Cosine Similarity¶

Module Interface¶

class torchmetrics.CosineSimilarity(reduction='sum', **kwargs)[source]

Computes the Cosine Similarity between targets and predictions:

$cos_{sim}(x,y) = \frac{x \cdot y}{||x|| \cdot ||y||} = \frac{\sum_{i=1}^n x_i y_i}{\sqrt{\sum_{i=1}^n x_i^2}\sqrt{\sum_{i=1}^n y_i^2}}$

where $y$ is a tensor of target values, and $x$ is a tensor of predictions.

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

preds (Tensor): Predicted float tensor with shape (N,d)
target (Tensor): Ground truth float tensor with shape (N,d)

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

cosine_similarity (Tensor): A float tensor with the cosine similarity

Parameters

reduction¶ (Literal[‘mean’, ‘sum’, ‘none’, None]) – how to reduce over the batch dimension using ‘sum’, ‘mean’ or ‘none’ (taking the individual scores)
kwargs¶ (Any) – Additional keyword arguments, see Advanced metric settings for more info.

Example

>>> from torchmetrics import CosineSimilarity
>>> target = torch.tensor([[0, 1], [1, 1]])
>>> preds = torch.tensor([[0, 1], [0, 1]])
>>> cosine_similarity = CosineSimilarity(reduction = 'mean')
>>> cosine_similarity(preds, target)
tensor(0.8536)

Initializes internal Module state, shared by both nn.Module and ScriptModule.

Functional Interface¶

torchmetrics.functional.cosine_similarity(preds, target, reduction='sum')[source]

Computes the Cosine Similarity between targets and predictions:

$cos_{sim}(x,y) = \frac{x \cdot y}{||x|| \cdot ||y||} = \frac{\sum_{i=1}^n x_i y_i}{\sqrt{\sum_{i=1}^n x_i^2}\sqrt{\sum_{i=1}^n y_i^2}}$

where $y$ is a tensor of target values, and $x$ is a tensor of predictions.

Parameters

preds¶ (Tensor) – Predicted tensor with shape (N,d)
target¶ (Tensor) – Ground truth tensor with shape (N,d)
reduction¶ (Optional[str]) – The method of reducing along the batch dimension using sum, mean or taking the individual scores

Example

>>> from torchmetrics.functional.regression import cosine_similarity
>>> target = torch.tensor([[1, 2, 3, 4],
...                        [1, 2, 3, 4]])
>>> preds = torch.tensor([[1, 2, 3, 4],
...                       [-1, -2, -3, -4]])
>>> cosine_similarity(preds, target, 'none')
tensor([ 1.0000, -1.0000])

Return type: Tensor