48 lines
1.6 KiB
Python
48 lines
1.6 KiB
Python
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
from __future__ import print_function
|
|
|
|
import numpy as np
|
|
import os
|
|
|
|
from .common_dataset import CommonDataset
|
|
|
|
|
|
class ImageNetDataset(CommonDataset):
|
|
def __init__(
|
|
self,
|
|
image_root,
|
|
cls_label_path,
|
|
transform_ops=None,
|
|
delimiter=None):
|
|
self.delimiter = delimiter if delimiter is not None else " "
|
|
super(ImageNetDataset, self).__init__(image_root, cls_label_path, transform_ops)
|
|
|
|
def _load_anno(self, seed=None):
|
|
assert os.path.exists(self._cls_path)
|
|
assert os.path.exists(self._img_root)
|
|
self.images = []
|
|
self.labels = []
|
|
|
|
with open(self._cls_path) as fd:
|
|
lines = fd.readlines()
|
|
if seed is not None:
|
|
np.random.RandomState(seed).shuffle(lines)
|
|
for l in lines:
|
|
l = l.strip().split(self.delimiter)
|
|
self.images.append(os.path.join(self._img_root, l[0]))
|
|
self.labels.append(np.int64(l[1]))
|
|
assert os.path.exists(self.images[-1])
|