View source on GitHub
|
Module for variants of ops in tf.nn.
Functions
alpha_dropout(...): Computes alpha dropout.
conv1d_transpose(...): The transpose of conv1d.
deprecated_flipped_sigmoid_cross_entropy_with_logits(...): Computes sigmoid cross entropy given logits.
deprecated_flipped_softmax_cross_entropy_with_logits(...): Computes softmax cross entropy between logits and labels.
deprecated_flipped_sparse_softmax_cross_entropy_with_logits(...): Computes sparse softmax cross entropy between logits and labels.
nth_element(...): Finds values of the n-th smallest value for the last dimension.
rank_sampled_softmax_loss(...): Computes softmax loss using rank-based adaptive resampling.
sampled_sparse_softmax_loss(...): Computes and returns the sampled sparse softmax training loss.
scaled_softplus(...): Returns y = alpha * ln(1 + exp(x / alpha)) or min(y, clip).