Сохраните дату! Google I / O возвращается 18-20 мая Зарегистрируйтесь сейчас


Computes softmax activations.

Used in the notebooks

Used in the guide Used in the tutorials

This function performs the equivalent of

softmax = tf.exp(logits) / tf.reduce_sum(tf.exp(logits), axis)

logits A non-empty Tensor. Must be one of the following types: half, float32, float64.
axis The dimension softmax would be performed on. The default is -1 which indicates the last dimension.
name A name for the operation (optional).

A Tensor. Has the same type and shape as logits.

InvalidArgumentError if logits is empty or axis is beyond the last dimension of logits.