com.intel.analytics.zoo.pipeline.api.keras.objectives
Boolean. Whether to accept log-probabilities or probabilities as input. Default is false and inputs should be probabilities.
Boolean. Whether target labels start from 0. Default is true. If false, labels start from 1.
Tensor. Weights of each class if you have an unbalanced training set. Default is null.
Boolean. Whether losses are averaged over observations for each mini-batch. Default is true. If false, the losses are instead summed for each mini-batch.
Integer. If the target is set to this value, the training process will skip this sample. In other words, the forward process will return zero output and the backward process will also return zero gradInput. Default is -1.
Boolean.
Boolean. Whether to accept log-probabilities or probabilities as input. Default is false and inputs should be probabilities.
Integer.
Integer. If the target is set to this value, the training process will skip this sample. In other words, the forward process will return zero output and the backward process will also return zero gradInput. Default is -1.
Boolean.
Boolean. Whether losses are averaged over observations for each mini-batch. Default is true. If false, the losses are instead summed for each mini-batch.
Tensor.
Tensor. Weights of each class if you have an unbalanced training set. Default is null.
Boolean.
Boolean. Whether target labels start from 0. Default is true. If false, labels start from 1.
A loss often used in multi-class classification problems with SoftMax as the last layer of the neural network.
By default, input(y_pred) is supposed to be probabilities of each class, and target(y_true) is supposed to be the class label starting from 0.