tf.contrib.layers.safe_embedding_lookup_sparse(embedding_weights, sparse_ids, sparse_weights=None, combiner=None, default_id=None, name=None, partition_strategy='div')
tf.contrib.layers.avg_pool2d(*args, **kwargs) Adds a 2D average pooling op. It is assumed that
tf.contrib.layers.one_hot_encoding(*args, **kwargs) Transform numeric labels into onehot_labels using tf.one_hot.
tf.contrib.layers.summarize_tensor(tensor, tag=None) Summarize a tensor using a suitable summary type. This
tf.contrib.layers.repeat(inputs, repetitions, layer, *args, **kwargs) Applies the same layer with the same arguments repeatedly
tf.contrib.layers.apply_regularization(regularizer, weights_list=None) Returns the summed penalty by applying regularizer
tf.contrib.layers.separable_convolution2d(*args, **kwargs) Adds a depth-separable 2D convolution with optional batch_norm layer
tf.contrib.layers.unit_norm(*args, **kwargs) Normalizes the given input across the specified dimension to unit length.
tf.contrib.layers.flatten(*args, **kwargs) Flattens the input while maintaining the batch_size. Assumes
tf.contrib.layers.l1_regularizer(scale, scope=None) Returns a function that can be used to apply L1 regularization to weights
Page 1 of 3