Table Of Contents
Table Of Contents

Block

class mxnet.gluon.nn.Block(prefix=None, params=None)[source]

Base class for all neural network layers and models. Your models should subclass this class.

Block can be nested recursively in a tree structure. You can create and assign child Block as regular attributes:

from mxnet.gluon import Block, nn
from mxnet import ndarray as F

class Model(Block):
    def __init__(self, **kwargs):
        super(Model, self).__init__(**kwargs)
        # use name_scope to give child Blocks appropriate names.
        with self.name_scope():
            self.dense0 = nn.Dense(20)
            self.dense1 = nn.Dense(20)

    def forward(self, x):
        x = F.relu(self.dense0(x))
        return F.relu(self.dense1(x))

model = Model()
model.initialize(ctx=mx.cpu(0))
model(F.zeros((10, 10), ctx=mx.cpu(0)))

Child Block assigned this way will be registered and collect_params() will collect their Parameters recursively. You can also manually register child blocks with register_child().

Parameters
  • prefix (str) – Prefix acts like a name space. All children blocks created in parent block’s name_scope() will have parent block’s prefix in their name. Please refer to naming tutorial for more info on prefix and naming.

  • params (ParameterDict or None) –

    ParameterDict for sharing weights with the new Block. For example, if you want dense1 to share dense0’s weights, you can do:

    dense0 = nn.Dense(20)
    dense1 = nn.Dense(20, params=dense0.collect_params())
    

Handle model parameters:

Block.initialize([init, ctx, verbose, …])

Initializes Parameter s of this Block and its children.

Block.save_parameters(filename)

Save parameters to file.

Block.load_parameters(filename[, ctx, …])

Load parameters from file previously saved by save_parameters.

Block.collect_params([select])

Returns a ParameterDict containing this Block and all of its children’s Parameters(default), also can returns the select ParameterDict which match some given regular expressions.

Block.cast(dtype)

Cast this Block to use another data type.

Block.apply(fn)

Applies fn recursively to every child block as well as self.

Run computation

Block.forward(*args)

Overrides to implement forward computation using NDArray.

Debugging

Block.summary(*inputs)

Print the summary of the model’s output and parameters.

Advanced API for customization

Block.name_scope()

Returns a name space object managing a child Block and parameter names.

Block.register_child(block[, name])

Registers block as a child of self.

Block.register_forward_hook(hook)

Registers a forward hook on the block.

Block.register_forward_pre_hook(hook)

Registers a forward pre-hook on the block.

Attributes

Block.name

Name of this Block, without ‘_’ in the end.

Block.params

Returns this Block’s parameter dictionary (does not include its children’s parameters).

Block.prefix

Prefix of this Block.

Warning

The following two APIs are deprecated since v1.2.1.

Block.save_params(filename)

[Deprecated] Please use save_parameters.

Block.load_params(filename[, ctx, …])

[Deprecated] Please use load_parameters.

prefix

Prefix of this Block.

name

Name of this Block, without ‘_’ in the end.

name_scope()[source]

Returns a name space object managing a child Block and parameter names. Should be used within a with statement:

with self.name_scope():
    self.dense = nn.Dense(20)

Please refer to naming tutorial for more info on prefix and naming.

params

Returns this Block’s parameter dictionary (does not include its children’s parameters).

collect_params(select=None)[source]

Returns a ParameterDict containing this Block and all of its children’s Parameters(default), also can returns the select ParameterDict which match some given regular expressions.

For example, collect the specified parameters in [‘conv1_weight’, ‘conv1_bias’, ‘fc_weight’, ‘fc_bias’]:

model.collect_params('conv1_weight|conv1_bias|fc_weight|fc_bias')

or collect all parameters whose names end with ‘weight’ or ‘bias’, this can be done using regular expressions:

model.collect_params('.*weight|.*bias')
Parameters

select (str) – regular expressions

Returns

Return type

The selected ParameterDict

save_parameters(filename)[source]

Save parameters to file.

Saved parameters can only be loaded with load_parameters. Note that this method only saves parameters, not model structure. If you want to save model structures, please use HybridBlock.export().

Parameters

filename (str) – Path to file.

References

Saving and Loading Gluon Models

save_params(filename)[source]

[Deprecated] Please use save_parameters. Note that if you want load from SymbolBlock later, please use export instead.

Save parameters to file.

filenamestr

Path to file.

load_parameters(filename, ctx=None, allow_missing=False, ignore_extra=False)[source]

Load parameters from file previously saved by save_parameters.

Parameters
  • filename (str) – Path to parameter file.

  • ctx (Context or list of Context, default cpu()) – Context(s) to initialize loaded parameters on.

  • allow_missing (bool, default False) – Whether to silently skip loading parameters not represents in the file.

  • ignore_extra (bool, default False) – Whether to silently ignore parameters from the file that are not present in this Block.

References

Saving and Loading Gluon Models

load_params(filename, ctx=None, allow_missing=False, ignore_extra=False)[source]

[Deprecated] Please use load_parameters.

Load parameters from file.

filenamestr

Path to parameter file.

ctxContext or list of Context, default cpu()

Context(s) to initialize loaded parameters on.

allow_missingbool, default False

Whether to silently skip loading parameters not represents in the file.

ignore_extrabool, default False

Whether to silently ignore parameters from the file that are not present in this Block.

register_child(block, name=None)[source]

Registers block as a child of self. Block s assigned to self as attributes will be registered automatically.

register_forward_pre_hook(hook)[source]

Registers a forward pre-hook on the block.

The hook function is called immediately before forward(). It should not modify the input or output.

Parameters

hook (callable) – The forward hook function of form hook(block, input) -> None.

Returns

Return type

mxnet.gluon.utils.HookHandle

register_forward_hook(hook)[source]

Registers a forward hook on the block.

The hook function is called immediately after forward(). It should not modify the input or output.

Parameters

hook (callable) – The forward hook function of form hook(block, input, output) -> None.

Returns

Return type

mxnet.gluon.utils.HookHandle

apply(fn)[source]

Applies fn recursively to every child block as well as self.

Parameters

fn (callable) – Function to be applied to each submodule, of form fn(block).

Returns

Return type

this block

initialize(init=<mxnet.initializer.Uniform object>, ctx=None, verbose=False, force_reinit=False)[source]

Initializes Parameter s of this Block and its children. Equivalent to block.collect_params().initialize(...)

Parameters
  • init (Initializer) – Global default Initializer to be used when Parameter.init() is None. Otherwise, Parameter.init() takes precedence.

  • ctx (Context or list of Context) – Keeps a copy of Parameters on one or many context(s).

  • verbose (bool, default False) – Whether to verbosely print out details on initialization.

  • force_reinit (bool, default False) – Whether to force re-initialization if parameter is already initialized.

hybridize(active=True, **kwargs)[source]

Activates or deactivates HybridBlock s recursively. Has no effect on non-hybrid children.

Parameters
  • active (bool, default True) – Whether to turn hybrid on or off.

  • static_alloc (bool, default False) – Statically allocate memory to improve speed. Memory usage may increase.

  • static_shape (bool, default False) – Optimize for invariant input shapes between iterations. Must also set static_alloc to True. Change of input shapes is still allowed but slower.

cast(dtype)[source]

Cast this Block to use another data type.

Parameters

dtype (str or numpy.dtype) – The new data type.

forward(*args)[source]

Overrides to implement forward computation using NDArray. Only accepts positional arguments.

Parameters

*args (list of NDArray) – Input tensors.

summary(*inputs)[source]

Print the summary of the model’s output and parameters.

The network must have been initialized, and must not have been hybridized.

Parameters

inputs (object) – Any input that the model supports. For any tensor in the input, only mxnet.ndarray.NDArray is supported.