def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'dataset_name',
help='A short string representing the dataset to be used as a partition key in MegaDB')
parser.add_argument(
'--image_db',
help='Path to the json containing the image DB in CCT format')
parser.add_argument(
'--bbox_db',
help='Path to the json containing the bbox DB in CCT format')
parser.add_argument(
'--docs',
help='Embedded CCT format json to use instead of image_db or bbox_db')
parser.add_argument(
'--partial_mega_db',
required=True,
help='Path to store the resulting json')
args = parser.parse_args()
assert len(args.dataset_name) > 0, 'dataset_name cannot be an empty string'
if args.image_db:
assert os.path.exists(args.image_db), 'image_db file path provided does not point to a file'
if args.bbox_db:
assert os.path.exists(args.bbox_db), 'bbox_db file path provided does not point to a file'
docs = make_cct_embedded(args.image_db, args.bbox_db)
sequences = process_sequences(docs, args.dataset_name)
sequences_schema_check.sequences_schema_check(sequences)
write_json(args.partial_mega_db, sequences)
def megadb_to_cct(dataset_name, mega_db, output_path, bbox_only):
mega_db = [i for i in mega_db if i['dataset'] == dataset_name]
assert len(mega_db) > 0, 'There are no entries from the dataset {}'.format(dataset_name)
for i in mega_db:
del i['dataset'] # all remaining fields will be added to the CCT database
print('Number of entries belonging to dataset {}: {}'.format(dataset_name, len(mega_db)))
cct_images, cct_annotations = break_into_images_annotations(mega_db, bbox_only)
# consolidate categories
category_names = set()
for anno in cct_annotations:
category_names.add(anno['category_name'])
cat_name_to_id = {
'empty': 0 # always set empty to 0 even for dataset without 'empty' labeled images
}
if bbox_only:
cat_name_to_id['animal'] = 1
cat_name_to_id['person'] = 2
cat_name_to_id['group'] = 3
cat_name_to_id['vehicle'] = 4
for cat in category_names:
if cat not in cat_name_to_id:
cat_name_to_id[cat] = len(cat_name_to_id)
for anno in cct_annotations:
anno['category_id'] = cat_name_to_id[anno['category_name']]
del anno['category_name']
cct_categories = []
for name, num_id in cat_name_to_id.items():
cct_categories.append({
'id': num_id,
'name': name
})
print('Final CCT DB has {} image entries, and {} annotation entries.'.format(len(cct_images), len(cct_annotations)))
cct_db = {
'info': {
'version': str(datetime.now()),
'date_created': str(datetime.today().date()),
'description': '' # to be filled by main()
},
'images': cct_images,
'categories': cct_categories,
'annotations': cct_annotations
}
cct_db = CameraTrapJsonUtils.order_db_keys(cct_db)
cct_db['info']['description'] = 'COCO Camera Traps database converted from sequences in dataset {}'.format(
dataset_name)
print('Writing to output file...')
write_json(output_path, cct_db)
print('Done!')
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
'dataset_name',
help=
'The name of the dataset; only entries from this dataset will be used')
parser.add_argument('mega_db_seqs',
help='A json containing a list of sequence objects')
parser.add_argument(
'out_file',
help='Path to store the resulting json to input to megadb_to_cct.py')
parser.add_argument(
'--ncores',
type=int,
default=None,
help=
'Number of cores to use when downloading images to read their dimensions'
)
args = parser.parse_args()
assert len(args.dataset_name) > 0, 'dataset_name cannot be an empty string'
assert os.path.exists(
args.mega_db_seqs), 'File at mega_db path does not exist'
assert args.out_file.endswith(
'.json'), 'out_cct_db path needs to end in .json'
assert args.out_file != args.mega_db_seqs
assert 'COSMOS_ENDPOINT' in os.environ and 'COSMOS_KEY' in os.environ
print('Loading entries...')
with open(args.mega_db_seqs) as f:
mega_db_entries = json.load(f)
print('Number of entries in the mega_db: {}'.format(len(mega_db_entries)))
megadb_utils = MegadbUtils()
datasets_table = megadb_utils.get_datasets_table()
start_time = time.time()
updated_seqs = get_image_dims(mega_db_entries, args.dataset_name,
datasets_table, args.ncores)
write_json(args.out_file, updated_seqs)
elapsed = time.time() - start_time
print('Time elapsed: {}'.format(humanfriendly.format_timespan(elapsed)))