File size: 23,406 Bytes
9c6594c |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 |
# 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 collections.abc import Sequence
from typing import Any, Optional, Union
from torch import Tensor
from typing_extensions import Literal
from torchmetrics.classification.base import _ClassificationTaskWrapper
from torchmetrics.classification.stat_scores import BinaryStatScores, MulticlassStatScores, MultilabelStatScores
from torchmetrics.functional.classification.accuracy import _accuracy_reduce
from torchmetrics.metric import Metric
from torchmetrics.utilities.enums import ClassificationTask
from torchmetrics.utilities.imports import _MATPLOTLIB_AVAILABLE
from torchmetrics.utilities.plot import _AX_TYPE, _PLOT_OUT_TYPE
if not _MATPLOTLIB_AVAILABLE:
__doctest_skip__ = ["BinaryAccuracy.plot", "MulticlassAccuracy.plot", "MultilabelAccuracy.plot"]
class BinaryAccuracy(BinaryStatScores):
r"""Compute `Accuracy`_ for binary tasks.
.. math::
\text{Accuracy} = \frac{1}{N}\sum_i^N 1(y_i = \hat{y}_i)
Where :math:`y` is a tensor of target values, and :math:`\hat{y}` is a tensor of predictions.
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. Additionally, 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:
- ``acc`` (:class:`~torch.Tensor`): If ``multidim_average`` is set to ``global``, metric returns a scalar value.
If ``multidim_average`` is set to ``samplewise``, the metric returns ``(N,)`` vector consisting of a scalar
value per sample.
If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present,
which the reduction will then be applied over instead of the sample dimension ``N``.
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.
Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.classification import BinaryAccuracy
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0, 0, 1, 1, 0, 1])
>>> metric = BinaryAccuracy()
>>> metric(preds, target)
tensor(0.6667)
Example (preds is float tensor):
>>> from torchmetrics.classification import BinaryAccuracy
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92])
>>> metric = BinaryAccuracy()
>>> metric(preds, target)
tensor(0.6667)
Example (multidim tensors):
>>> from torchmetrics.classification import BinaryAccuracy
>>> 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 = BinaryAccuracy(multidim_average='samplewise')
>>> metric(preds, target)
tensor([0.3333, 0.1667])
"""
is_differentiable: bool = False
higher_is_better: bool = True
full_state_update: bool = False
plot_lower_bound: float = 0.0
plot_upper_bound: float = 1.0
def compute(self) -> Tensor:
"""Compute accuracy based on inputs passed in to ``update`` previously."""
tp, fp, tn, fn = self._final_state()
return _accuracy_reduce(tp, fp, tn, fn, average="binary", multidim_average=self.multidim_average)
def plot(
self, val: Optional[Union[Tensor, Sequence[Tensor]]] = None, ax: Optional[_AX_TYPE] = None
) -> _PLOT_OUT_TYPE:
"""Plot a single or multiple values from the metric.
Args:
val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results.
If no value is provided, will automatically call `metric.compute` and plot that result.
ax: An matplotlib axis object. If provided will add plot to that axis
Returns:
Figure object and Axes object
Raises:
ModuleNotFoundError:
If `matplotlib` is not installed
.. plot::
:scale: 75
>>> from torch import rand, randint
>>> # Example plotting a single value
>>> from torchmetrics.classification import BinaryAccuracy
>>> metric = BinaryAccuracy()
>>> metric.update(rand(10), randint(2,(10,)))
>>> fig_, ax_ = metric.plot()
.. plot::
:scale: 75
>>> from torch import rand, randint
>>> # Example plotting multiple values
>>> from torchmetrics.classification import BinaryAccuracy
>>> metric = BinaryAccuracy()
>>> values = [ ]
>>> for _ in range(10):
... values.append(metric(rand(10), randint(2,(10,))))
>>> fig_, ax_ = metric.plot(values)
"""
return self._plot(val, ax)
class MulticlassAccuracy(MulticlassStatScores):
r"""Compute `Accuracy`_ for multiclass tasks.
.. math::
\text{Accuracy} = \frac{1}{N}\sum_i^N 1(y_i = \hat{y}_i)
Where :math:`y` is a tensor of target values, and :math:`\hat{y}` is a tensor of predictions.
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:
- ``mca`` (:class:`~torch.Tensor`): A tensor with the accuracy score whose returned shape depends on the
``average`` and ``multidim_average`` arguments:
- If ``multidim_average`` is set to ``global``:
- If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor
- If ``average=None/'none'``, the shape will be ``(C,)``
- If ``multidim_average`` is set to ``samplewise``:
- If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)``
- If ``average=None/'none'``, the shape will be ``(N, C)``
If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present,
which the reduction will then be applied over instead of the sample dimension ``N``.
Args:
num_classes: Integer specifying 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.
Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.classification import MulticlassAccuracy
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([2, 1, 0, 1])
>>> metric = MulticlassAccuracy(num_classes=3)
>>> metric(preds, target)
tensor(0.8333)
>>> mca = MulticlassAccuracy(num_classes=3, average=None)
>>> mca(preds, target)
tensor([0.5000, 1.0000, 1.0000])
Example (preds is float tensor):
>>> from torchmetrics.classification import MulticlassAccuracy
>>> 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 = MulticlassAccuracy(num_classes=3)
>>> metric(preds, target)
tensor(0.8333)
>>> mca = MulticlassAccuracy(num_classes=3, average=None)
>>> mca(preds, target)
tensor([0.5000, 1.0000, 1.0000])
Example (multidim tensors):
>>> from torchmetrics.classification import MulticlassAccuracy
>>> 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 = MulticlassAccuracy(num_classes=3, multidim_average='samplewise')
>>> metric(preds, target)
tensor([0.5000, 0.2778])
>>> mca = MulticlassAccuracy(num_classes=3, multidim_average='samplewise', average=None)
>>> mca(preds, target)
tensor([[1.0000, 0.0000, 0.5000],
[0.0000, 0.3333, 0.5000]])
"""
is_differentiable: bool = False
higher_is_better: bool = True
full_state_update: bool = False
plot_lower_bound: float = 0.0
plot_upper_bound: float = 1.0
plot_legend_name: str = "Class"
def compute(self) -> Tensor:
"""Compute accuracy based on inputs passed in to ``update`` previously."""
tp, fp, tn, fn = self._final_state()
return _accuracy_reduce(
tp, fp, tn, fn, average=self.average, multidim_average=self.multidim_average, top_k=self.top_k
)
def plot(
self, val: Optional[Union[Tensor, Sequence[Tensor]]] = None, ax: Optional[_AX_TYPE] = None
) -> _PLOT_OUT_TYPE:
"""Plot a single or multiple values from the metric.
Args:
val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results.
If no value is provided, will automatically call `metric.compute` and plot that result.
ax: An matplotlib axis object. If provided will add plot to that axis
Returns:
Figure object and Axes object
Raises:
ModuleNotFoundError:
If `matplotlib` is not installed
.. plot::
:scale: 75
>>> from torch import randint
>>> # Example plotting a single value per class
>>> from torchmetrics.classification import MulticlassAccuracy
>>> metric = MulticlassAccuracy(num_classes=3, average=None)
>>> metric.update(randint(3, (20,)), randint(3, (20,)))
>>> fig_, ax_ = metric.plot()
.. plot::
:scale: 75
>>> from torch import randint
>>> # Example plotting a multiple values per class
>>> from torchmetrics.classification import MulticlassAccuracy
>>> metric = MulticlassAccuracy(num_classes=3, average=None)
>>> values = []
>>> for _ in range(20):
... values.append(metric(randint(3, (20,)), randint(3, (20,))))
>>> fig_, ax_ = metric.plot(values)
"""
return self._plot(val, ax)
class MultilabelAccuracy(MultilabelStatScores):
r"""Compute `Accuracy`_ for multilabel tasks.
.. math::
\text{Accuracy} = \frac{1}{N}\sum_i^N 1(y_i = \hat{y}_i)
Where :math:`y` is a tensor of target values, and :math:`\hat{y}` is a tensor of predictions.
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. Additionally, 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:
- ``mla`` (:class:`~torch.Tensor`): A tensor with the accuracy score whose returned shape depends on the
``average`` and ``multidim_average`` arguments:
- If ``multidim_average`` is set to ``global``:
- If ``average='micro'/'macro'/'weighted'``, the output will be a scalar tensor
- If ``average=None/'none'``, the shape will be ``(C,)``
- If ``multidim_average`` is set to ``samplewise``:
- If ``average='micro'/'macro'/'weighted'``, the shape will be ``(N,)``
- If ``average=None/'none'``, the shape will be ``(N, C)``
If ``multidim_average`` is set to ``samplewise`` we expect at least one additional dimension ``...`` to be present,
which the reduction will then be applied over instead of the sample dimension ``N``.
Args:
num_labels: Integer specifying 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.
Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.classification import MultilabelAccuracy
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0, 0, 1], [1, 0, 1]])
>>> metric = MultilabelAccuracy(num_labels=3)
>>> metric(preds, target)
tensor(0.6667)
>>> mla = MultilabelAccuracy(num_labels=3, average=None)
>>> mla(preds, target)
tensor([1.0000, 0.5000, 0.5000])
Example (preds is float tensor):
>>> from torchmetrics.classification import MultilabelAccuracy
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
>>> metric = MultilabelAccuracy(num_labels=3)
>>> metric(preds, target)
tensor(0.6667)
>>> mla = MultilabelAccuracy(num_labels=3, average=None)
>>> mla(preds, target)
tensor([1.0000, 0.5000, 0.5000])
Example (multidim tensors):
>>> from torchmetrics.classification import MultilabelAccuracy
>>> 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]],
... ]
... )
>>> mla = MultilabelAccuracy(num_labels=3, multidim_average='samplewise')
>>> mla(preds, target)
tensor([0.3333, 0.1667])
>>> mla = MultilabelAccuracy(num_labels=3, multidim_average='samplewise', average=None)
>>> mla(preds, target)
tensor([[0.5000, 0.5000, 0.0000],
[0.0000, 0.0000, 0.5000]])
"""
is_differentiable: bool = False
higher_is_better: bool = True
full_state_update: bool = False
plot_lower_bound: float = 0.0
plot_upper_bound: float = 1.0
plot_legend_name: str = "Label"
def compute(self) -> Tensor:
"""Compute accuracy based on inputs passed in to ``update`` previously."""
tp, fp, tn, fn = self._final_state()
return _accuracy_reduce(
tp, fp, tn, fn, average=self.average, multidim_average=self.multidim_average, multilabel=True
)
def plot(
self, val: Optional[Union[Tensor, Sequence[Tensor]]] = None, ax: Optional[_AX_TYPE] = None
) -> _PLOT_OUT_TYPE:
"""Plot a single or multiple values from the metric.
Args:
val: Either a single result from calling `metric.forward` or `metric.compute` or a list of these results.
If no value is provided, will automatically call `metric.compute` and plot that result.
ax: An matplotlib axis object. If provided will add plot to that axis
Returns:
Figure and Axes object
Raises:
ModuleNotFoundError:
If `matplotlib` is not installed
.. plot::
:scale: 75
>>> from torch import rand, randint
>>> # Example plotting a single value
>>> from torchmetrics.classification import MultilabelAccuracy
>>> metric = MultilabelAccuracy(num_labels=3)
>>> metric.update(randint(2, (20, 3)), randint(2, (20, 3)))
>>> fig_, ax_ = metric.plot()
.. plot::
:scale: 75
>>> from torch import rand, randint
>>> # Example plotting multiple values
>>> from torchmetrics.classification import MultilabelAccuracy
>>> metric = MultilabelAccuracy(num_labels=3)
>>> values = [ ]
>>> for _ in range(10):
... values.append(metric(randint(2, (20, 3)), randint(2, (20, 3))))
>>> fig_, ax_ = metric.plot(values)
"""
return self._plot(val, ax)
class Accuracy(_ClassificationTaskWrapper):
r"""Compute `Accuracy`_.
.. math::
\text{Accuracy} = \frac{1}{N}\sum_i^N 1(y_i = \hat{y}_i)
Where :math:`y` is a tensor of target values, and :math:`\hat{y}` is a tensor of predictions.
This module 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
:class:`~torchmetrics.classification.BinaryAccuracy`, :class:`~torchmetrics.classification.MulticlassAccuracy` and
:class:`~torchmetrics.classification.MultilabelAccuracy` for the specific details of each argument influence and
examples.
Legacy Example:
>>> from torch import tensor
>>> target = tensor([0, 1, 2, 3])
>>> preds = tensor([0, 2, 1, 3])
>>> accuracy = Accuracy(task="multiclass", num_classes=4)
>>> accuracy(preds, target)
tensor(0.5000)
>>> target = tensor([0, 1, 2])
>>> preds = tensor([[0.1, 0.9, 0], [0.3, 0.1, 0.6], [0.2, 0.5, 0.3]])
>>> accuracy = Accuracy(task="multiclass", num_classes=3, top_k=2)
>>> accuracy(preds, target)
tensor(0.6667)
"""
def __new__( # type: ignore[misc]
cls: type["Accuracy"],
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: 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)
kwargs.update({
"multidim_average": multidim_average,
"ignore_index": ignore_index,
"validate_args": validate_args,
})
if task == ClassificationTask.BINARY:
return BinaryAccuracy(threshold, **kwargs)
if task == ClassificationTask.MULTICLASS:
if not isinstance(num_classes, int):
raise ValueError(
f"Optional arg `num_classes` must be type `int` when task is {task}. Got {type(num_classes)}"
)
if not isinstance(top_k, int):
raise ValueError(f"Optional arg `top_k` must be type `int` when task is {task}. Got {type(top_k)}")
return MulticlassAccuracy(num_classes, top_k, average, **kwargs)
if task == ClassificationTask.MULTILABEL:
if not isinstance(num_labels, int):
raise ValueError(
f"Optional arg `num_labels` must be type `int` when task is {task}. Got {type(num_labels)}"
)
return MultilabelAccuracy(num_labels, threshold, average, **kwargs)
raise ValueError(f"Not handled value: {task}")
|