keras: loss_binary_crossentropy – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

loss_binary_crossentropy

Computes the binary crossentropy loss.

Computes the binary crossentropy loss.

loss_binary_crossentropy(
  y_true,
  y_pred,
  from_logits = FALSE,
  label_smoothing = 0
)

`y_true`	True labels (Tensor)
`y_pred`	Predictions (Tensor of the same shape as `y_true`)
`from_logits`	Whether `y_pred` is expected to be a logits tensor. By default, we assume that y_pred encodes a probability distribution.
`label_smoothing`	numeric between 0 and 1. If > 0 then smooth the labels.