class MXNet::Executor
- MXNet::Executor
- Reference
- Object
Overview
Executor
provides efficient symbolic graph
execution and optimization.
Defined in:
mxnet/executor.crConstructors
Instance Method Summary
-
#backward(out_grads : Array(MXNet::NDArray) = [] of MXNet::NDArray, is_train : Bool = true)
Do backward pass to calculate the gradients.
- #finalize
-
#forward(is_train : Bool = false)
Calculate the outputs specified by the bound symbol.
Constructor Detail
Instance Method Detail
Do backward pass to calculate the gradients.
Parameters
- out_grads (
NDArray
, optional) Gradients on the outputs to be propagated back. This parameter is only needed whenSymbol#bind
is called on outputs that are not a loss function. - is_train (
Bool
, defaulttrue
) Whether this#backward
call is for training. Note, in rare cases you may want to call#backward
withis_train: false
to calculate gradients during inference.
def forward(is_train : Bool = false)
#