mxnet.gluon.nn.Flatten¶
-
class
mxnet.gluon.nn.Flatten(**kwargs)[source]¶ Flattens the input to two dimensional.
- Inputs:
data: input tensor with arbitrary shape (N, x1, x2, …, xn)
- Output:
out: 2D tensor with shape: (N, x1 cdot x2 cdot … cdot xn)
Methods
__init__(**kwargs)Initialize self.
apply(fn)Applies
fnrecursively to every child block as well as self.cast(dtype)Cast this Block to use another data type.
collect_params([select])Returns a
ParameterDictcontaining thisBlockand all of its children’s Parameters(default), also can returns the selectParameterDictwhich match some given regular expressions.export(path[, epoch])Export HybridBlock to json format that can be loaded by SymbolBlock.imports, mxnet.mod.Module or the C++ interface.
forward(x, *args)Defines the forward computation.
hybrid_forward(F, x)Overrides to construct symbolic graph for this Block.
hybridize([active])Activates or deactivates
HybridBlocks recursively.infer_shape(*args)Infers shape of Parameters from inputs.
infer_type(*args)Infers data type of Parameters from inputs.
initialize([init, ctx, verbose, force_reinit])Initializes
Parameters of thisBlockand its children.load_parameters(filename[, ctx, …])Load parameters from file previously saved by save_parameters.
load_params(filename[, ctx, allow_missing, …])[Deprecated] Please use load_parameters.
name_scope()Returns a name space object managing a child
Blockand parameter names.register_child(block[, name])Registers block as a child of self.
register_forward_hook(hook)Registers a forward hook on the block.
register_forward_pre_hook(hook)Registers a forward pre-hook on the block.
save_parameters(filename)Save parameters to file.
save_params(filename)[Deprecated] Please use save_parameters.
summary(*inputs)Print the summary of the model’s output and parameters.
Attributes
nameName of this
Block, without ‘_’ in the end.paramsReturns this
Block’s parameter dictionary (does not include its children’s parameters).prefixPrefix of this
Block.