tf.abs(x, name=None) Computes the absolute value of a tensor. Given a tensor of real numbers x, this operation returns a tensor containing the absolute value of each element in x. For example, if x is an input element and y is an output element, this operation computes \(y = |x|\). See tf.complex_abs() to compute the absolute value of a complex number. Args: x: A Tensor or SparseTensor of type float32, float64, int32, or int64. name: A name for the operation (optional). Returns: A Tensor o

Contents Neural Network RNN CellsBase interface for all RNN Cellsclass tf.nn.rnn_cell.RNNCell RNN Cells for use with TensorFlow's core RNN methodsclass tf.nn.rnn_cell.BasicRNNCell class tf.nn.rnn_cell.BasicLSTMCell class tf.nn.rnn_cell.GRUCell class tf.nn.rnn_cell.LSTMCell Classes storing split RNNCell stateclass tf.nn.rnn_cell.LSTMStateTuple RNN Cell wrappers (RNNCells that wrap other RNNCells)class tf.nn.rnn_cell.MultiRNNCell class tf.nn.rnn_cell.DropoutWrapper class tf.nn.rnn_cell.Embedd

KL[q || p] If log_p(z) = Log[p(z)] for distribution p, this Op approximates the negative Kullback-Leibler divergence. elbo_ratio(log_p, q, n=100) = -1 * KL[q || p], KL[q || p] = E[ Log[q(Z)] - Log[p(Z)] ] Note that if p is a Distribution, then distributions.kl(q, p) may be defined and available as an exact result.

Contents Metrics (contrib)Ops for evaluation metrics and summary statistics.API Metric Ops tf.contrib.metrics.streaming_accuracy(predictions, labels, weights=None, metrics_collections=None, updates_collections=None, name=None) tf.contrib.metrics.streaming_mean(values, weights=None, metrics_collections=None, updates_collections=None, name=None) tf.contrib.metrics.streaming_recall(*args, **kwargs) tf.contrib.metrics.streaming_precision(*args, **kwargs) tf.contrib.metrics.streaming_auc(predictio

Contents Metrics (contrib)Ops for evaluation metrics and summary statistics.API Metric Ops tf.contrib.metrics.streaming_accuracy(predictions, labels, weights=None, metrics_collections=None, updates_collections=None, name=None) tf.contrib.metrics.streaming_mean(values, weights=None, metrics_collections=None, updates_collections=None, name=None) tf.contrib.metrics.streaming_recall(*args, **kwargs) tf.contrib.metrics.streaming_precision(*args, **kwargs) tf.contrib.metrics.streaming_auc(predictio