mighty.monitor.accuracy.AccuracyEmbedding¶
- class mighty.monitor.accuracy.AccuracyEmbedding(metric='cosine', cache=False)[source]¶
Calculates the accuracy of embedding vectors. The mean embedding vector is kept for each class. Prediction is based on the closest centroid ID.
- Parameters:
- metricstr, optional
The metric to compute pairwise distances with. Default: ‘cosine’
- cachebool, optional
Cache predicted data or not. Default: False
Methods
__init__
([metric, cache])distances
(outputs_test)Returns the distances to fit centroid means.
extra_repr
()partial_fit
(outputs_batch, labels_batch)If the accuracy measure is not argmax (if the model's last layer isn't a softmax), the output is an embedding vector, which has to be stored and retrieved at prediction.
predict
(outputs_test)Predict the labels, given model output.
Predicts the output of a model, using cached output activations.
predict_proba
(outputs_test)Compute label probabilities, given model output.
reset
()Resets all cached predicted and ground truth data.
Resets predicted and ground truth labels.
Attributes
- Returns:
- Returns:
- property centroids¶
- Returns:
- torch.Tensor
(C, N) mean centroids tensor, where C is the number of unique classes, and N is the hidden layer dimensionality.
- distances(outputs_test)[source]¶
Returns the distances to fit centroid means.
- Parameters:
- outputs_test(B, D) torch.Tensor
Hidden layer activations.
- Returns:
- distances(B, C) torch.Tensor
Distances to each class (label).
- property is_fit¶
- Returns:
- bool
Whether the accuracy predictor is fit with data or not.
- partial_fit(outputs_batch, labels_batch)[source]¶
If the accuracy measure is not argmax (if the model’s last layer isn’t a softmax), the output is an embedding vector, which has to be stored and retrieved at prediction.
- Parameters:
- outputs_batchtorch.Tensor or tuple
The output of a model.
- labels_batchtorch.Tensor
True labels.
- predict(outputs_test)[source]¶
Predict the labels, given model output.
- Parameters:
- outputs_testtorch.Tensor or tuple
The output of a model.
- Returns:
- torch.Tensor
Predicted labels.
- predict_cached()[source]¶
Predicts the output of a model, using cached output activations.
- Returns:
- torch.Tensor
Predicted labels.
- predict_proba(outputs_test)[source]¶
Compute label probabilities, given model output.
- Parameters:
- outputs_testtorch.Tensor or tuple
The output of a model.
- Returns:
- torch.Tensor
The probabilities of assigning to each class of shape (., C), where C is the number of classes.
- reset_labels()¶
Resets predicted and ground truth labels.