def _download_and_prepare(self, dataset_dir, scratch_dir, _):
# Download dataset
tmp_zip_path = os.path.join(scratch_dir, "dataset.zip")
etaw.download_google_drive_file(self._GDRIVE_ID, path=tmp_zip_path)
# Extract zip
logger.info("Extracting dataset")
etau.extract_zip(tmp_zip_path, delete_zip=True)
_move_dir(os.path.join(scratch_dir, self._DIR_IN_ZIP), dataset_dir)
# Get metadata
logger.info("Parsing dataset metadata")
classes = foud.FiftyOneDatasetImporter.get_classes(dataset_dir)
num_samples = foud.FiftyOneDatasetImporter.get_num_samples(dataset_dir)
logger.info("Found %d samples", num_samples)
dataset_type = fot.FiftyOneDataset()
return dataset_type, num_samples, classes
def download_coco_dataset_split(dataset_dir, split, year="2017", cleanup=True):
"""Downloads and extracts the given split of the COCO dataset to the
specified directory.
Any existing files are not re-downloaded.
Args:
dataset_dir: the directory to download the dataset
split: the split to download. Supported values are
``("train", "validation", "test")``
year ("2017"): the dataset year to download. Supported values are
``("2014", "2017")``
cleanup (True): whether to cleanup the zip files after extraction
Returns:
a tuple of
- images_dir: the path to the directory containing the extracted
images
- anno_path: the path to the annotations JSON file
"""
if year not in _IMAGE_DOWNLOAD_LINKS:
raise ValueError(
"Unsupported year '%s'; supported values are %s"
% (year, tuple(_IMAGE_DOWNLOAD_LINKS.keys()))
)
if split not in _IMAGE_DOWNLOAD_LINKS[year]:
raise ValueError(
"Unsupported split '%s'; supported values are %s"
% (year, tuple(_IMAGE_DOWNLOAD_LINKS[year].keys()))
)
#
# Download images
#
images_src_path = _IMAGE_DOWNLOAD_LINKS[year][split]
images_zip_path = os.path.join(
dataset_dir, os.path.basename(images_src_path)
)
images_dir = os.path.join(
dataset_dir, os.path.splitext(os.path.basename(images_src_path))[0]
)
if not os.path.isdir(images_dir):
logger.info("Downloading images zip to '%s'", images_zip_path)
etaw.download_file(images_src_path, path=images_zip_path)
logger.info("Extracting images to '%s'", images_dir)
etau.extract_zip(images_zip_path, delete_zip=cleanup)
else:
logger.info("Image folder '%s' already exists", images_dir)
#
# Download annotations
#
anno_path = os.path.join(dataset_dir, _ANNOTATION_PATHS[year][split])
if split == "test":
# Test split has no annotations, so we must populate the labels file
# manually
images = _make_images_list(images_dir)
labels = {
"info": {},
"licenses": [],
"categories": [],
"images": images,
"annotations": [],
}
etas.write_json(labels, anno_path)
else:
anno_src_path = _ANNOTATION_DOWNLOAD_LINKS[year]
anno_zip_path = os.path.join(
dataset_dir, os.path.basename(anno_src_path)
)
if not os.path.isfile(anno_path):
logger.info("Downloading annotations zip to '%s'", anno_zip_path)
etaw.download_file(anno_src_path, path=anno_zip_path)
logger.info("Extracting annotations to '%s'", anno_path)
etau.extract_zip(anno_zip_path, delete_zip=cleanup)
else:
logger.info("Annotations file '%s' already exists", anno_path)
return images_dir, anno_path
'''
# pragma pylint: disable=redefined-builtin
# pragma pylint: disable=unused-wildcard-import
# pragma pylint: disable=wildcard-import
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
from builtins import *
# pragma pylint: enable=redefined-builtin
# pragma pylint: enable=unused-wildcard-import
# pragma pylint: enable=wildcard-import
import logging
import os
import eta.core.web as etaw
import eta.core.utils as etau
logger = logging.getLogger(__name__)
FILE_ID = "0B7phNvpRqNdpNEVpVjE2VXQxOWc"
logger.info("Downloading example data from Google Drive")
path = os.path.join(os.path.dirname(__file__), "data.zip")
etaw.download_google_drive_file(FILE_ID, path=path)
etau.extract_zip(path, delete_zip=True)