Hamming Distance

Module Interface

class torchmetrics.HammingDistance(**kwargs)[source]

Compute the average Hamming distance (also known as Hamming loss).

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

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 BinaryHammingDistance, MulticlassHammingDistance and MultilabelHammingDistance for the specific details of each argument influence and examples.

Legacy Example:
>>> from torch import tensor
>>> target = tensor([[0, 1], [1, 1]])
>>> preds = tensor([[0, 1], [0, 1]])
>>> hamming_distance = HammingDistance(task="multilabel", num_labels=2)
>>> hamming_distance(preds, target)
tensor(0.2500)
static __new__(cls, task, threshold=0.5, num_classes=None, num_labels=None, average='micro', multidim_average='global', top_k=1, ignore_index=None, validate_args=True, **kwargs)[source]

Initialize task metric.

Return type:

Metric

BinaryHammingDistance

class torchmetrics.classification.BinaryHammingDistance(threshold=0.5, multidim_average='global', ignore_index=None, validate_args=True, **kwargs)[source]

Compute the average Hamming distance (also known as Hamming loss) for binary tasks.

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

As input to forward and update the metric accepts the following input:

  • preds (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 (Tensor): An int tensor of shape (N, ...).

As output to forward and compute the metric returns the following output:

  • bhd (Tensor): A tensor whose returned shape depends on the multidim_average arguments:

    • If multidim_average is set to global, the 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.

Parameters:
  • threshold (float) – Threshold for transforming probability to binary {0,1} predictions

  • multidim_average (Literal['global', 'samplewise']) –

    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 (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – 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 BinaryHammingDistance
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0, 0, 1, 1, 0, 1])
>>> metric = BinaryHammingDistance()
>>> metric(preds, target)
tensor(0.3333)
Example (preds is float tensor):
>>> from torchmetrics.classification import BinaryHammingDistance
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92])
>>> metric = BinaryHammingDistance()
>>> metric(preds, target)
tensor(0.3333)
Example (multidim tensors):
>>> from torchmetrics.classification import BinaryHammingDistance
>>> 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 = BinaryHammingDistance(multidim_average='samplewise')
>>> metric(preds, target)
tensor([0.6667, 0.8333])
plot(val=None, ax=None)[source]

Plot a single or multiple values from the metric.

Parameters:
  • val (Union[Tensor, Sequence[Tensor], None]) – 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 (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

Tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure object and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value
>>> from torch import rand, randint
>>> from torchmetrics.classification import BinaryHammingDistance
>>> metric = BinaryHammingDistance()
>>> metric.update(rand(10), randint(2,(10,)))
>>> fig_, ax_ = metric.plot()
../_images/hamming_distance-1.png
>>> # Example plotting multiple values
>>> from torch import rand, randint
>>> from torchmetrics.classification import BinaryHammingDistance
>>> metric = BinaryHammingDistance()
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(rand(10), randint(2,(10,))))
>>> fig_, ax_ = metric.plot(values)
../_images/hamming_distance-2.png

MulticlassHammingDistance

class torchmetrics.classification.MulticlassHammingDistance(num_classes, top_k=1, average='macro', multidim_average='global', ignore_index=None, validate_args=True, **kwargs)[source]

Compute the average Hamming distance (also known as Hamming loss) for multiclass tasks.

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

As input to forward and update the metric accepts the following input:

  • preds (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 (Tensor): An int tensor of shape (N, ...).

As output to forward and compute the metric returns the following output:

  • mchd (Tensor): A tensor 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.

Parameters:
  • num_classes (int) – Integer specifying the number of classes

  • average (Optional[Literal['micro', 'macro', 'weighted', 'none']]) –

    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 (int) – Number of highest probability or logit score predictions considered to find the correct label. Only works when preds contain probabilities/logits.

  • multidim_average (Literal['global', 'samplewise']) –

    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 (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – 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 MulticlassHammingDistance
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([2, 1, 0, 1])
>>> metric = MulticlassHammingDistance(num_classes=3)
>>> metric(preds, target)
tensor(0.1667)
>>> mchd = MulticlassHammingDistance(num_classes=3, average=None)
>>> mchd(preds, target)
tensor([0.5000, 0.0000, 0.0000])
Example (preds is float tensor):
>>> from torchmetrics.classification import MulticlassHammingDistance
>>> 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 = MulticlassHammingDistance(num_classes=3)
>>> metric(preds, target)
tensor(0.1667)
>>> mchd = MulticlassHammingDistance(num_classes=3, average=None)
>>> mchd(preds, target)
tensor([0.5000, 0.0000, 0.0000])
Example (multidim tensors):
>>> from torchmetrics.classification import MulticlassHammingDistance
>>> 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 = MulticlassHammingDistance(num_classes=3, multidim_average='samplewise')
>>> metric(preds, target)
tensor([0.5000, 0.7222])
>>> mchd = MulticlassHammingDistance(num_classes=3, multidim_average='samplewise', average=None)
>>> mchd(preds, target)
tensor([[0.0000, 1.0000, 0.5000],
        [1.0000, 0.6667, 0.5000]])
plot(val=None, ax=None)[source]

Plot a single or multiple values from the metric.

Parameters:
  • val (Union[Tensor, Sequence[Tensor], None]) – 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 (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

Tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure object and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value per class
>>> from torch import randint
>>> from torchmetrics.classification import MulticlassHammingDistance
>>> metric = MulticlassHammingDistance(num_classes=3, average=None)
>>> metric.update(randint(3, (20,)), randint(3, (20,)))
>>> fig_, ax_ = metric.plot()
../_images/hamming_distance-3.png
>>> # Example plotting a multiple values per class
>>> from torch import randint
>>> from torchmetrics.classification import MulticlassHammingDistance
>>> metric = MulticlassHammingDistance(num_classes=3, average=None)
>>> values = []
>>> for _ in range(20):
...     values.append(metric(randint(3, (20,)), randint(3, (20,))))
>>> fig_, ax_ = metric.plot(values)
../_images/hamming_distance-4.png

MultilabelHammingDistance

class torchmetrics.classification.MultilabelHammingDistance(num_labels, threshold=0.5, average='macro', multidim_average='global', ignore_index=None, validate_args=True, **kwargs)[source]

Compute the average Hamming distance (also known as Hamming loss) for multilabel tasks.

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

As input to forward and update the metric accepts the following input:

  • preds (Tensor): An int tensor 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 (Tensor): An int tensor of shape (N, C, ...).

As output to forward and compute the metric returns the following output:

  • mlhd (Tensor): A tensor 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.

Parameters:
  • num_labels (int) – Integer specifying the number of labels

  • threshold (float) – Threshold for transforming probability to binary (0,1) predictions

  • average (Optional[Literal['micro', 'macro', 'weighted', 'none']]) –

    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 (Literal['global', 'samplewise']) –

    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 (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – 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 MultilabelHammingDistance
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0, 0, 1], [1, 0, 1]])
>>> metric = MultilabelHammingDistance(num_labels=3)
>>> metric(preds, target)
tensor(0.3333)
>>> mlhd = MultilabelHammingDistance(num_labels=3, average=None)
>>> mlhd(preds, target)
tensor([0.0000, 0.5000, 0.5000])
Example (preds is float tensor):
>>> from torchmetrics.classification import MultilabelHammingDistance
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
>>> metric = MultilabelHammingDistance(num_labels=3)
>>> metric(preds, target)
tensor(0.3333)
>>> mlhd = MultilabelHammingDistance(num_labels=3, average=None)
>>> mlhd(preds, target)
tensor([0.0000, 0.5000, 0.5000])
Example (multidim tensors):
>>> from torchmetrics.classification import MultilabelHammingDistance
>>> 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 = MultilabelHammingDistance(num_labels=3, multidim_average='samplewise')
>>> metric(preds, target)
tensor([0.6667, 0.8333])
>>> mlhd = MultilabelHammingDistance(num_labels=3, multidim_average='samplewise', average=None)
>>> mlhd(preds, target)
tensor([[0.5000, 0.5000, 1.0000],
        [1.0000, 1.0000, 0.5000]])
plot(val=None, ax=None)[source]

Plot a single or multiple values from the metric.

Parameters:
  • val (Union[Tensor, Sequence[Tensor], None]) – 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 (Optional[Axes]) – An matplotlib axis object. If provided will add plot to that axis

Return type:

Tuple[Figure, Union[Axes, ndarray]]

Returns:

Figure and Axes object

Raises:

ModuleNotFoundError – If matplotlib is not installed

>>> # Example plotting a single value
>>> from torch import rand, randint
>>> from torchmetrics.classification import MultilabelHammingDistance
>>> metric = MultilabelHammingDistance(num_labels=3)
>>> metric.update(randint(2, (20, 3)), randint(2, (20, 3)))
>>> fig_, ax_ = metric.plot()
../_images/hamming_distance-5.png
>>> # Example plotting multiple values
>>> from torch import rand, randint
>>> from torchmetrics.classification import MultilabelHammingDistance
>>> metric = MultilabelHammingDistance(num_labels=3)
>>> values = [ ]
>>> for _ in range(10):
...     values.append(metric(randint(2, (20, 3)), randint(2, (20, 3))))
>>> fig_, ax_ = metric.plot(values)
../_images/hamming_distance-6.png

Functional Interface

hamming_distance

torchmetrics.functional.hamming_distance(preds, target, task, threshold=0.5, num_classes=None, num_labels=None, average='micro', multidim_average='global', top_k=1, ignore_index=None, validate_args=True)[source]

Compute the average Hamming distance (also known as Hamming loss). :rtype: Tensor

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

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 binary_hamming_distance(), multiclass_hamming_distance() and multilabel_hamming_distance() for the specific details of each argument influence and examples.

Legacy Example:
>>> from torch import tensor
>>> target = tensor([[0, 1], [1, 1]])
>>> preds = tensor([[0, 1], [0, 1]])
>>> hamming_distance(preds, target, task="binary")
tensor(0.2500)

binary_hamming_distance

torchmetrics.functional.classification.binary_hamming_distance(preds, target, threshold=0.5, multidim_average='global', ignore_index=None, validate_args=True)[source]

Compute the average Hamming distance (also known as Hamming loss) for binary tasks.

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

Accepts the following input tensors:

  • preds (int or float tensor): (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 (int tensor): (N, ...)

Parameters:
  • preds (Tensor) – Tensor with predictions

  • target (Tensor) – Tensor with true labels

  • threshold (float) – Threshold for transforming probability to binary {0,1} predictions

  • multidim_average (Literal['global', 'samplewise']) –

    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 (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

Return type:

Tensor

Returns:

If multidim_average is set to global, the metric returns a scalar value. If multidim_average is set to samplewise, the metric returns (N,) vector consisting of a scalar value per sample.

Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.functional.classification import binary_hamming_distance
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0, 0, 1, 1, 0, 1])
>>> binary_hamming_distance(preds, target)
tensor(0.3333)
Example (preds is float tensor):
>>> from torchmetrics.functional.classification import binary_hamming_distance
>>> target = tensor([0, 1, 0, 1, 0, 1])
>>> preds = tensor([0.11, 0.22, 0.84, 0.73, 0.33, 0.92])
>>> binary_hamming_distance(preds, target)
tensor(0.3333)
Example (multidim tensors):
>>> from torchmetrics.functional.classification import binary_hamming_distance
>>> 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]]])
>>> binary_hamming_distance(preds, target, multidim_average='samplewise')
tensor([0.6667, 0.8333])

multiclass_hamming_distance

torchmetrics.functional.classification.multiclass_hamming_distance(preds, target, num_classes, average='macro', top_k=1, multidim_average='global', ignore_index=None, validate_args=True)[source]

Compute the average Hamming distance (also known as Hamming loss) for multiclass tasks.

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

Accepts the following input tensors:

  • preds: (N, ...) (int tensor) or (N, C, ..) (float tensor). If preds is a floating point we apply torch.argmax along the C dimension to automatically convert probabilities/logits into an int tensor.

  • target (int tensor): (N, ...)

Parameters:
  • preds (Tensor) – Tensor with predictions

  • target (Tensor) – Tensor with true labels

  • num_classes (int) – Integer specifying the number of classes

  • average (Optional[Literal['micro', 'macro', 'weighted', 'none']]) –

    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 (int) – Number of highest probability or logit score predictions considered to find the correct label. Only works when preds contain probabilities/logits.

  • multidim_average (Literal['global', 'samplewise']) –

    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 (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

Returns:

  • 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)

Return type:

The returned shape depends on the average and multidim_average arguments

Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.functional.classification import multiclass_hamming_distance
>>> target = tensor([2, 1, 0, 0])
>>> preds = tensor([2, 1, 0, 1])
>>> multiclass_hamming_distance(preds, target, num_classes=3)
tensor(0.1667)
>>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
tensor([0.5000, 0.0000, 0.0000])
Example (preds is float tensor):
>>> from torchmetrics.functional.classification import multiclass_hamming_distance
>>> 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]])
>>> multiclass_hamming_distance(preds, target, num_classes=3)
tensor(0.1667)
>>> multiclass_hamming_distance(preds, target, num_classes=3, average=None)
tensor([0.5000, 0.0000, 0.0000])
Example (multidim tensors):
>>> from torchmetrics.functional.classification import multiclass_hamming_distance
>>> 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]]])
>>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise')
tensor([0.5000, 0.7222])
>>> multiclass_hamming_distance(preds, target, num_classes=3, multidim_average='samplewise', average=None)
tensor([[0.0000, 1.0000, 0.5000],
        [1.0000, 0.6667, 0.5000]])

multilabel_hamming_distance

torchmetrics.functional.classification.multilabel_hamming_distance(preds, target, num_labels, threshold=0.5, average='macro', multidim_average='global', ignore_index=None, validate_args=True)[source]

Compute the average Hamming distance (also known as Hamming loss) for multilabel tasks.

\[\text{Hamming distance} = \frac{1}{N \cdot L} \sum_i^N \sum_l^L 1(y_{il} \neq \hat{y}_{il})\]

Where \(y\) is a tensor of target values, \(\hat{y}\) is a tensor of predictions, and \(\bullet_{il}\) refers to the \(l\)-th label of the \(i\)-th sample of that tensor.

Accepts the following input tensors:

  • preds (int or float tensor): (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 (int tensor): (N, C, ...)

Parameters:
  • preds (Tensor) – Tensor with predictions

  • target (Tensor) – Tensor with true labels

  • num_labels (int) – Integer specifying the number of labels

  • threshold (float) – Threshold for transforming probability to binary (0,1) predictions

  • average (Optional[Literal['micro', 'macro', 'weighted', 'none']]) –

    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 (Literal['global', 'samplewise']) –

    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 (Optional[int]) – Specifies a target value that is ignored and does not contribute to the metric calculation

  • validate_args (bool) – bool indicating if input arguments and tensors should be validated for correctness. Set to False for faster computations.

Returns:

  • 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)

Return type:

The returned shape depends on the average and multidim_average arguments

Example (preds is int tensor):
>>> from torch import tensor
>>> from torchmetrics.functional.classification import multilabel_hamming_distance
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0, 0, 1], [1, 0, 1]])
>>> multilabel_hamming_distance(preds, target, num_labels=3)
tensor(0.3333)
>>> multilabel_hamming_distance(preds, target, num_labels=3, average=None)
tensor([0.0000, 0.5000, 0.5000])
Example (preds is float tensor):
>>> from torchmetrics.functional.classification import multilabel_hamming_distance
>>> target = tensor([[0, 1, 0], [1, 0, 1]])
>>> preds = tensor([[0.11, 0.22, 0.84], [0.73, 0.33, 0.92]])
>>> multilabel_hamming_distance(preds, target, num_labels=3)
tensor(0.3333)
>>> multilabel_hamming_distance(preds, target, num_labels=3, average=None)
tensor([0.0000, 0.5000, 0.5000])
Example (multidim tensors):
>>> from torchmetrics.functional.classification import multilabel_hamming_distance
>>> 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]]])
>>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise')
tensor([0.6667, 0.8333])
>>> multilabel_hamming_distance(preds, target, num_labels=3, multidim_average='samplewise', average=None)
tensor([[0.5000, 0.5000, 1.0000],
        [1.0000, 1.0000, 0.5000]])