fibber.metrics.similarity.use_similarity_metric module

This metric computes the cosine similarity between two sentences. The sentence embedding is the universal sentence encoder.

class fibber.metrics.similarity.use_similarity_metric.USESimilarityMetric(use_gpu_id=- 1, **kwargs)

Bases: fibber.metrics.metric_base.MetricBase

This metric uses universal sentence encoder to measure the semantic similarity of two sentences.

Initialize universal sentence encoder.

fibber.metrics.similarity.use_similarity_metric.config_tf_gpu(gpu_id)

Configure tensorflow to use a specific GPU.

Parameters

gpu_id (int) – the gpu id. Set -1 to use CPU.

previous

fibber.metrics.similarity.glove_similarity_metric module

next

fibber.metrics.attack_aggregation_utils module