Spaces:
Runtime error
Runtime error
File size: 11,581 Bytes
b334e29 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 |
import os.path as osp
import warnings
from collections import OrderedDict
import mmcv
import numpy as np
from mmcv.utils import print_log
from torch.utils.data import Dataset
from mmdet.core import eval_map, eval_recalls
from .builder import DATASETS
from .pipelines import Compose
@DATASETS.register_module()
class CustomDataset(Dataset):
"""Custom dataset for detection.
The annotation format is shown as follows. The `ann` field is optional for
testing.
.. code-block:: none
[
{
'filename': 'a.jpg',
'width': 1280,
'height': 720,
'ann': {
'bboxes': <np.ndarray> (n, 4) in (x1, y1, x2, y2) order.
'labels': <np.ndarray> (n, ),
'bboxes_ignore': <np.ndarray> (k, 4), (optional field)
'labels_ignore': <np.ndarray> (k, 4) (optional field)
}
},
...
]
Args:
ann_file (str): Annotation file path.
pipeline (list[dict]): Processing pipeline.
classes (str | Sequence[str], optional): Specify classes to load.
If is None, ``cls.CLASSES`` will be used. Default: None.
data_root (str, optional): Data root for ``ann_file``,
``img_prefix``, ``seg_prefix``, ``proposal_file`` if specified.
test_mode (bool, optional): If set True, annotation will not be loaded.
filter_empty_gt (bool, optional): If set true, images without bounding
boxes of the dataset's classes will be filtered out. This option
only works when `test_mode=False`, i.e., we never filter images
during tests.
"""
CLASSES = None
def __init__(self,
ann_file,
pipeline,
classes=None,
data_root=None,
img_prefix='',
seg_prefix=None,
proposal_file=None,
test_mode=False,
filter_empty_gt=True):
self.ann_file = ann_file
self.data_root = data_root
self.img_prefix = img_prefix
self.seg_prefix = seg_prefix
self.proposal_file = proposal_file
self.test_mode = test_mode
self.filter_empty_gt = filter_empty_gt
self.CLASSES = self.get_classes(classes)
# join paths if data_root is specified
if self.data_root is not None:
if not osp.isabs(self.ann_file):
self.ann_file = osp.join(self.data_root, self.ann_file)
if not (self.img_prefix is None or osp.isabs(self.img_prefix)):
self.img_prefix = osp.join(self.data_root, self.img_prefix)
if not (self.seg_prefix is None or osp.isabs(self.seg_prefix)):
self.seg_prefix = osp.join(self.data_root, self.seg_prefix)
if not (self.proposal_file is None
or osp.isabs(self.proposal_file)):
self.proposal_file = osp.join(self.data_root,
self.proposal_file)
# load annotations (and proposals)
self.data_infos = self.load_annotations(self.ann_file)
if self.proposal_file is not None:
self.proposals = self.load_proposals(self.proposal_file)
else:
self.proposals = None
# filter images too small and containing no annotations
if not test_mode:
valid_inds = self._filter_imgs()
self.data_infos = [self.data_infos[i] for i in valid_inds]
if self.proposals is not None:
self.proposals = [self.proposals[i] for i in valid_inds]
# set group flag for the sampler
self._set_group_flag()
# processing pipeline
self.pipeline = Compose(pipeline)
def __len__(self):
"""Total number of samples of data."""
return len(self.data_infos)
def load_annotations(self, ann_file):
"""Load annotation from annotation file."""
return mmcv.load(ann_file)
def load_proposals(self, proposal_file):
"""Load proposal from proposal file."""
return mmcv.load(proposal_file)
def get_ann_info(self, idx):
"""Get annotation by index.
Args:
idx (int): Index of data.
Returns:
dict: Annotation info of specified index.
"""
return self.data_infos[idx]['ann']
def get_cat_ids(self, idx):
"""Get category ids by index.
Args:
idx (int): Index of data.
Returns:
list[int]: All categories in the image of specified index.
"""
return self.data_infos[idx]['ann']['labels'].astype(np.int).tolist()
def pre_pipeline(self, results):
"""Prepare results dict for pipeline."""
results['img_prefix'] = self.img_prefix
results['seg_prefix'] = self.seg_prefix
results['proposal_file'] = self.proposal_file
results['bbox_fields'] = []
results['mask_fields'] = []
results['seg_fields'] = []
def _filter_imgs(self, min_size=32):
"""Filter images too small."""
if self.filter_empty_gt:
warnings.warn(
'CustomDataset does not support filtering empty gt images.')
valid_inds = []
for i, img_info in enumerate(self.data_infos):
if min(img_info['width'], img_info['height']) >= min_size:
valid_inds.append(i)
return valid_inds
def _set_group_flag(self):
"""Set flag according to image aspect ratio.
Images with aspect ratio greater than 1 will be set as group 1,
otherwise group 0.
"""
self.flag = np.zeros(len(self), dtype=np.uint8)
for i in range(len(self)):
img_info = self.data_infos[i]
if img_info['width'] / img_info['height'] > 1:
self.flag[i] = 1
def _rand_another(self, idx):
"""Get another random index from the same group as the given index."""
pool = np.where(self.flag == self.flag[idx])[0]
return np.random.choice(pool)
def __getitem__(self, idx):
"""Get training/test data after pipeline.
Args:
idx (int): Index of data.
Returns:
dict: Training/test data (with annotation if `test_mode` is set \
True).
"""
if self.test_mode:
return self.prepare_test_img(idx)
while True:
data = self.prepare_train_img(idx)
if data is None:
idx = self._rand_another(idx)
continue
return data
def prepare_train_img(self, idx):
"""Get training data and annotations after pipeline.
Args:
idx (int): Index of data.
Returns:
dict: Training data and annotation after pipeline with new keys \
introduced by pipeline.
"""
img_info = self.data_infos[idx]
ann_info = self.get_ann_info(idx)
results = dict(img_info=img_info, ann_info=ann_info)
if self.proposals is not None:
results['proposals'] = self.proposals[idx]
self.pre_pipeline(results)
return self.pipeline(results)
def prepare_test_img(self, idx):
"""Get testing data after pipeline.
Args:
idx (int): Index of data.
Returns:
dict: Testing data after pipeline with new keys introduced by \
pipeline.
"""
img_info = self.data_infos[idx]
results = dict(img_info=img_info)
if self.proposals is not None:
results['proposals'] = self.proposals[idx]
self.pre_pipeline(results)
return self.pipeline(results)
@classmethod
def get_classes(cls, classes=None):
"""Get class names of current dataset.
Args:
classes (Sequence[str] | str | None): If classes is None, use
default CLASSES defined by builtin dataset. If classes is a
string, take it as a file name. The file contains the name of
classes where each line contains one class name. If classes is
a tuple or list, override the CLASSES defined by the dataset.
Returns:
tuple[str] or list[str]: Names of categories of the dataset.
"""
if classes is None:
return cls.CLASSES
if isinstance(classes, str):
# take it as a file path
class_names = mmcv.list_from_file(classes)
elif isinstance(classes, (tuple, list)):
class_names = classes
else:
raise ValueError(f'Unsupported type {type(classes)} of classes.')
return class_names
def format_results(self, results, **kwargs):
"""Place holder to format result to dataset specific output."""
def evaluate(self,
results,
metric='mAP',
logger=None,
proposal_nums=(100, 300, 1000),
iou_thr=0.5,
scale_ranges=None):
"""Evaluate the dataset.
Args:
results (list): Testing results of the dataset.
metric (str | list[str]): Metrics to be evaluated.
logger (logging.Logger | None | str): Logger used for printing
related information during evaluation. Default: None.
proposal_nums (Sequence[int]): Proposal number used for evaluating
recalls, such as recall@100, recall@1000.
Default: (100, 300, 1000).
iou_thr (float | list[float]): IoU threshold. Default: 0.5.
scale_ranges (list[tuple] | None): Scale ranges for evaluating mAP.
Default: None.
"""
if not isinstance(metric, str):
assert len(metric) == 1
metric = metric[0]
allowed_metrics = ['mAP', 'recall']
if metric not in allowed_metrics:
raise KeyError(f'metric {metric} is not supported')
annotations = [self.get_ann_info(i) for i in range(len(self))]
eval_results = OrderedDict()
iou_thrs = [iou_thr] if isinstance(iou_thr, float) else iou_thr
if metric == 'mAP':
assert isinstance(iou_thrs, list)
mean_aps = []
for iou_thr in iou_thrs:
print_log(f'\n{"-" * 15}iou_thr: {iou_thr}{"-" * 15}')
mean_ap, _ = eval_map(
results,
annotations,
scale_ranges=scale_ranges,
iou_thr=iou_thr,
dataset=self.CLASSES,
logger=logger)
mean_aps.append(mean_ap)
eval_results[f'AP{int(iou_thr * 100):02d}'] = round(mean_ap, 3)
eval_results['mAP'] = sum(mean_aps) / len(mean_aps)
elif metric == 'recall':
gt_bboxes = [ann['bboxes'] for ann in annotations]
recalls = eval_recalls(
gt_bboxes, results, proposal_nums, iou_thr, logger=logger)
for i, num in enumerate(proposal_nums):
for j, iou in enumerate(iou_thrs):
eval_results[f'recall@{num}@{iou}'] = recalls[i, j]
if recalls.shape[1] > 1:
ar = recalls.mean(axis=1)
for i, num in enumerate(proposal_nums):
eval_results[f'AR@{num}'] = ar[i]
return eval_results
|