# Module: tf.contrib.nn

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/contrib/nn/__init__.py) |

Module for variants of ops in tf.nn.

## Functions

[`alpha_dropout(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/alpha_dropout): Computes alpha dropout.

[`conv1d_transpose(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/nn/conv1d_transpose): The transpose of `conv1d`.

[`deprecated_flipped_sigmoid_cross_entropy_with_logits(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/deprecated_flipped_sigmoid_cross_entropy_with_logits): Computes sigmoid cross entropy given `logits`.

[`deprecated_flipped_softmax_cross_entropy_with_logits(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/deprecated_flipped_softmax_cross_entropy_with_logits): Computes softmax cross entropy between `logits` and `labels`.

[`deprecated_flipped_sparse_softmax_cross_entropy_with_logits(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/deprecated_flipped_sparse_softmax_cross_entropy_with_logits): Computes sparse softmax cross entropy between `logits` and `labels`.

[`nth_element(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/nth_element): Finds values of the `n`-th smallest value for the last dimension.

[`rank_sampled_softmax_loss(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/rank_sampled_softmax_loss): Computes softmax loss using rank-based adaptive resampling.

[`sampled_sparse_softmax_loss(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/sampled_sparse_softmax_loss): Computes and returns the sampled sparse softmax training loss.

[`scaled_softplus(...)`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/contrib/nn/scaled_softplus): Returns `y = alpha * ln(1 + exp(x / alpha))` or `min(y, clip)`.