View source on GitHub |
Computes the cosine similarity between the labels and predictions.
tf.keras.metrics.CosineSimilarity( name='cosine_similarity', dtype=None, axis=-1 )
cosine similarity = (a . b) / ||a|| ||b||
See: Cosine Similarity.
This metric keeps the average cosine similarity between predictions
and labels
over a stream of data.
Args | |
---|---|
name | (Optional) string name of the metric instance. |
dtype | (Optional) data type of the metric result. |
axis | (Optional) Defaults to -1. The dimension along which the cosine similarity is computed. |
# l2_norm(y_true) = [[0., 1.], [1./1.414], 1./1.414]]] # l2_norm(y_pred) = [[1., 0.], [1./1.414], 1./1.414]]] # l2_norm(y_true) . l2_norm(y_pred) = [[0., 0.], [0.5, 0.5]] # result = mean(sum(l2_norm(y_true) . l2_norm(y_pred), axis=1)) # = ((0. + 0.) + (0.5 + 0.5)) / 2 m = tf.keras.metrics.CosineSimilarity(axis=1) m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]]) m.result().numpy() 0.49999997
m.reset_states() m.update_state([[0., 1.], [1., 1.]], [[1., 0.], [1., 1.]], sample_weight=[0.3, 0.7]) m.result().numpy() 0.6999999
Usage with compile()
API:
model.compile( optimizer='sgd', loss='mse', metrics=[tf.keras.metrics.CosineSimilarity(axis=1)])
reset_states
reset_states()
Resets all of the metric state variables.
This function is called between epochs/steps, when a metric is evaluated during training.
result
result()
Computes and returns the metric value tensor.
Result computation is an idempotent operation that simply calculates the metric value using the state variables.
update_state
update_state( y_true, y_pred, sample_weight=None )
Accumulates metric statistics.
y_true
and y_pred
should have the same shape.
Args | |
---|---|
y_true | Ground truth values. shape = [batch_size, d0, .. dN] . |
y_pred | The predicted values. shape = [batch_size, d0, .. dN] . |
sample_weight | Optional sample_weight acts as a coefficient for the metric. If a scalar is provided, then the metric is simply scaled by the given value. If sample_weight is a tensor of size [batch_size] , then the metric for each sample of the batch is rescaled by the corresponding element in the sample_weight vector. If the shape of sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to this shape), then each metric element of y_pred is scaled by the corresponding value of sample_weight . (Note on dN-1 : all metric functions reduce by 1 dimension, usually the last axis (-1)). |
Returns | |
---|---|
Update op. |
© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/metrics/CosineSimilarity