-
Notifications
You must be signed in to change notification settings - Fork 387
/
stat_scores.py
521 lines (450 loc) · 23.8 KB
/
stat_scores.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
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
# Copyright The Lightning team.
#
# 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 typing import Any, Callable, Optional, Tuple, Union
import torch
from torch import Tensor
from typing_extensions import Literal
from torchmetrics.classification.base import _ClassificationTaskWrapper
from torchmetrics.functional.classification.stat_scores import (
_binary_stat_scores_arg_validation,
_binary_stat_scores_compute,
_binary_stat_scores_format,
_binary_stat_scores_tensor_validation,
_binary_stat_scores_update,
_multiclass_stat_scores_arg_validation,
_multiclass_stat_scores_compute,
_multiclass_stat_scores_format,
_multiclass_stat_scores_tensor_validation,
_multiclass_stat_scores_update,
_multilabel_stat_scores_arg_validation,
_multilabel_stat_scores_compute,
_multilabel_stat_scores_format,
_multilabel_stat_scores_tensor_validation,
_multilabel_stat_scores_update,
)
from torchmetrics.metric import Metric
from torchmetrics.utilities.data import dim_zero_cat
from torchmetrics.utilities.enums import ClassificationTask
class _AbstractStatScores(Metric):
# define common functions
def _create_state(
self,
size: int,
multidim_average: Literal["global", "samplewise"] = "global",
) -> None:
"""Initialize the states for the different statistics."""
default: Union[Callable[[], list], Callable[[], Tensor]]
if multidim_average == "samplewise":
default = list
dist_reduce_fx = "cat"
else:
default = lambda: torch.zeros(size, dtype=torch.long)
dist_reduce_fx = "sum"
self.add_state("tp", default(), dist_reduce_fx=dist_reduce_fx)
self.add_state("fp", default(), dist_reduce_fx=dist_reduce_fx)
self.add_state("tn", default(), dist_reduce_fx=dist_reduce_fx)
self.add_state("fn", default(), dist_reduce_fx=dist_reduce_fx)
def _update_state(self, tp: Tensor, fp: Tensor, tn: Tensor, fn: Tensor) -> None:
"""Update states depending on multidim_average argument."""
if self.multidim_average == "samplewise":
self.tp.append(tp)
self.fp.append(fp)
self.tn.append(tn)
self.fn.append(fn)
else:
self.tp += tp
self.fp += fp
self.tn += tn
self.fn += fn
def _final_state(self) -> Tuple[Tensor, Tensor, Tensor, Tensor]:
"""Aggregate states that are lists and return final states."""
tp = dim_zero_cat(self.tp)
fp = dim_zero_cat(self.fp)
tn = dim_zero_cat(self.tn)
fn = dim_zero_cat(self.fn)
return tp, fp, tn, fn
class BinaryStatScores(_AbstractStatScores):
r"""Compute true positives, false positives, true negatives, false negatives and the support for binary tasks.
Related to `Type I and Type II errors`_.
As input to ``forward`` and ``update`` the metric accepts the following input:
- ``preds`` (:class:`~torch.Tensor`): An int or float tensor of shape ``(N, ...)``. If preds is a floating
point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid
per element. Addtionally, we convert to int tensor with thresholding using the value in ``threshold``.
- ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``
As output to ``forward`` and ``compute`` the metric returns the following output:
- ``bss`` (:class:`~torch.Tensor`): A tensor of shape ``(..., 5)``, where the last dimension corresponds
to ``[tp, fp, tn, fn, sup]`` (``sup`` stands for support and equals ``tp + fn``). The shape
depends on the ``multidim_average`` parameter:
- If ``multidim_average`` is set to ``global``, the shape will be ``(5,)``
- If ``multidim_average`` is set to ``samplewise``, the shape will be ``(N, 5)``
Args:
threshold: Threshold for transforming probability to binary {0,1} predictions
multidim_average:
Defines how additionally dimensions ``...`` should be handled. Should be one of the following:
- ``global``: Additional dimensions are flatted along the batch dimension
- ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
The statistics in this case are calculated over the additional dimensions.
ignore_index:
Specifies a target value that is ignored and does not contribute to the metric calculation
validate_args: bool indicating if input arguments and tensors should be validated for correctness.
Set to ``False`` for faster computations.
kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.classification import BinaryStatScores
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0, 0, 1, 1, 0, 1])
>>> metric = BinaryStatScores()
>>> metric(preds, target)
tensor([2, 1, 2, 1, 3])
Example (preds is float tensor):
>>> from torchmetrics.classification import BinaryStatScores
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92])
>>> metric = BinaryStatScores()
>>> metric(preds, target)
tensor([2, 1, 2, 1, 3])
Example (multidim tensors):
>>> from torchmetrics.classification import BinaryStatScores
>>> target = tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
>>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
... [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
>>> metric = BinaryStatScores(multidim_average='samplewise')
>>> metric(preds, target)
tensor([[2, 3, 0, 1, 3],
[0, 2, 1, 3, 3]])
"""
is_differentiable: bool = False
higher_is_better: Optional[bool] = None
full_state_update: bool = False
def __init__(
self,
threshold: float = 0.5,
multidim_average: Literal["global", "samplewise"] = "global",
ignore_index: Optional[int] = None,
validate_args: bool = True,
**kwargs: Any,
) -> None:
super(_AbstractStatScores, self).__init__(**kwargs)
if validate_args:
_binary_stat_scores_arg_validation(threshold, multidim_average, ignore_index)
self.threshold = threshold
self.multidim_average = multidim_average
self.ignore_index = ignore_index
self.validate_args = validate_args
self._create_state(size=1, multidim_average=multidim_average)
def update(self, preds: Tensor, target: Tensor) -> None:
"""Update state with predictions and targets."""
if self.validate_args:
_binary_stat_scores_tensor_validation(preds, target, self.multidim_average, self.ignore_index)
preds, target = _binary_stat_scores_format(preds, target, self.threshold, self.ignore_index)
tp, fp, tn, fn = _binary_stat_scores_update(preds, target, self.multidim_average)
self._update_state(tp, fp, tn, fn)
def compute(self) -> Tensor:
"""Compute the final statistics."""
tp, fp, tn, fn = self._final_state()
return _binary_stat_scores_compute(tp, fp, tn, fn, self.multidim_average)
class MulticlassStatScores(_AbstractStatScores):
r"""Computes true positives, false positives, true negatives, false negatives and the support for multiclass tasks.
Related to `Type I and Type II errors`_.
As input to ``forward`` and ``update`` the metric accepts the following input:
- ``preds`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)`` or float tensor of shape ``(N, C, ..)``.
If preds is a floating point we apply ``torch.argmax`` along the ``C`` dimension to automatically convert
probabilities/logits into an int tensor.
- ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, ...)``
As output to ``forward`` and ``compute`` the metric returns the following output:
- ``mcss`` (:class:`~torch.Tensor`): A tensor of shape ``(..., 5)``, where the last dimension corresponds
to ``[tp, fp, tn, fn, sup]`` (``sup`` stands for support and equals ``tp + fn``). The shape
depends on ``average`` and ``multidim_average`` parameters:
- If ``multidim_average`` is set to ``global``
- If ``average='micro'/'macro'/'weighted'``, the shape will be ``(5,)``
- If ``average=None/'none'``, the shape will be ``(C, 5)``
- If ``multidim_average`` is set to ``samplewise``
- If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N, 5)``
- If ``average=None/'none'``, the shape will be ``(N, C, 5)``
Args:
num_classes: Integer specifing the number of classes
average:
Defines the reduction that is applied over labels. Should be one of the following:
- ``micro``: Sum statistics over all labels
- ``macro``: Calculate statistics for each label and average them
- ``weighted``: calculates statistics for each label and computes weighted average using their support
- ``"none"`` or ``None``: calculates statistic for each label and applies no reduction
top_k:
Number of highest probability or logit score predictions considered to find the correct label.
Only works when ``preds`` contain probabilities/logits.
multidim_average:
Defines how additionally dimensions ``...`` should be handled. Should be one of the following:
- ``global``: Additional dimensions are flatted along the batch dimension
- ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
The statistics in this case are calculated over the additional dimensions.
ignore_index:
Specifies a target value that is ignored and does not contribute to the metric calculation
validate_args: bool indicating if input arguments and tensors should be validated for correctness.
Set to ``False`` for faster computations.
kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.classification import MulticlassStatScores
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([2, 1, 0, 1])
>>> metric = MulticlassStatScores(num_classes=3, average='micro')
>>> metric(preds, target)
tensor([3, 1, 7, 1, 4])
>>> mcss = MulticlassStatScores(num_classes=3, average=None)
>>> mcss(preds, target)
tensor([[1, 0, 2, 1, 2],
[1, 1, 2, 0, 1],
[1, 0, 3, 0, 1]])
Example (preds is float tensor):
>>> from torchmetrics.classification import MulticlassStatScores
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([[0.16, 0.26, 0.58],
... [0.22, 0.61, 0.17],
... [0.71, 0.09, 0.20],
... [0.05, 0.82, 0.13]])
>>> metric = MulticlassStatScores(num_classes=3, average='micro')
>>> metric(preds, target)
tensor([3, 1, 7, 1, 4])
>>> mcss = MulticlassStatScores(num_classes=3, average=None)
>>> mcss(preds, target)
tensor([[1, 0, 2, 1, 2],
[1, 1, 2, 0, 1],
[1, 0, 3, 0, 1]])
Example (multidim tensors):
>>> from torchmetrics.classification import MulticlassStatScores
>>> target = tensor([[[0, 1], [2, 1], [0, 2]], [[1, 1], [2, 0], [1, 2]]])
>>> preds = tensor([[[0, 2], [2, 0], [0, 1]], [[2, 2], [2, 1], [1, 0]]])
>>> metric = MulticlassStatScores(num_classes=3, multidim_average="samplewise", average='micro')
>>> metric(preds, target)
tensor([[3, 3, 9, 3, 6],
[2, 4, 8, 4, 6]])
>>> mcss = MulticlassStatScores(num_classes=3, multidim_average="samplewise", average=None)
>>> mcss(preds, target)
tensor([[[2, 1, 3, 0, 2],
[0, 1, 3, 2, 2],
[1, 1, 3, 1, 2]],
[[0, 1, 4, 1, 1],
[1, 1, 2, 2, 3],
[1, 2, 2, 1, 2]]])
"""
is_differentiable: bool = False
higher_is_better: Optional[bool] = None
full_state_update: bool = False
def __init__(
self,
num_classes: int,
top_k: int = 1,
average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
multidim_average: Literal["global", "samplewise"] = "global",
ignore_index: Optional[int] = None,
validate_args: bool = True,
**kwargs: Any,
) -> None:
super(_AbstractStatScores, self).__init__(**kwargs)
if validate_args:
_multiclass_stat_scores_arg_validation(num_classes, top_k, average, multidim_average, ignore_index)
self.num_classes = num_classes
self.top_k = top_k
self.average = average
self.multidim_average = multidim_average
self.ignore_index = ignore_index
self.validate_args = validate_args
self._create_state(
size=1 if (average == "micro" and top_k == 1) else num_classes, multidim_average=multidim_average
)
def update(self, preds: Tensor, target: Tensor) -> None:
"""Update state with predictions and targets."""
if self.validate_args:
_multiclass_stat_scores_tensor_validation(
preds, target, self.num_classes, self.multidim_average, self.ignore_index
)
preds, target = _multiclass_stat_scores_format(preds, target, self.top_k)
tp, fp, tn, fn = _multiclass_stat_scores_update(
preds, target, self.num_classes, self.top_k, self.average, self.multidim_average, self.ignore_index
)
self._update_state(tp, fp, tn, fn)
def compute(self) -> Tensor:
"""Compute the final statistics."""
tp, fp, tn, fn = self._final_state()
return _multiclass_stat_scores_compute(tp, fp, tn, fn, self.average, self.multidim_average)
class MultilabelStatScores(_AbstractStatScores):
r"""Compute true positives, false positives, true negatives, false negatives and the support for multilabel tasks.
Related to `Type I and Type II errors`_.
As input to ``forward`` and ``update`` the metric accepts the following input:
- ``preds`` (:class:`~torch.Tensor`): An int or float tensor of shape ``(N, C, ...)``. If preds is a floating
point tensor with values outside [0,1] range we consider the input to be logits and will auto apply sigmoid
per element. Addtionally, we convert to int tensor with thresholding using the value in ``threshold``.
- ``target`` (:class:`~torch.Tensor`): An int tensor of shape ``(N, C, ...)``
As output to ``forward`` and ``compute`` the metric returns the following output:
- ``mlss`` (:class:`~torch.Tensor`): A tensor of shape ``(..., 5)``, where the last dimension corresponds
to ``[tp, fp, tn, fn, sup]`` (``sup`` stands for support and equals ``tp + fn``). The shape
depends on ``average`` and ``multidim_average`` parameters:
- If ``multidim_average`` is set to ``global``
- If ``average='micro'/'macro'/'weighted'``, the shape will be ``(5,)``
- If ``average=None/'none'``, the shape will be ``(C, 5)``
- If ``multidim_average`` is set to ``samplewise``
- If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N, 5)``
- If ``average=None/'none'``, the shape will be ``(N, C, 5)``
Args:
num_labels: Integer specifing the number of labels
threshold: Threshold for transforming probability to binary (0,1) predictions
average:
Defines the reduction that is applied over labels. Should be one of the following:
- ``micro``: Sum statistics over all labels
- ``macro``: Calculate statistics for each label and average them
- ``weighted``: calculates statistics for each label and computes weighted average using their support
- ``"none"`` or ``None``: calculates statistic for each label and applies no reduction
multidim_average:
Defines how additionally dimensions ``...`` should be handled. Should be one of the following:
- ``global``: Additional dimensions are flatted along the batch dimension
- ``samplewise``: Statistic will be calculated independently for each sample on the ``N`` axis.
The statistics in this case are calculated over the additional dimensions.
ignore_index:
Specifies a target value that is ignored and does not contribute to the metric calculation
validate_args: bool indicating if input arguments and tensors should be validated for correctness.
Set to ``False`` for faster computations.
kwargs: Additional keyword arguments, see :ref:`Metric kwargs` for more info.
Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.classification import MultilabelStatScores
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0, 0, 1], [1, 0, 1]])
>>> metric = MultilabelStatScores(num_labels=3, average='micro')
>>> metric(preds, target)
tensor([2, 1, 2, 1, 3])
>>> mlss = MultilabelStatScores(num_labels=3, average=None)
>>> mlss(preds, target)
tensor([[1, 0, 1, 0, 1],
[0, 0, 1, 1, 1],
[1, 1, 0, 0, 1]])
Example (preds is float tensor):
>>> from torchmetrics.classification import MultilabelStatScores
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
>>> metric = MultilabelStatScores(num_labels=3, average='micro')
>>> metric(preds, target)
tensor([2, 1, 2, 1, 3])
>>> mlss = MultilabelStatScores(num_labels=3, average=None)
>>> mlss(preds, target)
tensor([[1, 0, 1, 0, 1],
[0, 0, 1, 1, 1],
[1, 1, 0, 0, 1]])
Example (multidim tensors):
>>> from torchmetrics.classification import MultilabelStatScores
>>> target = tensor([[[0, 1], [1, 0], [0, 1]], [[1, 1], [0, 0], [1, 0]]])
>>> preds = tensor([[[0.59, 0.91], [0.91, 0.99], [0.63, 0.04]],
... [[0.38, 0.04], [0.86, 0.780], [0.45, 0.37]]])
>>> metric = MultilabelStatScores(num_labels=3, multidim_average='samplewise', average='micro')
>>> metric(preds, target)
tensor([[2, 3, 0, 1, 3],
[0, 2, 1, 3, 3]])
>>> mlss = MultilabelStatScores(num_labels=3, multidim_average='samplewise', average=None)
>>> mlss(preds, target)
tensor([[[1, 1, 0, 0, 1],
[1, 1, 0, 0, 1],
[0, 1, 0, 1, 1]],
[[0, 0, 0, 2, 2],
[0, 2, 0, 0, 0],
[0, 0, 1, 1, 1]]])
"""
is_differentiable: bool = False
higher_is_better: Optional[bool] = None
full_state_update: bool = False
def __init__(
self,
num_labels: int,
threshold: float = 0.5,
average: Optional[Literal["micro", "macro", "weighted", "none"]] = "macro",
multidim_average: Literal["global", "samplewise"] = "global",
ignore_index: Optional[int] = None,
validate_args: bool = True,
**kwargs: Any,
) -> None:
super(_AbstractStatScores, self).__init__(**kwargs)
if validate_args:
_multilabel_stat_scores_arg_validation(num_labels, threshold, average, multidim_average, ignore_index)
self.num_labels = num_labels
self.threshold = threshold
self.average = average
self.multidim_average = multidim_average
self.ignore_index = ignore_index
self.validate_args = validate_args
self._create_state(size=num_labels, multidim_average=multidim_average)
def update(self, preds: Tensor, target: Tensor) -> None:
"""Update state with predictions and targets."""
if self.validate_args:
_multilabel_stat_scores_tensor_validation(
preds, target, self.num_labels, self.multidim_average, self.ignore_index
)
preds, target = _multilabel_stat_scores_format(
preds, target, self.num_labels, self.threshold, self.ignore_index
)
tp, fp, tn, fn = _multilabel_stat_scores_update(preds, target, self.multidim_average)
self._update_state(tp, fp, tn, fn)
def compute(self) -> Tensor:
"""Compute the final statistics."""
tp, fp, tn, fn = self._final_state()
return _multilabel_stat_scores_compute(tp, fp, tn, fn, self.average, self.multidim_average)
class StatScores(_ClassificationTaskWrapper):
r"""Compute the number of true positives, false positives, true negatives, false negatives and the support.
This function is a simple wrapper to get the task specific versions of this metric, which is done by setting the
``task`` argument to either ``'binary'``, ``'multiclass'`` or ``multilabel``. See the documentation of
:mod:`BinaryStatScores`, :mod:`MulticlassStatScores` and :mod:`MultilabelStatScores` for the specific
details of each argument influence and examples.
Legacy Example:
>>> from torch import tensor
>>> preds = tensor([1, 0, 2, 1])
>>> target = tensor([1, 1, 2, 0])
>>> stat_scores = StatScores(task="multiclass", num_classes=3, average='micro')
>>> stat_scores(preds, target)
tensor([2, 2, 6, 2, 4])
>>> stat_scores = StatScores(task="multiclass", num_classes=3, average=None)
>>> stat_scores(preds, target)
tensor([[0, 1, 2, 1, 1],
[1, 1, 1, 1, 2],
[1, 0, 3, 0, 1]])
"""
def __new__(
cls,
task: Literal["binary", "multiclass", "multilabel"],
threshold: float = 0.5,
num_classes: Optional[int] = None,
num_labels: Optional[int] = None,
average: Optional[Literal["micro", "macro", "weighted", "none"]] = "micro",
multidim_average: Optional[Literal["global", "samplewise"]] = "global",
top_k: Optional[int] = 1,
ignore_index: Optional[int] = None,
validate_args: bool = True,
**kwargs: Any,
) -> Metric:
"""Initialize task metric."""
task = ClassificationTask.from_str(task)
assert multidim_average is not None # noqa: S101 # needed for mypy
kwargs.update(
{"multidim_average": multidim_average, "ignore_index": ignore_index, "validate_args": validate_args}
)
if task == ClassificationTask.BINARY:
return BinaryStatScores(threshold, **kwargs)
if task == ClassificationTask.MULTICLASS:
if not isinstance(num_classes, int):
raise ValueError(f"`num_classes` is expected to be `int` but `{type(num_classes)} was passed.`")
if not isinstance(top_k, int):
raise ValueError(f"`top_k` is expected to be `int` but `{type(top_k)} was passed.`")
return MulticlassStatScores(num_classes, top_k, average, **kwargs)
if task == ClassificationTask.MULTILABEL:
if not isinstance(num_labels, int):
raise ValueError(f"`num_labels` is expected to be `int` but `{type(num_labels)} was passed.`")
return MultilabelStatScores(num_labels, threshold, average, **kwargs)
raise ValueError(f"Task {task} not supported!")