chainer.Function¶
-
class
chainer.
Function
[source]¶ Function on variables with backpropagation ability.
All function implementations defined in
chainer.functions
inherit this class.The main feature of this class is keeping track of function applications as a backward graph. When a function is applied to
Variable
objects, itsforward()
method is called ondata
fields of input variables, and at the same time it chains references from output variable nodes to the function and from the function to its input nodes.Note
As of v2.0, the input/output variables and their corresponding variable nodes in the graph are distinguished. Function acts like a function on
Variable
objects that returnsVariable
objects as outputs, whereas these objects do not appear directly in the graph. Instead, their correspondingVariableNode
objects are inserted to the graph.Note
As of v1.5, a function instance cannot be used twice in any computational graphs. In order to reuse a function object multiple times, use
copy.copy()
before the function applications to make a copy of the instance.This restriction also means that we cannot make a stateful function anymore. For example, it is now not allowed to let a function hold parameters. Define a function as a pure (stateless) procedure, and use
Link
to combine it with parameter variables.Example
Let
x
an instance ofVariable
andf
an instance ofFunction
taking only one argument. Then a line>>> import numpy, chainer, chainer.functions as F >>> x = chainer.Variable(numpy.zeros(10)) >>> f = F.Identity() >>> y = f(x)
computes a new variable
y
and creates backward references. Actually, backward references are set as per the following diagram:x.node <--- f <--- y.node
If an application of another function
g
occurs as>>> g = F.Identity() >>> z = g(x)
then the graph grows with a branch:
|--- f <--- y.node x.node <-+ |--- g <--- z.node
Note that the branching is correctly managed on backward computation, i.e. the gradients from
f
andg
are accumulated to the gradient ofx
.Every function implementation should provide
forward_cpu()
,forward_gpu()
,backward_cpu()
andbackward_gpu()
. Alternatively, one can provideforward()
andbackward()
instead of separate methods. Backward methods have default implementations that just returnNone
, which indicates that the function is non- differentiable.For functions that do not need a part of inputs in backward computation, there is a way to possibly reduce the memory consumption by quickly releasing the input arrays after the forward propagation. This is done by calling
retain_inputs()
from inside offorward()
(includingforward_cpu()
andforward_gpu()
). See the documentation ofretain_inputs()
for details.For functions that need a part of outputs in backward computation, it is strongly recommended to call
retain_outputs()
from inside offorward()
(includingforward_cpu()
andforward_gpu()
). It marks the specified output variable nodes to retain the data. The retained data can be accessed byoutput_arrays
property.Variables: - inputs – A tuple or list of input variables.
- outputs – A tuple or list of output variables.
- output_data – A tuple of retained output arrays. It has the same length
as
outputs
. The data of variables that are not retained are set toNone
. Seeretain_outputs()
for details.
Methods
-
__call__
(*inputs)[source]¶ Applies forward propagation with chaining backward references.
Basic behavior is expressed in documentation of
Function
class.Note
If the
data
attribute of input variables exist on GPU device, then, before it callsforward()
method, the appropriate device is selected, so in most cases implementers do not need to take care of device selection.Parameters: inputs – Tuple of input Variable
,numpy.ndarray
orcupy.ndarray
objects. If the input is annumpy.ndarray
or acupy.ndarray
, it is automatically wrapped withVariable
.Returns: One Variable
object or a tuple of multipleVariable
objects.
-
add_hook
(hook, name=None)[source]¶ Registers the function hook.
Parameters: - hook (FunctionHook) – Function hook to be registered.
- name (str) – Name of the function hook.
name must be unique among function hooks
registered to the function. If
None
, default name of the function hook is used.
-
backward
(inputs, grad_outputs)[source]¶ Applies backprop to output gradient arrays.
It delegates the procedure to
backward_cpu()
orbackward_gpu()
by default. Which it selects is determined by the type of input arrays and output gradient arrays. Implementations ofFunction
must implement either CPU/GPU methods or this method, if the function is intended to be backprop-ed.Parameters: - inputs – Tuple of input arrays.
- grad_outputs – Tuple of output gradient arrays.
Returns: Tuple of input gradient arrays. Some or all of them can be
None
, if the function is not differentiable on inputs.Return type: Warning
Implementations of
Function
must take care that the return value must be a tuple even if it returns only one array.
-
backward_cpu
(inputs, grad_outputs)[source]¶ Applies backprop to output gradient arrays on CPU.
Parameters: - inputs – Tuple of input
numpy.ndarray
object(s). - grad_outputs – Tuple of output gradient
numpy.ndarray
object(s).
Returns: Tuple of input gradient
numpy.ndarray
object(s). Some or all of them can beNone
, if the function is not differentiable on corresponding inputs.Return type: Warning
Implementations of
Function
must take care that the return value must be a tuple even if it returns only one array.- inputs – Tuple of input
-
backward_gpu
(inputs, grad_outputs)[source]¶ Applies backprop to output gradient arrays on GPU.
Parameters: - inputs – Tuple of input
cupy.ndarray
object(s). - grad_outputs – Tuple of output gradient
cupy.ndarray
object(s).
Returns: Tuple of input gradient
cupy.ndarray
object(s). Some or all of them can beNone
, if the function is not differentiable on corresponding inputs.Return type: Warning
Implementations of
Function
must take care that the return value must be a tuple even if it returns only one array.- inputs – Tuple of input
-
check_type_forward
(in_types)[source]¶ Checks types of input data before forward propagation.
Before
forward()
is called, this function is called. You need to validate types of input data in this function using the type checking utilities.Parameters: in_types (TypeInfoTuple) – The type information of input data for forward()
.
-
delete_hook
(name)[source]¶ Unregisters the function hook.
Parameters: name (str) – the name of the function hook to be unregistered.
-
forward
(inputs)[source]¶ Applies forward propagation to input arrays.
It delegates the procedure to
forward_cpu()
orforward_gpu()
by default. Which it selects is determined by the type of input arrays. Implementations ofFunction
must implement either CPU/GPU methods or this method.Parameters: inputs – Tuple of input array(s). Returns: Tuple of output array(s). Warning
Implementations of
Function
must take care that the return value must be a tuple even if it returns only one array.
-
forward_cpu
(inputs)[source]¶ Applies forward propagation to input arrays on CPU.
Parameters: inputs – Tuple of numpy.ndarray
object(s).Returns: Tuple of numpy.ndarray
object(s).Return type: tuple Warning
Implementations of
Function
must take care that the return value must be a tuple even if it returns only one array.
-
forward_gpu
(inputs)[source]¶ Applies forward propagation to input arrays on GPU.
Parameters: inputs – Tuple of cupy.ndarray
object(s).Returns: Tuple of cupy.ndarray
object(s).Return type: tuple Warning
Implementations of
Function
must take care that the return value must be a tuple even if it returns only one array.
-
retain_inputs
(indexes)[source]¶ Lets specified input variable nodes keep data arrays.
By calling this method from
forward()
, the function can specify which inputs are required for backprop.If this method is not called, the function keeps all input arrays. If you want to release all input arrays, call this method by passing an empty sequence.
Note that this method must not be called from the outside of forward method.
Parameters: indexes (iterable of int) – Indexes of input variables that the function does not require for backprop.
-
retain_outputs
(indexes, retain_after_backward=False)[source]¶ Lets specified output variable nodes keep data arrays.
By calling this method from
forward()
, the function can specify which outputs are required for backprop. If this method is not called, any output variables are not marked to keep the data array at the point of returning from__call__()
. The retained arrays are stored tooutput_data
.Note
It is STRONGLY RECOMMENDED to use this method if the function requires some or all output arrays in backprop. The function can also use output arrays just by keeping references to them directly, whereas it might influence on the performance of later function applications to the output variables.
Note that this method must not be called from the outside of forward method.
Parameters: - indexes (iterable of int) – Indexes of input variables that the function does not require for backprop.
- retain_after_backward (bool) – If
True
, a reference to the outputs will remain after the backprop of the function is over. IfFalse
, the reference will be deleted.
-
unchain
()[source]¶ Purges in/out nodes and this function itself from the graph.
This method is called from
Variable.unchain_backward()
method.
Attributes
-
label
¶ Short text that represents the function.
The default implementation returns its type name. Each function should override it to give more information.
-
local_function_hooks
¶ Ordered Dictionary of registered function hooks.
Contrary to
chainer.thread_local.function_hooks
, which registers its elements to all functions, Function hooks in this property is specific to this function.
-
rank
= 0¶
-
stack
¶