def image_feats_converter(filenames):
h_train = h5py.File(filenames['train_data_file'], "w")
h_val = h5py.File(filenames['val_data_file'], "w")
if os.path.exists(filenames['train_ids_file']) and os.path.exists(filenames['val_ids_file']):
print(filenames['train_ids_file'])
print(filenames['val_ids_file'])
train_imgids = cPickle.load(open(filenames['train_ids_file'],'rb'))
val_imgids = cPickle.load(open(filenames['val_ids_file'],'rb'))
else:
train_imgids = utils.load_imageid('data/train2014')
val_imgids = utils.load_imageid('data/val2014')
cPickle.dump(train_imgids, open(filenames['train_ids_file'], 'wb'))
cPickle.dump(val_imgids, open(filenames['val_ids_file'], 'wb'))
train_indices = {}
val_indices = {}
train_img_features = h_train.create_dataset(
'image_features', (len(train_imgids), num_fixed_boxes, feature_length), 'f')
train_img_bb = h_train.create_dataset(
'image_bb', (len(train_imgids), num_fixed_boxes, 4), 'f')
train_spatial_img_features = h_train.create_dataset(
'spatial_features', (len(train_imgids), num_fixed_boxes, 6), 'f')
val_img_bb = h_val.create_dataset(
'image_bb', (len(val_imgids), num_fixed_boxes, 4), 'f')
val_img_features = h_val.create_dataset(
'image_features', (len(val_imgids), num_fixed_boxes, feature_length), 'f')
val_spatial_img_features = h_val.create_dataset(
'spatial_features', (len(val_imgids), num_fixed_boxes, 6), 'f')
train_counter = 0
val_counter = 0
print("reading tsv...")
with open(filenames['infile'], "r") as tsv_in_file:
reader = csv.DictReader(tsv_in_file, delimiter='\t', fieldnames=FIELDNAMES)
for item in tqdm(reader):
item['num_boxes'] = int(item['num_boxes'])
image_id = int(item['image_id'])
image_w = float(item['image_w'])
image_h = float(item['image_h'])
bboxes = np.frombuffer(
base64.b64decode(item['boxes']),
dtype=np.float32).reshape((item['num_boxes'], -1))
box_width = bboxes[:, 2] - bboxes[:, 0]
box_height = bboxes[:, 3] - bboxes[:, 1]
scaled_width = box_width / image_w
scaled_height = box_height / image_h
scaled_x = bboxes[:, 0] / image_w
scaled_y = bboxes[:, 1] / image_h
box_width = box_width[..., np.newaxis]
box_height = box_height[..., np.newaxis]
scaled_width = scaled_width[..., np.newaxis]
scaled_height = scaled_height[..., np.newaxis]
scaled_x = scaled_x[..., np.newaxis]
scaled_y = scaled_y[..., np.newaxis]
spatial_features = np.concatenate(
(scaled_x,
scaled_y,
scaled_x + scaled_width,
scaled_y + scaled_height,
scaled_width,
scaled_height),
axis=1)
if image_id in train_imgids:
train_imgids.remove(image_id)
train_indices[image_id] = train_counter
train_img_bb[train_counter, :, :] = bboxes
train_img_features[train_counter, :, :] = np.frombuffer(
base64.b64decode(item['features']),
dtype=np.float32).reshape((item['num_boxes'], -1))
train_spatial_img_features[train_counter, :, :] = spatial_features
train_counter += 1
elif image_id in val_imgids:
val_imgids.remove(image_id)
val_indices[image_id] = val_counter
val_img_bb[val_counter, :, :] = bboxes
val_img_features[val_counter, :, :] = np.frombuffer(
base64.b64decode(item['features']),
dtype=np.float32).reshape((item['num_boxes'], -1))
val_spatial_img_features[val_counter, :, :] = spatial_features
val_counter += 1
else:
assert False, 'Unknown image id: %d' % image_id
if len(train_imgids) != 0:
print('Warning: train_image_ids is not empty')
if len(val_imgids) != 0:
print('Warning: val_image_ids is not empty')
cPickle.dump(train_indices, open(filenames['train_indices_file'], 'wb'))
cPickle.dump(val_indices, open(filenames['val_indices_file'], 'wb'))
h_train.close()
h_val.close()
print("done!")
val_indices_file = 'val36_imgid2idx.pkl'
train_ids_file = 'train_ids.pkl'
val_ids_file = 'val_ids.pkl'
feature_length = 2048
num_fixed_boxes = 36
if __name__ == '__main__':
h_train = h5py.File(train_data_file, "w")
h_val = h5py.File(val_data_file, "w")
if os.path.exists(train_ids_file) and os.path.exists(val_ids_file):
train_imgids = cPickle.load(open(train_ids_file))
val_imgids = cPickle.load(open(val_ids_file))
else:
train_imgids = utils.load_imageid('../data/train2014')
val_imgids = utils.load_imageid('../data/val2014')
cPickle.dump(train_imgids, open(train_ids_file, 'wb'), protocol=2)
cPickle.dump(val_imgids, open(val_ids_file, 'wb'), protocol=2)
train_indices = {}
val_indices = {}
train_img_features = h_train.create_dataset(
'image_features', (len(train_imgids), num_fixed_boxes, feature_length),
'f')
train_img_bb = h_train.create_dataset(
'image_bb', (len(train_imgids), num_fixed_boxes, 4), 'f')
train_spatial_img_features = h_train.create_dataset(
'spatial_features', (len(train_imgids), num_fixed_boxes, 6), 'f')
train_ids_file = 'data/train_ids.pkl'
val_ids_file = 'data/val_ids.pkl'
feature_length = 2048
num_fixed_boxes = 36
if __name__ == '__main__':
h_train = h5py.File(train_data_file, "w")
h_val = h5py.File(val_data_file, "w")
if os.path.exists(train_ids_file) and os.path.exists(val_ids_file):
train_imgids = cPickle.load(open(train_ids_file))
val_imgids = cPickle.load(open(val_ids_file))
else:
train_imgids = utils.load_imageid('data/train2014')
val_imgids = utils.load_imageid('data/val2014')
cPickle.dump(train_imgids, open(train_ids_file, 'wb'))
cPickle.dump(val_imgids, open(val_ids_file, 'wb'))
train_indices = {}
val_indices = {}
train_img_features = h_train.create_dataset(
'image_features', (len(train_imgids), num_fixed_boxes, feature_length), 'f')
train_img_bb = h_train.create_dataset(
'image_bb', (len(train_imgids), num_fixed_boxes, 4), 'f')
train_spatial_img_features = h_train.create_dataset(
'spatial_features', (len(train_imgids), num_fixed_boxes, 6), 'f')
val_img_bb = h_val.create_dataset(
def extract(split, infiles, task='scenario_data'):
FIELDNAMES = ["img_id", "img_h", "img_w", "objects_id", "objects_conf",
"attrs_id", "attrs_conf", "num_boxes", "boxes", "features"]
data_file = {
'infer': f'data/{task}/infer.hdf5',
}
indices_file = {
'infer': f'data/{task}/infer_imgid2idx.pkl'
}
ids_file = {
'infer': f'data/{task}/infer_ids.pkl'
}
path_imgs = {
'infer': f'data/{task}/images'
}
known_num_boxes = {'infer': None}
feature_length = 2048
min_fixed_boxes = 10
max_fixed_boxes = 100
if os.path.exists(ids_file[split]):
imgids = cPickle.load(open(ids_file[split], 'rb'))
else:
imgids = utils.load_imageid(path_imgs[split])
cPickle.dump(imgids, open(ids_file[split], 'wb'))
h = h5py.File(data_file[split], 'w')
if known_num_boxes[split] is None:
num_boxes = 0
for infile in infiles:
print("reading tsv...%s" % infile)
with open(infile, "r+") as tsv_in_file:
reader = csv.DictReader(tsv_in_file, delimiter='\t', fieldnames=FIELDNAMES)
for item in reader:
item['num_boxes'] = int(item['num_boxes'])
image_id = item['img_id']
if image_id in imgids:
num_boxes += item['num_boxes']
else:
num_boxes = known_num_boxes[split]
print('num_boxes=%d' % num_boxes)
img_features = h.create_dataset(
'image_features', (num_boxes, feature_length), 'f')
img_bb = h.create_dataset(
'image_bb', (num_boxes, 4), 'f')
spatial_img_features = h.create_dataset(
'spatial_features', (num_boxes, 6), 'f')
pos_boxes = h.create_dataset(
'pos_boxes', (len(imgids), 2), dtype='int32')
counter = 0
num_boxes = 0
indices = {}
for infile in infiles:
unknown_ids = []
print("reading tsv...%s" % infile)
with open(infile, "r+") as tsv_in_file:
reader = csv.DictReader(tsv_in_file, delimiter='\t', fieldnames=FIELDNAMES)
for item in reader:
item['num_boxes'] = int(item['num_boxes'])
item['boxes'] = bytes(item['boxes'], 'utf')
item['features'] = bytes(item['features'], 'utf')
image_id = item['img_id']
image_w = float(item['img_w'])
image_h = float(item['img_h'])
bboxes = np.frombuffer(
base64.decodestring(item['boxes']),
dtype=np.float32).reshape((item['num_boxes'], -1))
box_width = bboxes[:, 2] - bboxes[:, 0]
box_height = bboxes[:, 3] - bboxes[:, 1]
scaled_width = box_width / image_w
scaled_height = box_height / image_h
scaled_x = bboxes[:, 0] / image_w
scaled_y = bboxes[:, 1] / image_h
box_width = box_width[..., np.newaxis]
box_height = box_height[..., np.newaxis]
scaled_width = scaled_width[..., np.newaxis]
scaled_height = scaled_height[..., np.newaxis]
scaled_x = scaled_x[..., np.newaxis]
scaled_y = scaled_y[..., np.newaxis]
spatial_features = np.concatenate(
(scaled_x,
scaled_y,
scaled_x + scaled_width,
scaled_y + scaled_height,
scaled_width,
scaled_height),
axis=1)
if image_id in imgids:
imgids.remove(image_id)
indices[image_id] = counter
pos_boxes[counter,:] = np.array([num_boxes, num_boxes + item['num_boxes']])
img_bb[num_boxes:num_boxes+item['num_boxes'], :] = bboxes
img_features[num_boxes:num_boxes+item['num_boxes'], :] = np.frombuffer(
base64.decodestring(item['features']),
dtype=np.float32).reshape((item['num_boxes'], -1))
spatial_img_features[num_boxes:num_boxes+item['num_boxes'], :] = spatial_features
counter += 1
num_boxes += item['num_boxes']
else:
unknown_ids.append(image_id)
print('%d unknown_ids...' % len(unknown_ids))
print('%d image_ids left...' % len(imgids))
if len(imgids) != 0:
print('Warning: %s_image_ids is not empty' % split)
cPickle.dump(indices, open(indices_file[split], 'wb'))
h.close()
print("done!")
infile = os.path.join(
addr_BU_path, 'test2014_36/test2014_resnet101_faster_rcnn_genome_36.tsv')
test_data_file = os.path.join(addr_hdf5path, 'test201436.hdf5')
test_indices_file = os.path.join(addr_pkl_path, 'test201436_imgid2idx.pkl')
test_ids_file = os.path.join(addr_pkl_path, 'test201436_ids.pkl')
feature_length = 2048
num_fixed_boxes = 36
if __name__ == '__main__':
h_test = h5py.File(test_data_file, "w")
if os.path.exists(test_ids_file):
test_imgids = pickle.load(open(test_ids_file, 'rb'))
else:
test_imgids = utils.load_imageid(addr_test_imgs)
pickle.dump(test_imgids, open(test_ids_file, 'wb'), protocol=2)
test_indices = {}
test_img_features = h_test.create_dataset(
'image_features', (len(test_imgids), num_fixed_boxes, feature_length),
'f')
test_img_bb = h_test.create_dataset('image_bb',
(len(test_imgids), num_fixed_boxes, 4),
'f')
test_spatial_img_features = h_test.create_dataset(
'spatial_features', (len(test_imgids), num_fixed_boxes, 6), 'f')
test_counter = 0
unknown_ids = []
]
infile = 'data/test2015_36/test2015_resnet101_faster_rcnn_genome_36.tsv'
test_data_file = 'data/test36.hdf5'
test_indices_file = 'data/test36_imgid2idx.pkl'
test_ids_file = 'data/test_ids.pkl'
feature_length = 2048
num_fixed_boxes = 36
if __name__ == '__main__':
h_test = h5py.File(test_data_file, "w")
if os.path.exists(test_ids_file):
test_imgids = cPickle.load(open(test_ids_file))
else:
test_imgids = utils.load_imageid('data/test2015')
cPickle.dump(test_imgids, open(test_ids_file, 'wb'))
test_indices = {}
test_img_features = h_test.create_dataset(
'image_features', (len(test_imgids), num_fixed_boxes, feature_length),
'f')
test_img_bb = h_test.create_dataset('image_bb',
(len(test_imgids), num_fixed_boxes, 4),
'f')
test_spatial_img_features = h_test.create_dataset(
'spatial_features', (len(test_imgids), num_fixed_boxes, 6), 'f')
test_counter = 0
infile = 'data/%s_36/%s_resnet101_faster_rcnn_genome_36.tsv' % (target, target)
data_file = 'data/%s36.hdf5' % target
indices_file = 'data/%s36_imgid2idx.pkl' % target
ids_file = 'data/%s_ids.pkl' % target
feature_length = 2048
num_fixed_boxes = 36
if __name__ == '__main__':
h = h5py.File(data_file, "w")
if os.path.exists(ids_file):
imgids = cPickle.load(open(ids_file, 'rb'))
else:
imgids = utils.load_imageid('data/%s' % target)
cPickle.dump(imgids, open(ids_file, 'wb'))
indices = {}
img_bb = h.create_dataset(
'image_bb', (len(imgids), num_fixed_boxes, 4), 'f')
img_features = h.create_dataset(
'image_features', (len(imgids), num_fixed_boxes, feature_length), 'f')
spatial_img_features = h.create_dataset(
'spatial_features', (len(imgids), num_fixed_boxes, 6), 'f')
counter = 0
print("reading tsv...")
with open(infile, "r+") as tsv_in_file:
feature_length = 2048
num_fixed_boxes = 36
if __name__ == '__main__':
# h_train = h5py.File(train_data_file, "w")
# h_val = h5py.File(val_data_file, "w")
h_test = h5py.File(test_data_file, "w")
if os.path.exists(train_ids_file) and os.path.exists(val_ids_file) and os.path.exists(test_ids_file):
train_imgids = cPickle.load(open(train_ids_file))
val_imgids = cPickle.load(open(val_ids_file))
test_imgids = cPickle.load(open(test_ids_file))
else:
train_imgids = utils.load_imageid('data/images/train2014')
val_imgids = utils.load_imageid('data/images/val2014')
# test_imgids = []
test_imgids = utils.load_imageid('data/images/test2015')
cPickle.dump(train_imgids, open(train_ids_file, 'wb'))
cPickle.dump(val_imgids, open(val_ids_file, 'wb'))
cPickle.dump(test_imgids, open(test_ids_file, 'wb'))
train_indices = {}
val_indices = {}
test_indices = {}
print('> len(test_imgids): %d' % len(test_imgids))
'''
train_img_features = h_train.create_dataset(
if __name__ == '__main__':
h_train = h5py.File(train_data_file, "w")
h_val = h5py.File(val_data_file, "w")
if os.path.exists(train_ids_file) and os.path.exists(val_ids_file):
train_imgids = cPickle.load(open(train_ids_file))
val_imgids = cPickle.load(open(val_ids_file))
else:
base_imgs = '../DATA_imgs/'
folders = [
'scene_img_abstract_v002_train2015/',
'scene_img_abstract_v002_val2015/'
]
train_imgids = utils.load_imageid(base_imgs + folders[0]) #set of ids
val_imgids = utils.load_imageid(base_imgs + folders[1]) #set of ids
cPickle.dump(train_imgids, open(train_ids_file, 'wb'))
cPickle.dump(val_imgids, open(val_ids_file, 'wb'))
train_indices = {}
val_indices = {}
train_img_features = h_train.create_dataset(
'image_features', (len(train_imgids), num_fixed_boxes, feature_length),
'f')
train_img_bb = h_train.create_dataset(
'image_bb', (len(train_imgids), num_fixed_boxes, 4), 'f')
train_spatial_img_features = h_train.create_dataset(
'spatial_features', (len(train_imgids), num_fixed_boxes, 6), 'f')
def extract(split, infiles):
FIELDNAMES = [
'image_id', 'image_w', 'image_h', 'num_boxes', 'boxes', 'features'
]
data_file = {
'train': 'data/train.hdf5',
'val': 'data/val.hdf5',
'test': 'data/test2015.hdf5'
}
indices_file = {
'train': 'data/train_imgid2idx.pkl',
'val': 'data/val_imgid2idx.pkl',
'test': 'data/test2015_imgid2idx.pkl'
}
ids_file = {
'train': 'data/train_ids.pkl',
'val': 'data/val_ids.pkl',
'test': 'data/test2015_ids.pkl'
}
path_imgs = {
'train': '/media/data-aioz/VQA/Visual7W/train',
'val': '/media/data-aioz/VQA/Visual7W/val',
'test': '/media/data-aioz/VQA/Visual7W/test'
}
# known_num_boxes = {
# 'train': 2643089,
# 'val': 1281164,
# 'test': 2566887,
# }
known_num_boxes = {'train': None, 'val': None, 'test': None}
feature_length = 2048
min_fixed_boxes = 10
max_fixed_boxes = 100
if os.path.exists(ids_file[split]):
imgids = cPickle.load(open(ids_file[split], 'rb'))
else:
imgids = utils.load_imageid(path_imgs[split])
cPickle.dump(imgids, open(ids_file[split], 'wb'))
h = h5py.File(data_file[split], 'w')
if known_num_boxes[split] is None:
num_boxes = 0
for infile in infiles:
print("reading tsv...%s" % infile)
with open(infile, "r+") as tsv_in_file:
reader = csv.DictReader(tsv_in_file,
delimiter='\t',
fieldnames=FIELDNAMES)
for item in reader:
item['num_boxes'] = int(item['num_boxes'])
image_id = int(item['image_id'].split('_')[1])
if image_id in imgids:
num_boxes += item['num_boxes']
else:
num_boxes = known_num_boxes[split]
print('num_boxes=%d' % num_boxes)
img_features = h.create_dataset('image_features',
(num_boxes, 196, feature_length), 'f')
img_bb = h.create_dataset('image_bb', (num_boxes, 4), 'f')
spatial_img_features = h.create_dataset('spatial_features', (num_boxes, 6),
'f')
pos_boxes = h.create_dataset('pos_boxes', (len(imgids), 2), dtype='int32')
counter = 0
num_boxes = 0
indices = {}
for infile in infiles:
unknown_ids = []
print("reading tsv...%s" % infile)
with open(infile, "r+") as tsv_in_file:
reader = csv.DictReader(tsv_in_file,
delimiter='\t',
fieldnames=FIELDNAMES)
for item in reader:
item['num_boxes'] = int(item['num_boxes'])
item['boxes'] = bytes(item['boxes'], 'utf')
item['features'] = bytes(item['features'], 'utf')
image_id = int(item['image_id'].split('_')[1])
image_w = float(item['image_w'])
image_h = float(item['image_h'])
bboxes = np.frombuffer(base64.decodestring(item['boxes']),
dtype=np.float64).reshape(
(item['num_boxes'], -1))
box_width = bboxes[:, 2] - bboxes[:, 0]
box_height = bboxes[:, 3] - bboxes[:, 1]
scaled_width = box_width / image_w
scaled_height = box_height / image_h
scaled_x = bboxes[:, 0] / image_w
scaled_y = bboxes[:, 1] / image_h
box_width = box_width[..., np.newaxis]
box_height = box_height[..., np.newaxis]
scaled_width = scaled_width[..., np.newaxis]
scaled_height = scaled_height[..., np.newaxis]
scaled_x = scaled_x[..., np.newaxis]
scaled_y = scaled_y[..., np.newaxis]
spatial_features = np.concatenate(
(scaled_x, scaled_y, scaled_x + scaled_width,
scaled_y + scaled_height, scaled_width, scaled_height),
axis=1)
if image_id in imgids:
imgids.remove(image_id)
indices[image_id] = counter
pos_boxes[counter, :] = np.array(
[num_boxes, num_boxes + item['num_boxes']])
img_bb[num_boxes:num_boxes + item['num_boxes'], :] = bboxes
img_features[counter, :, :] = np.frombuffer(
base64.decodestring(item['features']),
dtype=np.float32).reshape((196, -1))
spatial_img_features[
num_boxes:num_boxes +
item['num_boxes'], :] = spatial_features
counter += 1
num_boxes += 196
else:
unknown_ids.append(image_id)
print('%d unknown_ids...' % len(unknown_ids))
print('%d image_ids left...' % len(imgids))
if len(imgids) != 0:
print('Warning: %s_image_ids is not empty' % split)
cPickle.dump(indices, open(indices_file[split], 'wb'))
h.close()
print("done!")
val_ids_file = 'data/val_ids.pkl'
feature_length = 2048
num_fixed_boxes = 36
train_path = os.path.join(config.data_path, 'train2014')
val_path = os.path.join(config.data_path, 'val2014')
if __name__ == '__main__':
h_train = h5py.File(train_data_file, "w")
h_val = h5py.File(val_data_file, "w")
if os.path.exists(train_ids_file) and os.path.exists(val_ids_file):
train_imgids = cPickle.load(open(train_ids_file))
val_imgids = cPickle.load(open(val_ids_file))
else:
train_imgids = utils.load_imageid(train_path)
val_imgids = utils.load_imageid(val_path)
cPickle.dump(train_imgids, open(train_ids_file, 'wb'))
cPickle.dump(val_imgids, open(val_ids_file, 'wb'))
train_indices = {}
val_indices = {}
train_img_features = h_train.create_dataset(
'image_features', (len(train_imgids), num_fixed_boxes, feature_length),
'f')
train_img_bb = h_train.create_dataset(
'image_bb', (len(train_imgids), num_fixed_boxes, 4), 'f')
train_spatial_img_features = h_train.create_dataset(
'spatial_features', (len(train_imgids), num_fixed_boxes, 6), 'f')
