdb'
d = create_dictionary(ds)
d.dump_to_file('data/dictionary.pickle')
d = Dictionary.load_from_file('data/dictionary.pickle')
emb_dim = 300
glove_file = 'data/glove/glove.6B.%dd.txt' % emb_dim
weights, word2emb = create_glove_embedding_init(d.idx2word, glove_file)
np.save('data/glove6b_init_%dd.npy' % emb_dim, weights)
import os.path as osp
import json
for ds in config.dataset:
kwargs = {**config.global_config, **config.dataset[ds]}
data_root = kwargs.get('data_root')
dataset = kwargs.get('dataset')
splitBy = kwargs.get('splitBy')
splits = kwargs.get('splits')
data = []
for split in splits + ['train']:
data_json = osp.join('cache/prepro', dataset + "_" + splitBy,
split + '.json')
with open(data_json, 'r') as f:
d = json.load(f)
data.extend(d)
d = create_dictionary(data, dataset=dataset)
basedir = os.path.dirname(kwargs['dictionaryfile'].format(dataset))
if not os.path.exists(basedir):
os.mkdir(basedir)
d.dump_to_file(kwargs['dictionaryfile'].format(dataset))
d = Dictionary.load_from_file(kwargs['dictionaryfile'].format(dataset))
emb_dim = 300
glove = 'glove/glove.6B.%dd.txt' % emb_dim
embedding_basedir = os.path.dirname(kwargs['glove'])
glove_file = embedding_basedir.format(glove)
weights, word2emb = create_glove_embedding_init(d.idx2word, glove_file)
np.save(
os.path.join(embedding_basedir.format(ds),
'glove6b_init_%dd.npy' % emb_dim), weights)
