-
Notifications
You must be signed in to change notification settings - Fork 2.6k
/
Copy pathmetrics.py
396 lines (349 loc) · 15.7 KB
/
metrics.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
391
392
393
394
395
396
# Copyright (c) OpenMMLab. All rights reserved.
from collections import OrderedDict
import mmcv
import numpy as np
import torch
def f_score(precision, recall, beta=1):
"""calculate the f-score value.
Args:
precision (float | torch.Tensor): The precision value.
recall (float | torch.Tensor): The recall value.
beta (int): Determines the weight of recall in the combined score.
Default: False.
Returns:
[torch.tensor]: The f-score value.
"""
score = (1 + beta**2) * (precision * recall) / (
(beta**2 * precision) + recall)
return score
def intersect_and_union(pred_label,
label,
num_classes,
ignore_index,
label_map=dict(),
reduce_zero_label=False):
"""Calculate intersection and Union.
Args:
pred_label (ndarray | str): Prediction segmentation map
or predict result filename.
label (ndarray | str): Ground truth segmentation map
or label filename.
num_classes (int): Number of categories.
ignore_index (int): Index that will be ignored in evaluation.
label_map (dict): Mapping old labels to new labels. The parameter will
work only when label is str. Default: dict().
reduce_zero_label (bool): Whether ignore zero label. The parameter will
work only when label is str. Default: False.
Returns:
torch.Tensor: The intersection of prediction and ground truth
histogram on all classes.
torch.Tensor: The union of prediction and ground truth histogram on
all classes.
torch.Tensor: The prediction histogram on all classes.
torch.Tensor: The ground truth histogram on all classes.
"""
if isinstance(pred_label, str):
pred_label = torch.from_numpy(np.load(pred_label))
else:
pred_label = torch.from_numpy((pred_label))
if isinstance(label, str):
label = torch.from_numpy(
mmcv.imread(label, flag='unchanged', backend='pillow'))
else:
label = torch.from_numpy(label)
if reduce_zero_label:
label[label == 0] = 255
label = label - 1
label[label == 254] = 255
if label_map is not None:
label_copy = label.clone()
for old_id, new_id in label_map.items():
label[label_copy == old_id] = new_id
mask = (label != ignore_index)
pred_label = pred_label[mask]
label = label[mask]
intersect = pred_label[pred_label == label]
area_intersect = torch.histc(
intersect.float(), bins=(num_classes), min=0, max=num_classes - 1)
area_pred_label = torch.histc(
pred_label.float(), bins=(num_classes), min=0, max=num_classes - 1)
area_label = torch.histc(
label.float(), bins=(num_classes), min=0, max=num_classes - 1)
area_union = area_pred_label + area_label - area_intersect
return area_intersect, area_union, area_pred_label, area_label
def total_intersect_and_union(results,
gt_seg_maps,
num_classes,
ignore_index,
label_map=dict(),
reduce_zero_label=False):
"""Calculate Total Intersection and Union.
Args:
results (list[ndarray] | list[str]): List of prediction segmentation
maps or list of prediction result filenames.
gt_seg_maps (list[ndarray] | list[str] | Iterables): list of ground
truth segmentation maps or list of label filenames.
num_classes (int): Number of categories.
ignore_index (int): Index that will be ignored in evaluation.
label_map (dict): Mapping old labels to new labels. Default: dict().
reduce_zero_label (bool): Whether ignore zero label. Default: False.
Returns:
ndarray: The intersection of prediction and ground truth histogram
on all classes.
ndarray: The union of prediction and ground truth histogram on all
classes.
ndarray: The prediction histogram on all classes.
ndarray: The ground truth histogram on all classes.
"""
total_area_intersect = torch.zeros((num_classes, ), dtype=torch.float64)
total_area_union = torch.zeros((num_classes, ), dtype=torch.float64)
total_area_pred_label = torch.zeros((num_classes, ), dtype=torch.float64)
total_area_label = torch.zeros((num_classes, ), dtype=torch.float64)
for result, gt_seg_map in zip(results, gt_seg_maps):
area_intersect, area_union, area_pred_label, area_label = \
intersect_and_union(
result, gt_seg_map, num_classes, ignore_index,
label_map, reduce_zero_label)
total_area_intersect += area_intersect
total_area_union += area_union
total_area_pred_label += area_pred_label
total_area_label += area_label
return total_area_intersect, total_area_union, total_area_pred_label, \
total_area_label
def mean_iou(results,
gt_seg_maps,
num_classes,
ignore_index,
nan_to_num=None,
label_map=dict(),
reduce_zero_label=False):
"""Calculate Mean Intersection and Union (mIoU)
Args:
results (list[ndarray] | list[str]): List of prediction segmentation
maps or list of prediction result filenames.
gt_seg_maps (list[ndarray] | list[str]): list of ground truth
segmentation maps or list of label filenames.
num_classes (int): Number of categories.
ignore_index (int): Index that will be ignored in evaluation.
nan_to_num (int, optional): If specified, NaN values will be replaced
by the numbers defined by the user. Default: None.
label_map (dict): Mapping old labels to new labels. Default: dict().
reduce_zero_label (bool): Whether ignore zero label. Default: False.
Returns:
dict[str, float | ndarray]:
<aAcc> float: Overall accuracy on all images.
<Acc> ndarray: Per category accuracy, shape (num_classes, ).
<IoU> ndarray: Per category IoU, shape (num_classes, ).
"""
iou_result = eval_metrics(
results=results,
gt_seg_maps=gt_seg_maps,
num_classes=num_classes,
ignore_index=ignore_index,
metrics=['mIoU'],
nan_to_num=nan_to_num,
label_map=label_map,
reduce_zero_label=reduce_zero_label)
return iou_result
def mean_dice(results,
gt_seg_maps,
num_classes,
ignore_index,
nan_to_num=None,
label_map=dict(),
reduce_zero_label=False):
"""Calculate Mean Dice (mDice)
Args:
results (list[ndarray] | list[str]): List of prediction segmentation
maps or list of prediction result filenames.
gt_seg_maps (list[ndarray] | list[str]): list of ground truth
segmentation maps or list of label filenames.
num_classes (int): Number of categories.
ignore_index (int): Index that will be ignored in evaluation.
nan_to_num (int, optional): If specified, NaN values will be replaced
by the numbers defined by the user. Default: None.
label_map (dict): Mapping old labels to new labels. Default: dict().
reduce_zero_label (bool): Whether ignore zero label. Default: False.
Returns:
dict[str, float | ndarray]: Default metrics.
<aAcc> float: Overall accuracy on all images.
<Acc> ndarray: Per category accuracy, shape (num_classes, ).
<Dice> ndarray: Per category dice, shape (num_classes, ).
"""
dice_result = eval_metrics(
results=results,
gt_seg_maps=gt_seg_maps,
num_classes=num_classes,
ignore_index=ignore_index,
metrics=['mDice'],
nan_to_num=nan_to_num,
label_map=label_map,
reduce_zero_label=reduce_zero_label)
return dice_result
def mean_fscore(results,
gt_seg_maps,
num_classes,
ignore_index,
nan_to_num=None,
label_map=dict(),
reduce_zero_label=False,
beta=1):
"""Calculate Mean F-Score (mFscore)
Args:
results (list[ndarray] | list[str]): List of prediction segmentation
maps or list of prediction result filenames.
gt_seg_maps (list[ndarray] | list[str]): list of ground truth
segmentation maps or list of label filenames.
num_classes (int): Number of categories.
ignore_index (int): Index that will be ignored in evaluation.
nan_to_num (int, optional): If specified, NaN values will be replaced
by the numbers defined by the user. Default: None.
label_map (dict): Mapping old labels to new labels. Default: dict().
reduce_zero_label (bool): Whether ignore zero label. Default: False.
beta (int): Determines the weight of recall in the combined score.
Default: False.
Returns:
dict[str, float | ndarray]: Default metrics.
<aAcc> float: Overall accuracy on all images.
<Fscore> ndarray: Per category recall, shape (num_classes, ).
<Precision> ndarray: Per category precision, shape (num_classes, ).
<Recall> ndarray: Per category f-score, shape (num_classes, ).
"""
fscore_result = eval_metrics(
results=results,
gt_seg_maps=gt_seg_maps,
num_classes=num_classes,
ignore_index=ignore_index,
metrics=['mFscore'],
nan_to_num=nan_to_num,
label_map=label_map,
reduce_zero_label=reduce_zero_label,
beta=beta)
return fscore_result
def eval_metrics(results,
gt_seg_maps,
num_classes,
ignore_index,
metrics=['mIoU'],
nan_to_num=None,
label_map=dict(),
reduce_zero_label=False,
beta=1):
"""Calculate evaluation metrics
Args:
results (list[ndarray] | list[str]): List of prediction segmentation
maps or list of prediction result filenames.
gt_seg_maps (list[ndarray] | list[str] | Iterables): list of ground
truth segmentation maps or list of label filenames.
num_classes (int): Number of categories.
ignore_index (int): Index that will be ignored in evaluation.
metrics (list[str] | str): Metrics to be evaluated, 'mIoU' and 'mDice'.
nan_to_num (int, optional): If specified, NaN values will be replaced
by the numbers defined by the user. Default: None.
label_map (dict): Mapping old labels to new labels. Default: dict().
reduce_zero_label (bool): Whether ignore zero label. Default: False.
Returns:
float: Overall accuracy on all images.
ndarray: Per category accuracy, shape (num_classes, ).
ndarray: Per category evaluation metrics, shape (num_classes, ).
"""
total_area_intersect, total_area_union, total_area_pred_label, \
total_area_label = total_intersect_and_union(
results, gt_seg_maps, num_classes, ignore_index, label_map,
reduce_zero_label)
ret_metrics = total_area_to_metrics(total_area_intersect, total_area_union,
total_area_pred_label,
total_area_label, metrics, nan_to_num,
beta)
return ret_metrics
def pre_eval_to_metrics(pre_eval_results,
metrics=['mIoU'],
nan_to_num=None,
beta=1):
"""Convert pre-eval results to metrics.
Args:
pre_eval_results (list[tuple[torch.Tensor]]): per image eval results
for computing evaluation metric
metrics (list[str] | str): Metrics to be evaluated, 'mIoU' and 'mDice'.
nan_to_num (int, optional): If specified, NaN values will be replaced
by the numbers defined by the user. Default: None.
Returns:
float: Overall accuracy on all images.
ndarray: Per category accuracy, shape (num_classes, ).
ndarray: Per category evaluation metrics, shape (num_classes, ).
"""
# convert list of tuples to tuple of lists, e.g.
# [(A_1, B_1, C_1, D_1), ..., (A_n, B_n, C_n, D_n)] to
# ([A_1, ..., A_n], ..., [D_1, ..., D_n])
pre_eval_results = tuple(zip(*pre_eval_results))
assert len(pre_eval_results) == 4
total_area_intersect = sum(pre_eval_results[0])
total_area_union = sum(pre_eval_results[1])
total_area_pred_label = sum(pre_eval_results[2])
total_area_label = sum(pre_eval_results[3])
ret_metrics = total_area_to_metrics(total_area_intersect, total_area_union,
total_area_pred_label,
total_area_label, metrics, nan_to_num,
beta)
return ret_metrics
def total_area_to_metrics(total_area_intersect,
total_area_union,
total_area_pred_label,
total_area_label,
metrics=['mIoU'],
nan_to_num=None,
beta=1):
"""Calculate evaluation metrics
Args:
total_area_intersect (ndarray): The intersection of prediction and
ground truth histogram on all classes.
total_area_union (ndarray): The union of prediction and ground truth
histogram on all classes.
total_area_pred_label (ndarray): The prediction histogram on all
classes.
total_area_label (ndarray): The ground truth histogram on all classes.
metrics (list[str] | str): Metrics to be evaluated, 'mIoU' and 'mDice'.
nan_to_num (int, optional): If specified, NaN values will be replaced
by the numbers defined by the user. Default: None.
Returns:
float: Overall accuracy on all images.
ndarray: Per category accuracy, shape (num_classes, ).
ndarray: Per category evaluation metrics, shape (num_classes, ).
"""
if isinstance(metrics, str):
metrics = [metrics]
allowed_metrics = ['mIoU', 'mDice', 'mFscore']
if not set(metrics).issubset(set(allowed_metrics)):
raise KeyError('metrics {} is not supported'.format(metrics))
all_acc = total_area_intersect.sum() / total_area_label.sum()
ret_metrics = OrderedDict({'aAcc': all_acc})
for metric in metrics:
if metric == 'mIoU':
iou = total_area_intersect / total_area_union
acc = total_area_intersect / total_area_label
ret_metrics['IoU'] = iou
ret_metrics['Acc'] = acc
elif metric == 'mDice':
dice = 2 * total_area_intersect / (
total_area_pred_label + total_area_label)
acc = total_area_intersect / total_area_label
ret_metrics['Dice'] = dice
ret_metrics['Acc'] = acc
elif metric == 'mFscore':
precision = total_area_intersect / total_area_pred_label
recall = total_area_intersect / total_area_label
f_value = torch.tensor(
[f_score(x[0], x[1], beta) for x in zip(precision, recall)])
ret_metrics['Fscore'] = f_value
ret_metrics['Precision'] = precision
ret_metrics['Recall'] = recall
ret_metrics = {
metric: value.numpy()
for metric, value in ret_metrics.items()
}
if nan_to_num is not None:
ret_metrics = OrderedDict({
metric: np.nan_to_num(metric_value, nan=nan_to_num)
for metric, metric_value in ret_metrics.items()
})
return ret_metrics