Russian
Языки
English
Bengali
French
Hindi
Italian
Japanese
Korean
Malayalam
Russian
Spanish
Tamil
Turkish
Vietnamese
Shortcuts



CrossEntropySigmoidLoss.gradient

CrossEntropySigmoidLoss.gradient(predict, target)[исходный код]

An abstract method for computing the gradient. Inputs are expected in a shape of (N, *). Where N is a number of samples. Gradient is computed for each sample individually.

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

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

Тип результата

ndarray

Результат

An array with gradient values of the shape (N, *). The output shape depends on the loss function.

Исключение

QiskitMachineLearningError – shapes of predict and target do not match.