class CrossEntropyLoss[स्रोत]#

आधार: Loss

This class computes the cross entropy loss for each sample as:

\[\text{CrossEntropyLoss}(predict, target) = -\sum_{i=0}^{N_{\text{classes}}} target_i * log(predict_i).\]


evaluate(predict, target)[स्रोत]#

An abstract method for evaluating the loss function. Inputs are expected in a shape of (N, *). Where N is a number of samples. Loss is computed for each sample individually.

  • predict (ndarray) -- an array of predicted values using the model.

  • target (ndarray) -- an array of the true values.

प्रदत्त :

An array with values of the loss function of the shape (N, 1).

उभारता है :

QiskitMachineLearningError -- shapes of predict and target do not match

प्रदत्त प्रकार :


gradient(predict, target)[स्रोत]#

Assume softmax is used, and target vector may or may not be one-hot encoding

प्रदत्त प्रकार :