Source code for common.vision.datasets.aircrafts
"""
@author: Yifei Ji
@contact: jiyf990330@163.com
"""
import os
from typing import Optional
from .imagelist import ImageList
from ._util import download as download_data, check_exits
[docs]class Aircraft(ImageList):
"""`FVGC-Aircraft <https://www.robots.ox.ac.uk/~vgg/data/fgvc-aircraft/>`_ \
is a benchmark for the fine-grained visual categorization of aircraft. \
The dataset contains 10,200 images of aircraft, with 100 images for each \
of the 102 different aircraft variants.
Args:
root (str): Root directory of dataset
split (str, optional): The dataset split, supports ``train``, or ``test``.
sample_rate (int): The sampling rates to sample random ``training`` images for each category.
Choices include 100, 50, 30, 15. Default: 100.
download (bool, optional): If true, downloads the dataset from the internet and puts it \
in root directory. If dataset is already downloaded, it is not downloaded again.
transform (callable, optional): A function/transform that takes in an PIL image and returns a \
transformed version. E.g, :class:`torchvision.transforms.RandomCrop`.
target_transform (callable, optional): A function/transform that takes in the target and transforms it.
.. note:: In `root`, there will exist following files after downloading.
::
train/
test/
image_list/
train_100.txt
train_50.txt
train_30.txt
train_15.txt
test.txt
"""
download_list = [
("image_list", "image_list.zip", "https://cloud.tsinghua.edu.cn/f/04356d49d0054092b07e/?dl=1"),
("train", "train.tgz", "https://cloud.tsinghua.edu.cn/f/9fed22eba03046d69012/?dl=1"),
("test", "test.tgz", "https://cloud.tsinghua.edu.cn/f/8d5e4c1b031a4a608c68/?dl=1"),
]
image_list = {
"train": "image_list/train_100.txt",
"train100": "image_list/train_100.txt",
"train50": "image_list/train_50.txt",
"train30": "image_list/train_30.txt",
"train15": "image_list/train_15.txt",
"test": "image_list/test.txt",
"test100": "image_list/test.txt",
}
CLASSES = ['707-320', '727-200', '737-200', '737-300', '737-400', '737-500', '737-600', '737-700', '737-800', '737-900', '747-100',
'747-200', '747-300', '747-400', '757-200', '757-300', '767-200', '767-300', '767-400', '777-200', '777-300', 'A300B4',
'A310', 'A318', 'A319', 'A320', 'A321', 'A330-200', 'A330-300', 'A340-200', 'A340-300', 'A340-500', 'A340-600', 'A380',
'ATR-42', 'ATR-72', 'An-12', 'BAE 146-200', 'BAE 146-300', 'BAE-125', 'Beechcraft 1900', 'Boeing 717', 'C-130', 'C-47',
'CRJ-200', 'CRJ-700', 'CRJ-900', 'Cessna 172', 'Cessna 208', 'Cessna 525', 'Cessna 560', 'Challenger 600', 'DC-10',
'DC-3', 'DC-6', 'DC-8', 'DC-9-30', 'DH-82', 'DHC-1', 'DHC-6', 'DHC-8-100', 'DHC-8-300', 'DR-400', 'Dornier 328', 'E-170',
'E-190', 'E-195', 'EMB-120', 'ERJ 135', 'ERJ 145', 'Embraer Legacy 600', 'Eurofighter Typhoon', 'F-16A-B', 'F-A-18',
'Falcon 2000', 'Falcon 900', 'Fokker 100', 'Fokker 50', 'Fokker 70', 'Global Express', 'Gulfstream IV', 'Gulfstream V',
'Hawk T1', 'Il-76', 'L-1011', 'MD-11', 'MD-80', 'MD-87', 'MD-90', 'Metroliner', 'Model B200', 'PA-28', 'SR-20',
'Saab 2000', 'Saab 340', 'Spitfire', 'Tornado', 'Tu-134', 'Tu-154', 'Yak-42']
def __init__(self, root: str, split: str, sample_rate: Optional[int]=100, download: Optional[bool] = False, **kwargs):
if split == 'train':
list_name = 'train' + str(sample_rate)
assert list_name in self.image_list
data_list_file = os.path.join(root, self.image_list[list_name])
else:
data_list_file = os.path.join(root, self.image_list['test'])
if download:
list(map(lambda args: download_data(root, *args), self.download_list))
else:
list(map(lambda file_name, _: check_exits(root, file_name), self.download_list))
super(Aircraft, self).__init__(root, Aircraft.CLASSES, data_list_file=data_list_file, **kwargs)
