o %ݫi @s4dZddlZddlmZdddZGdddZdS) z3Calculate accuracy. Authors * Jianyuan Zhong 2020 N)length_to_maskcCs|dur(t||jd|jdd}t|jdkr(|ddd|jd}|d}|durDt| || |k}t|}n t||k}|jd}t |t |fS)aCalculates the accuracy for predicted log probabilities and targets in a batch. Arguments --------- log_probabilities : torch.Tensor Predicted log probabilities (batch_size, time, feature). targets : torch.Tensor Target (batch_size, time). length : torch.Tensor Length of target (batch_size,). Returns ------- numerator : float The number of correct samples denominator : float The total number of samples Example ------- >>> probs = torch.tensor([[0.9, 0.1], [0.1, 0.9], [0.8, 0.2]]).unsqueeze(0) >>> acc = Accuracy(torch.log(probs), torch.tensor([1, 1, 0]).unsqueeze(0), torch.tensor([2/3])) >>> print(acc) (1.0, 2.0) N)max_len) rshapeboollen unsqueezerepeatargmaxtorchsum masked_selectfloat)log_probabilitiestargetslengthmask padded_pred numerator denominatorrN/home/ubuntu/.local/lib/python3.10/site-packages/speechbrain/utils/Accuracy.pyAccuracy s$    rc@s*eZdZdZddZd ddZddZdS) AccuracyStatsaqModule for calculate the overall one-step-forward prediction accuracy. Example ------- >>> probs = torch.tensor([[0.9, 0.1], [0.1, 0.9], [0.8, 0.2]]).unsqueeze(0) >>> stats = AccuracyStats() >>> stats.append(torch.log(probs), torch.tensor([1, 1, 0]).unsqueeze(0), torch.tensor([2/3])) >>> acc = stats.summarize() >>> print(acc) 0.5 cCsd|_d|_dS)Nrcorrecttotalselfrrr__init__Hs zAccuracyStats.__init__NcCs0t|||\}}|j|7_|j|7_dS)aThis function is for updating the stats according to the prediction and target in the current batch. Arguments --------- log_probabilities : torch.Tensor Predicted log probabilities (batch_size, time, feature). targets : torch.Tensor Target (batch_size, time). length : torch.Tensor Length of target (batch_size,). N)rrr)r!rrrrrrrrappendLs zAccuracyStats.appendcCs |j|jS)zComputes the accuracy metric.rr rrr summarize]s zAccuracyStats.summarizeN)__name__ __module__ __qualname____doc__r"r#r$rrrrr;s   rr%)r)rspeechbrain.dataio.dataiorrrrrrrs   /