metrax.CosineSimilarity

class metrax.CosineSimilarity(total: Array, count: Array)

Bases: Average

Calculates the Cosine Similarity between two arrays.

The Cosine Similarity is defined as the dot product of the vectors divided by the product of their magnitudes (norms).

\[cos_{sim}(x,y) = \frac{x \cdot y}{||x|| * ||y||}\]

__init__(total: Array, count: Array) → None

Methods

__init__(total, count)
compute()	Computes final metrics from intermediate values.
compute_value()	Wraps compute() and returns a values.Value.
empty()	Returns an empty instance (i.e. .merge(Metric.empty()) is a no-op).
from_fun(fun)	Calls cls.from_model_output with the return value from fun.
from_model_output(predictions, targets[, axis])	Creates a CosineSimilarity instance.
from_output(name)	Calls cls.from_model_output with model output named name.
merge(other)	Returns Metric that is the accumulation of self and other.
reduce()	Reduces the metric along it first axis by calling _reduce_merge().
replace(**updates)	Returns a new object replacing the specified fields with new values.

Attributes

total
count

classmethod from_model_output(predictions: Array, targets: Array, axis: int = -1) → CosineSimilarity

Creates a CosineSimilarity instance.

Parameters:

• predictions – A floating point array of the predictions. The shape should be (batch_size,).

• targets – A floating point array of the targets. The shape should be (batch_size,).

• axis – The axis to compute the norm over.

Returns:

A CosineSimilarity instance.

__init__(total: Array, count: Array) → None

replace(**updates)

Returns a new object replacing the specified fields with new values.