Computes log sigmoid of the input tf.Tensor element-wise: logSigmoid(x). For numerical stability, we use -tf.softplus(-x).
tf.Tensor
logSigmoid(x)
-tf.softplus(-x)
const x = tf.tensor1d([0, 1, -1, .7]);x.logSigmoid().print(); // or tf.logSigmoid(x) Copy
const x = tf.tensor1d([0, 1, -1, .7]);x.logSigmoid().print(); // or tf.logSigmoid(x)
The input tensor.
Generated using TypeDoc
Computes log sigmoid of the input
tf.Tensorelement-wise:logSigmoid(x). For numerical stability, we use-tf.softplus(-x).