-
Notifications
You must be signed in to change notification settings - Fork 544
/
rotated_coco_metric.py
390 lines (339 loc) · 15.1 KB
/
rotated_coco_metric.py
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
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
# Copyright (c) OpenMMLab. All rights reserved.
import datetime
import itertools
import os.path as osp
import tempfile
from collections import OrderedDict
from typing import Dict, Optional, Sequence
import cv2
import numpy as np
import pycocotools.mask as maskUtils
from mmcv.ops import box_iou_rotated
from mmdet.datasets.api_wrappers import COCO
from mmdet.evaluation import CocoMetric
from mmengine import MMLogger
from mmengine.fileio import dump, load
from pycocotools.cocoeval import COCOeval
from terminaltables import AsciiTable
from mmrotate.registry import METRICS
from mmrotate.structures.bbox import RotatedBoxes
def qbox2rbox_list(boxes: list) -> list:
"""Convert quadrilateral boxes to rotated boxes.
Args:
boxes (list): Quadrilateral box list with shape of (8).
Returns:
List: Rotated box list with shape of (5).
"""
pts = np.array(boxes, dtype=np.float32).reshape(4, 2)
(x, y), (w, h), angle = cv2.minAreaRect(pts)
return [x, y, w, h, angle / 180 * np.pi]
class RotatedCocoEval(COCOeval):
"""This is a wrapper to support Rotated Box Eval."""
def computeIoU(self, imgId, catId):
p = self.params
if p.useCats:
gt = self._gts[imgId, catId]
dt = self._dts[imgId, catId]
else:
gt = [_ for cId in p.catIds for _ in self._gts[imgId, cId]]
dt = [_ for cId in p.catIds for _ in self._dts[imgId, cId]]
if len(gt) == 0 and len(dt) == 0:
return []
inds = np.argsort([-d['score'] for d in dt], kind='mergesort')
dt = [dt[i] for i in inds]
if len(dt) > p.maxDets[-1]:
dt = dt[0:p.maxDets[-1]]
if p.iouType == 'segm':
# For segm, its same with original COCOeval
g = [g['segmentation'] for g in gt]
d = [d['segmentation'] for d in dt]
# compute iou between each dt and gt region
iscrowd = [int(o['iscrowd']) for o in gt]
ious = maskUtils.iou(d, g, iscrowd)
elif p.iouType == 'bbox':
# Modified for Rotated Box
g = [g['bbox'] for g in gt]
d = [d['bbox'] for d in dt]
# Convert List[List[float]] to Tensor for iou compute
g = RotatedBoxes(g).tensor
d = RotatedBoxes(d).tensor
ious = box_iou_rotated(d, g)
else:
raise Exception('unknown iouType for iou computation')
return ious
@METRICS.register_module()
class RotatedCocoMetric(CocoMetric):
"""Rotated COCO evaluation metric."""
default_prefix: Optional[str] = 'r_coco'
def results2json(self, results: Sequence[dict],
outfile_prefix: str) -> dict:
"""Dump the detection results to a COCO style json file.
There are 3 types of results: proposals, bbox predictions, mask
predictions, and they have different data types. This method will
automatically recognize the type, and dump them to json files.
Args:
results (Sequence[dict]): Testing results of the
dataset.
outfile_prefix (str): The filename prefix of the json files. If the
prefix is "somepath/xxx", the json files will be named
"somepath/xxx.bbox.json", "somepath/xxx.segm.json",
"somepath/xxx.proposal.json".
Returns:
dict: Possible keys are "bbox", "segm", "proposal", and
values are corresponding filenames.
"""
bbox_json_results = []
segm_json_results = [] if 'masks' in results[0] else None
for idx, result in enumerate(results):
image_id = result.get('img_id', idx)
labels = result['labels']
bboxes = result['bboxes']
scores = result['scores']
# bbox results
for i, label in enumerate(labels):
data = dict()
data['image_id'] = image_id
data['bbox'] = bboxes[i].tolist()
data['score'] = float(scores[i])
data['category_id'] = self.cat_ids[label]
bbox_json_results.append(data)
if segm_json_results is None:
continue
# segm results
masks = result['masks']
mask_scores = result.get('mask_scores', scores)
for i, label in enumerate(labels):
data = dict()
data['image_id'] = image_id
data['bbox'] = self.xyxy2xywh(bboxes[i])
data['score'] = float(mask_scores[i])
data['category_id'] = self.cat_ids[label]
if isinstance(masks[i]['counts'], bytes):
masks[i]['counts'] = masks[i]['counts'].decode()
data['segmentation'] = masks[i]
segm_json_results.append(data)
result_files = dict()
result_files['bbox'] = f'{outfile_prefix}.bbox.json'
result_files['proposal'] = f'{outfile_prefix}.bbox.json'
dump(bbox_json_results, result_files['bbox'])
if segm_json_results is not None:
result_files['segm'] = f'{outfile_prefix}.segm.json'
dump(segm_json_results, result_files['segm'])
return result_files
def gt_to_coco_json(self, gt_dicts: Sequence[dict],
outfile_prefix: str) -> str:
"""Convert ground truth to coco format json file.
Args:
gt_dicts (Sequence[dict]): Ground truth of the dataset.
outfile_prefix (str): The filename prefix of the json files. If the
prefix is "somepath/xxx", the json file will be named
"somepath/xxx.gt.json".
Returns:
str: The filename of the json file.
"""
categories = [
dict(id=id, name=name)
for id, name in enumerate(self.dataset_meta['CLASSES'])
]
image_infos = []
annotations = []
for idx, gt_dict in enumerate(gt_dicts):
img_id = gt_dict.get('img_id', idx)
image_info = dict(
id=img_id,
width=gt_dict['width'],
height=gt_dict['height'],
file_name='')
image_infos.append(image_info)
for ann in gt_dict['anns']:
label = ann['bbox_label']
bbox = ann['bbox']
coco_bbox = qbox2rbox_list(bbox)
annotation = dict(
id=len(annotations) +
1, # coco api requires id starts with 1
image_id=img_id,
bbox=coco_bbox,
iscrowd=ann.get('ignore_flag', 0),
category_id=int(label),
area=coco_bbox[2] * coco_bbox[3])
if ann.get('mask', None):
mask = ann['mask']
# area = mask_util.area(mask)
if isinstance(mask, dict) and isinstance(
mask['counts'], bytes):
mask['counts'] = mask['counts'].decode()
annotation['segmentation'] = mask
# annotation['area'] = float(area)
annotations.append(annotation)
info = dict(
date_created=str(datetime.datetime.now()),
description='Coco json file converted by mmdet CocoMetric.')
coco_json = dict(
info=info,
images=image_infos,
categories=categories,
licenses=None,
)
if len(annotations) > 0:
coco_json['annotations'] = annotations
converted_json_path = f'{outfile_prefix}.gt.json'
dump(coco_json, converted_json_path)
return converted_json_path
def compute_metrics(self, results: list) -> Dict[str, float]:
"""Compute the metrics from processed results.
Args:
results (list): The processed results of each batch.
Returns:
Dict[str, float]: The computed metrics. The keys are the names of
the metrics, and the values are corresponding results.
"""
logger: MMLogger = MMLogger.get_current_instance()
# split gt and prediction list
gts, preds = zip(*results)
tmp_dir = None
if self.outfile_prefix is None:
tmp_dir = tempfile.TemporaryDirectory()
outfile_prefix = osp.join(tmp_dir.name, 'results')
else:
outfile_prefix = self.outfile_prefix
if self._coco_api is None:
# use converted gt json file to initialize coco api
logger.info('Converting ground truth to coco format...')
coco_json_path = self.gt_to_coco_json(
gt_dicts=gts, outfile_prefix=outfile_prefix)
self._coco_api = COCO(coco_json_path)
# handle lazy init
if self.cat_ids is None:
self.cat_ids = self._coco_api.get_cat_ids(
cat_names=self.dataset_meta['CLASSES'])
if self.img_ids is None:
self.img_ids = self._coco_api.get_img_ids()
# convert predictions to coco format and dump to json file
result_files = self.results2json(preds, outfile_prefix)
eval_results = OrderedDict()
if self.format_only:
logger.info('results are saved in '
f'{osp.dirname(outfile_prefix)}')
return eval_results
for metric in self.metrics:
logger.info(f'Evaluating {metric}...')
# TODO: May refactor fast_eval_recall to an independent metric?
# fast eval recall
if metric == 'proposal_fast':
ar = self.fast_eval_recall(
preds, self.proposal_nums, self.iou_thrs, logger=logger)
log_msg = []
for i, num in enumerate(self.proposal_nums):
eval_results[f'AR@{num}'] = ar[i]
log_msg.append(f'\nAR@{num}\t{ar[i]:.4f}')
log_msg = ''.join(log_msg)
logger.info(log_msg)
continue
# evaluate proposal, bbox and segm
iou_type = 'bbox' if metric == 'proposal' else metric
if metric not in result_files:
raise KeyError(f'{metric} is not in results')
try:
predictions = load(result_files[metric])
if iou_type == 'segm':
# Refer to https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocotools/coco.py#L331 # noqa
# When evaluating mask AP, if the results contain bbox,
# cocoapi will use the box area instead of the mask area
# for calculating the instance area. Though the overall AP
# is not affected, this leads to different
# small/medium/large mask AP results.
for x in predictions:
x.pop('bbox')
coco_dt = self._coco_api.loadRes(predictions)
except IndexError:
logger.error(
'The testing results of the whole dataset is empty.')
break
coco_eval = RotatedCocoEval(self._coco_api, coco_dt, iou_type)
coco_eval.params.catIds = self.cat_ids
coco_eval.params.imgIds = self.img_ids
coco_eval.params.maxDets = list(self.proposal_nums)
coco_eval.params.iouThrs = self.iou_thrs
# mapping of cocoEval.stats
coco_metric_names = {
'mAP': 0,
'mAP_50': 1,
'mAP_75': 2,
'mAP_s': 3,
'mAP_m': 4,
'mAP_l': 5,
'AR@100': 6,
'AR@300': 7,
'AR@1000': 8,
'AR_s@1000': 9,
'AR_m@1000': 10,
'AR_l@1000': 11
}
metric_items = self.metric_items
if metric_items is not None:
for metric_item in metric_items:
if metric_item not in coco_metric_names:
raise KeyError(
f'metric item "{metric_item}" is not supported')
if metric == 'proposal':
coco_eval.params.useCats = 0
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
if metric_items is None:
metric_items = [
'AR@100', 'AR@300', 'AR@1000', 'AR_s@1000',
'AR_m@1000', 'AR_l@1000'
]
for item in metric_items:
val = float(
f'{coco_eval.stats[coco_metric_names[item]]:.3f}')
eval_results[item] = val
else:
coco_eval.evaluate()
coco_eval.accumulate()
coco_eval.summarize()
if self.classwise: # Compute per-category AP
# Compute per-category AP
# from https://github.com/facebookresearch/detectron2/
precisions = coco_eval.eval['precision']
# precision: (iou, recall, cls, area range, max dets)
assert len(self.cat_ids) == precisions.shape[2]
results_per_category = []
for idx, cat_id in enumerate(self.cat_ids):
# area range index 0: all area ranges
# max dets index -1: typically 100 per image
nm = self._coco_api.loadCats(cat_id)[0]
precision = precisions[:, :, idx, 0, -1]
precision = precision[precision > -1]
if precision.size:
ap = np.mean(precision)
else:
ap = float('nan')
results_per_category.append(
(f'{nm["name"]}', f'{round(ap, 3)}'))
eval_results[f'{nm["name"]}_precision'] = round(ap, 3)
num_columns = min(6, len(results_per_category) * 2)
results_flatten = list(
itertools.chain(*results_per_category))
headers = ['category', 'AP'] * (num_columns // 2)
results_2d = itertools.zip_longest(*[
results_flatten[i::num_columns]
for i in range(num_columns)
])
table_data = [headers]
table_data += [result for result in results_2d]
table = AsciiTable(table_data)
logger.info('\n' + table.table)
if metric_items is None:
metric_items = [
'mAP', 'mAP_50', 'mAP_75', 'mAP_s', 'mAP_m', 'mAP_l'
]
for metric_item in metric_items:
key = f'{metric}_{metric_item}'
val = coco_eval.stats[coco_metric_names[metric_item]]
eval_results[key] = float(f'{round(val, 3)}')
if tmp_dir is not None:
tmp_dir.cleanup()
return eval_results