* \brief Transpose a vector or a matrix * \details This raises an invalid_argument exception on tensors with more than 2 dimensions * \return The

Adds parameters.

this calls the rule-specific updates over all updated parameters

* \brief Constructor * * \param m ParameterCollection to be trained * \param learning_rate Initial learning rate */

Loads parameter.

Sets dropout.

* \brief remove trailing dimensions of 1 * \details iterate all the dimensions of Dim, stop at last dimension of 1 * \return truncated dimension

* \brief Get the matrix for a particular batch * \details Automatically broadcasting if the size is zero. * * \param bid Batch id requested * \return

Reset the graph to a newly created state.

Returns the gradient of the expression.

* \brief Total size of a batch * \return Batch size * size of a batch */

sbdm hash

Returns the number of dimensions. # Examples ``` # use dynet::Dim; let dim = Dim::from([2, 3, 1, 1, 1, 5]); assert_eq!(dim.ndims(), 6); ```

Sets dropout masks at the beginning of a sequence for a specific batch size.

Adds another timestep by reading in the variable x.

Computes backward gradients from the front-most evaluated node.

Returns the dimension of the expression.

* \brief Number of arguments to the function * \return Arity of the function */