ReLU6¶

class paddle.sparse.nn. ReLU6 ( name=None ) [source]

Sparse ReLU6 Activation, requiring x to be a SparseCooTensor or SparseCsrTensor.

\[ReLU6(x) = min(max(0,x), 6)\]

Parameters

name (str, optional) – Name for the operation (optional, default is None). For more information, please refer to Name.

Shape:

• input: Sparse Tensor with any shape.

• output: Sparse Tensor with the same shape as input.

Examples

>>> import paddle

>>> dense_x = paddle.to_tensor([-2., 0., 8.])
>>> sparse_x = dense_x.to_sparse_coo(1)
>>> relu6 = paddle.sparse.nn.ReLU6()
>>> out = relu6(sparse_x)

forward ( x )

forward¶

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

• *inputs (tuple) – unpacked tuple arguments

• **kwargs (dict) – unpacked dict arguments

extra_repr ( )

extra_repr¶

Extra representation of this layer, you can have custom implementation of your own layer.

add_parameter ( name, parameter )

add_parameter¶

Adds a Parameter instance.

Added parameter can be accessed by self.name

Parameters

• name (str) – name of this sublayer.

• parameter (Parameter) – an instance of Parameter.

Returns

Parameter, the parameter passed in.

Examples

>>> import paddle
>>> paddle.seed(100)

>>> class MyLayer(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self._linear = paddle.nn.Linear(1, 1)
...         w_tmp = self.create_parameter([1,1])
...         self.add_parameter("w_tmp", w_tmp)
...
...     def forward(self, input):
...         return self._linear(input)
...
>>> mylayer = MyLayer()
>>> for name, param in mylayer.named_parameters():
...     print(name, param)
w_tmp Parameter containing:
Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[-1.01448846]])
_linear.weight Parameter containing:
Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[0.18551230]])
_linear.bias Parameter containing:
Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=False,
[0.])

add_sublayer ( name, sublayer )

add_sublayer¶

Adds a sub Layer instance.

Added sublayer can be accessed by self.name

Parameters

• name (str) – name of this sublayer.

• sublayer (Layer) – an instance of Layer.

Returns

Layer, the sublayer passed in.

Examples

>>> import paddle

>>> class MySequential(paddle.nn.Layer):
...     def __init__(self, *layers):
...         super().__init__()
...         if len(layers) > 0 and isinstance(layers[0], tuple):
...             for name, layer in layers:
...                 self.add_sublayer(name, layer)
...         else:
...             for idx, layer in enumerate(layers):
...                 self.add_sublayer(str(idx), layer)
...
...     def forward(self, input):
...         for layer in self._sub_layers.values():
...             input = layer(input)
...         return input
...
>>> fc1 = paddle.nn.Linear(10, 3)
>>> fc2 = paddle.nn.Linear(3, 10, bias_attr=False)
>>> model = MySequential(fc1, fc2)
>>> for prefix, layer in model.named_sublayers():
...     print(prefix, layer)
0 Linear(in_features=10, out_features=3, dtype=float32)
1 Linear(in_features=3, out_features=10, dtype=float32)

apply ( fn )

apply¶

Applies fn recursively to every sublayer (as returned by .sublayers()) as well as self. Typical use includes initializing the parameters of a model.

Parameters

fn (function) – a function to be applied to each sublayer

Returns

Layer, self

Example::

>>> import paddle
>>> import paddle.nn as nn
>>> paddle.seed(2023)

>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))

>>> def init_weights(layer):
...     if type(layer) == nn.Linear:
...         print('before init weight:', layer.weight.numpy())
...         new_weight = paddle.full(shape=layer.weight.shape, dtype=layer.weight.dtype, fill_value=0.9)
...         layer.weight.set_value(new_weight)
...         print('after init weight:', layer.weight.numpy())
...
>>> net.apply(init_weights)

>>> print(net.state_dict())
before init weight: [[ 0.89611185  0.04935038]
                     [-0.5888344   0.99266374]]
after init weight: [[0.9 0.9]
                    [0.9 0.9]]
before init weight: [[-0.18615901 -0.22924072]
                     [ 1.1517721   0.59859073]]
after init weight: [[0.9 0.9]
                    [0.9 0.9]]
OrderedDict([('0.weight', Parameter containing:
Tensor(shape=[2, 2], dtype=float32, place=Place(cpu), stop_gradient=False,
[[0.89999998, 0.89999998],
 [0.89999998, 0.89999998]])), ('0.bias', Parameter containing:
Tensor(shape=[2], dtype=float32, place=Place(cpu), stop_gradient=False,
[0., 0.])), ('1.weight', Parameter containing:
Tensor(shape=[2, 2], dtype=float32, place=Place(cpu), stop_gradient=False,
[[0.89999998, 0.89999998],
 [0.89999998, 0.89999998]])), ('1.bias', Parameter containing:
Tensor(shape=[2], dtype=float32, place=Place(cpu), stop_gradient=False,
[0., 0.]))])

astype ( dtype=None )

astype¶

Casts all parameters and buffers to dtype and then return the Layer.

Parameters

dtype (str|paddle.dtype|numpy.dtype) – target data type of layer. If set str, it can be “bool”, “bfloat16”, “float16”, “float32”, “float64”, “int8”, “int16”, “int32”, “int64”, “uint8”, “complex64”, “complex128”. Default: None

Returns

Layer, self

Examples

>>> import paddle
>>> import paddle.nn as nn
>>> weight_attr = paddle.ParamAttr(name="weight",initializer=paddle.nn.initializer.Constant(value=1.5))
>>> bias_attr = paddle.ParamAttr(name="bias",initializer=paddle.nn.initializer.Constant(value=2.5))

>>> linear = paddle.nn.Linear(2, 2, weight_attr=weight_attr, bias_attr=bias_attr).to(device="cpu",dtype="float32")
>>> print(linear)
Linear(in_features=2, out_features=2, dtype=float32)
>>> print(linear.parameters())
[Parameter containing:
Tensor(shape=[2, 2], dtype=float32, place=Place(cpu), stop_gradient=False,
    [[1.50000000, 1.50000000],
        [1.50000000, 1.50000000]]), Parameter containing:
Tensor(shape=[2], dtype=float32, place=Place(cpu), stop_gradient=False,
    [2.50000000, 2.50000000])]

>>> linear=linear.astype("int8")
>>> print(linear)
Linear(in_features=2, out_features=2, dtype=paddle.int8)
>>> print(linear.parameters())
[Parameter containing:
Tensor(shape=[2, 2], dtype=int8, place=Place(cpu), stop_gradient=False,
    [[1, 1],
        [1, 1]]), Parameter containing:
Tensor(shape=[2], dtype=int8, place=Place(cpu), stop_gradient=False,
    [2, 2])]

bfloat16 ( excluded_layers=None )

bfloat16¶

Casts all floating point parameters and buffers to bfloat16 data type.

Note

nn.BatchNorm does not support bfloat16 weights, so it would not be converted by default.

Parameters

excluded_layers (nn.Layer|list|tuple|None, optional) – Specify the layers that need to be kept original data type. if excluded_layers is None, casts all floating point parameters and buffers except nn.BatchNorm. Default: None.

Returns

self

Return type

Layer

Examples

>>> 
>>> import paddle

>>> class Model(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self.linear = paddle.nn.Linear(1, 1)
...         self.dropout = paddle.nn.Dropout(p=0.5)
...
...     def forward(self, input):
...         out = self.linear(input)
...         out = self.dropout(out)
...         return out
...
>>> model = Model()
>>> model.bfloat16()
>>> #UserWarning: Paddle compiled by the user does not support bfloat16, so keep original data type.
Model(
    (linear): Linear(in_features=1, out_features=1, dtype=float32)
    (dropout): Dropout(p=0.5, axis=None, mode=upscale_in_train)
)

buffers ( include_sublayers=True )

buffers¶

Returns a list of all buffers from current layer and its sub-layers.

Parameters

include_sublayers (bool, optional) – Whether include the buffers of sublayers. If True, also include the buffers from sublayers. Default: True.

Returns

list of Tensor, a list of buffers.

Examples

>>> import numpy as np
>>> import paddle

>>> linear = paddle.nn.Linear(10, 3)
>>> value = np.array([0]).astype("float32")
>>> buffer = paddle.to_tensor(value)
>>> linear.register_buffer("buf_name", buffer, persistable=True)

>>> print(linear.buffers())
[Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
[0.])]

children ( )

children¶

Returns an iterator over immediate children layers.

Yields

Layer – a child layer

Examples

>>> import paddle

>>> linear1 = paddle.nn.Linear(10, 3)
>>> linear2 = paddle.nn.Linear(3, 10, bias_attr=False)
>>> model = paddle.nn.Sequential(linear1, linear2)

>>> layer_list = list(model.children())

>>> print(layer_list)
[Linear(in_features=10, out_features=3, dtype=float32), Linear(in_features=3, out_features=10, dtype=float32)]

clear_gradients ( set_to_zero=True )

clear_gradients¶

Clear the gradients of all parameters for this layer.

Parameters

set_to_zero (bool, optional) – Whether to set the trainable parameters’ gradients to zero or None. Default is True.

Returns

None

Examples

>>> import paddle
>>> import numpy as np

>>> value = np.arange(26).reshape(2, 13).astype("float32")
>>> a = paddle.to_tensor(value)
>>> linear = paddle.nn.Linear(13, 5)
>>> adam = paddle.optimizer.Adam(learning_rate=0.01,
...                              parameters=linear.parameters())
>>> out = linear(a)
>>> out.backward()
>>> adam.step()
>>> linear.clear_gradients()

create_parameter ( shape, attr=None, dtype=None, is_bias=False, default_initializer=None )

create_parameter¶

Create parameters for this layer.

Parameters

• shape (list) – Shape of the parameter. The data type in the list must be int.

• attr (ParamAttr, optional) – Parameter attribute of weight. Please refer to ParamAttr. Default: None.

• dtype (str, optional) – Data type of this parameter. If set str, it can be “bool”, “float16”, “float32”, “float64”, “int8”, “int16”, “int32”, “int64”, “uint8” or “uint16”. Default: “float32”.

• is_bias (bool, optional) – if this is a bias parameter. Default: False.

• default_initializer (Initializer, optional) – the default initializer for this parameter. If set None, default initializer will be set to paddle.nn.initializer.Xavier and paddle.nn.initializer.Constant for non-bias and bias parameter, respectively. Default: None.

Returns

Tensor, created parameter.

Examples

>>> import paddle
>>> paddle.seed(2023)

>>> class MyLayer(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self._linear = paddle.nn.Linear(1, 1)
...         w_tmp = self.create_parameter([1,1])
...         self.add_parameter("w_tmp", w_tmp)
...
...     def forward(self, input):
...         return self._linear(input)
...
>>> mylayer = MyLayer()
>>> for name, param in mylayer.named_parameters():
...     print(name, param)      # will print w_tmp,_linear.weight,_linear.bias
w_tmp Parameter containing:
Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[0.06979191]])
_linear.weight Parameter containing:
Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[1.26729357]])
_linear.bias Parameter containing:
Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=False,
[0.])

create_tensor ( name=None, persistable=None, dtype=None )

create_tensor¶

Create Tensor for this layer.

Parameters

• name (str, optional) – name of the tensor. Please refer to Name . Default: None.

• persistable (bool, optional) – if set this tensor persistable. Default: False.

• dtype (str, optional) – data type of this parameter. If set str, it can be “bool”, “float16”, “float32”, “float64”, “int8”, “int16”, “int32”, “int64”, “uint8” or “uint16”. If set None, it will be “float32”. Default: None.

Returns

Tensor, created Tensor.

Examples

>>> import paddle

>>> class MyLinear(paddle.nn.Layer):
...     def __init__(self,
...                  in_features,
...                  out_features):
...         super().__init__()
...         self.linear = paddle.nn.Linear(10, 10)
...
...         self.back_var = self.create_tensor(name = "linear_tmp_0", dtype=self._dtype)
...
...     def forward(self, input):
...         out = self.linear(input)
...         paddle.assign(out, self.back_var)
...
...         return out

create_variable ( name=None, persistable=None, dtype=None )

create_variable¶

Warning

API “paddle.nn.layer.layers.create_variable” is deprecated since 2.0.0, and will be removed in future versions. Please use “paddle.nn.Layer.create_tensor” instead. Reason: New api in create_tensor, easier to use.

Create Tensor for this layer.

Parameters

• name (str, optional) – name of the tensor. Please refer to Name . Default: None

• persistable (bool, optional) – if set this tensor persistable. Default: False

• dtype (str, optional) – data type of this parameter. If set str, it can be “bool”, “float16”, “float32”, “float64”,”int8”, “int16”, “int32”, “int64”, “uint8” or “uint16”. If set None, it will be “float32”. Default: None

Returns

Tensor, created Tensor.

Examples

>>> import paddle

>>> class MyLinear(paddle.nn.Layer):
...     def __init__(self,
...                 in_features,
...                 out_features):
...         super().__init__()
...         self.linear = paddle.nn.Linear( 10, 10)
...
...         self.back_var = self.create_variable(name = "linear_tmp_0", dtype=self._dtype)
...
...     def forward(self, input):
...         out = self.linear(input)
...         paddle.assign( out, self.back_var)
...
...         return out

eval ( )

eval¶

Sets this Layer and all its sublayers to evaluation mode. This only effects certain modules like Dropout and BatchNorm.

Returns

None

Example::

>>> import paddle
>>> paddle.seed(100)
>>> class MyLayer(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self._linear = paddle.nn.Linear(1, 1)
...         self._dropout = paddle.nn.Dropout(p=0.5)
...
...     def forward(self, input):
...         temp = self._linear(input)
...         temp = self._dropout(temp)
...         return temp
...
>>> x = paddle.randn([10, 1], 'float32')
>>> mylayer = MyLayer()
>>> mylayer.eval()  # set mylayer._dropout to eval mode
>>> out = mylayer(x)
>>> print(out)
Tensor(shape=[10, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[-1.72439659],
 [ 0.31532824],
 [ 0.01192369],
 [-0.36912638],
 [-1.63426113],
 [-0.93169814],
 [ 0.32222399],
 [-1.61092973],
 [ 0.77209264],
 [-0.34038994]])

float ( excluded_layers=None )

float¶

Casts all floating point parameters and buffers to float data type.

Parameters

excluded_layers (nn.Layer|list|tuple|None, optional) – Specify the layers that need to be kept original data type. if excluded_layers is None, casts all floating point parameters and buffers. Default: None.

Returns

self

Return type

Layer

Examples

>>> import paddle

>>> class Model(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self.linear = paddle.nn.Linear(1, 1)
...         self.dropout = paddle.nn.Dropout(p=0.5)
...
...     def forward(self, input):
...         out = self.linear(input)
...         out = self.dropout(out)
...         return out
...
>>> model = Model()
>>> model.float()
Model(
    (linear): Linear(in_features=1, out_features=1, dtype=paddle.float32)
    (dropout): Dropout(p=0.5, axis=None, mode=upscale_in_train)
)

float16 ( excluded_layers=None )

float16¶

Casts all floating point parameters and buffers to float16 data type.

Note

nn.BatchNorm does not support bfloat16 weights, so it would not be converted by default.

Parameters

excluded_layers (nn.Layer|list|tuple|None, optional) – Specify the layers that need to be kept original data type. if excluded_layers is None, casts all floating point parameters and buffers except nn.BatchNorm. Default: None.

Returns

self

Return type

Layer

Examples

>>> 
>>> import paddle

>>> class Model(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self.linear = paddle.nn.Linear(1, 1)
...         self.dropout = paddle.nn.Dropout(p=0.5)
...
...     def forward(self, input):
...         out = self.linear(input)
...         out = self.dropout(out)
...         return out
...
>>> model = Model()
>>> model.float16()
Model(
    (linear): Linear(in_features=1, out_features=1, dtype=float32)
    (dropout): Dropout(p=0.5, axis=None, mode=upscale_in_train)
)

full_name ( )

full_name¶

Full name for this layer, composed by name_scope + “/” + MyLayer.__class__.__name__

Returns

str, full name of this layer.

Example::

>>> import paddle

>>> class LinearNet(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__(name_scope = "demo_linear_net")
...         self._linear = paddle.nn.Linear(1, 1)
...
...     def forward(self, x):
...         return self._linear(x)
...
>>> linear_net = LinearNet()
>>> print(linear_net.full_name())
demo_linear_net_0

load_dict ( state_dict, use_structured_name=True )

load_dict¶

Set parameters and persistable buffers from state_dict. All the parameters and buffers will be reset by the tensor in the state_dict

Parameters

• state_dict (dict) – Dict contains all the parameters and persistable buffers.

• use_structured_name (bool, optional) – If true, use structured name as key, otherwise, use parameter or buffer name as key. Default: True.

Returns

A list of str containing the missing keys unexpected_keys(list):A list of str containing the unexpected keys

Return type

missing_keys(list)

Examples

>>> import paddle

>>> emb = paddle.nn.Embedding(10, 10)

>>> state_dict = emb.state_dict()
>>> paddle.save(state_dict, "paddle_dy.pdparams")
>>> para_state_dict = paddle.load("paddle_dy.pdparams")
>>> emb.set_state_dict(para_state_dict)

named_buffers ( prefix='', include_sublayers=True )

named_buffers¶

Returns an iterator over all buffers in the Layer, yielding tuple of name and Tensor.

Parameters

• prefix (str, optional) – Prefix to prepend to all buffer names. Default: ‘’.

• include_sublayers (bool, optional) – Whether include the buffers of sublayers. If True, also include the named buffers from sublayers. Default: True.

Yields

(string, Tensor) – Tuple of name and tensor

Examples

>>> import numpy as np
>>> import paddle

>>> fc1 = paddle.nn.Linear(10, 3)
>>> buffer1 = paddle.to_tensor(np.array([0]).astype("float32"))
>>> # register a tensor as buffer by specific `persistable`
>>> fc1.register_buffer("buf_name_1", buffer1, persistable=True)

>>> fc2 = paddle.nn.Linear(3, 10)
>>> buffer2 = paddle.to_tensor(np.array([1]).astype("float32"))
>>> # register a buffer by assigning an attribute with Tensor.
>>> # The `persistable` can only be False by this way.
>>> fc2.buf_name_2 = buffer2

>>> model = paddle.nn.Sequential(fc1, fc2)

>>> # get all named buffers
>>> for name, buffer in model.named_buffers():
...     print(name, buffer)
0.buf_name_1 Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
[0.])
1.buf_name_2 Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
[1.])

named_children ( )

named_children¶

Returns an iterator over immediate children layers, yielding both the name of the layer as well as the layer itself.

Yields

(string, Layer) – Tuple containing a name and child layer

Examples

>>> import paddle

>>> linear1 = paddle.nn.Linear(10, 3)
>>> linear2 = paddle.nn.Linear(3, 10, bias_attr=False)
>>> model = paddle.nn.Sequential(linear1, linear2)
>>> for prefix, layer in model.named_children():
...     print(prefix, layer)
0 Linear(in_features=10, out_features=3, dtype=float32)
1 Linear(in_features=3, out_features=10, dtype=float32)

named_parameters ( prefix='', include_sublayers=True )

named_parameters¶

Returns an iterator over all parameters in the Layer, yielding tuple of name and parameter.

Parameters

• prefix (str, optional) – Prefix to prepend to all parameter names. Default: ‘’.

• include_sublayers (bool, optional) – Whether include the parameters of sublayers. If True, also include the named parameters from sublayers. Default: True.

Yields

(string, Parameter) – Tuple of name and Parameter

Examples

>>> import paddle
>>> paddle.seed(100)

>>> fc1 = paddle.nn.Linear(10, 3)
>>> fc2 = paddle.nn.Linear(3, 10, bias_attr=False)
>>> model = paddle.nn.Sequential(fc1, fc2)
>>> for name, param in model.named_parameters():
...     print(name, param)
0.weight Parameter containing:
Tensor(shape=[10, 3], dtype=float32, place=Place(cpu), stop_gradient=False,
[[ 0.07276392, -0.39791510, -0.66356444],
 [ 0.02143478, -0.18519843, -0.32485050],
 [-0.42249614,  0.08450919, -0.66838276],
 [ 0.38208580, -0.24303678,  0.55127048],
 [ 0.47745085,  0.62117910, -0.08336520],
 [-0.28653207,  0.47237599, -0.05868882],
 [-0.14385653,  0.29945642,  0.12832761],
 [-0.21237159,  0.38539791, -0.62760031],
 [ 0.02637231,  0.20621127,  0.43255770],
 [-0.19984481, -0.26259184, -0.29696006]])
0.bias Parameter containing:
Tensor(shape=[3], dtype=float32, place=Place(cpu), stop_gradient=False,
[0., 0., 0.])
1.weight Parameter containing:
Tensor(shape=[3, 10], dtype=float32, place=Place(cpu), stop_gradient=False,
[[ 0.01985580, -0.40268910,  0.41172385, -0.47249708, -0.09002256,
 -0.00533628, -0.52048630,  0.62360322,  0.20848787, -0.02033746],
 [ 0.58281910,  0.12841827,  0.12907702,  0.02325618, -0.07746267,
 0.31950659, -0.37924835, -0.59209681, -0.11732036, -0.58378261],
 [-0.62100595,  0.22293305,  0.28229684, -0.03687060, -0.59323978,
 0.08411229,  0.53275704,  0.40431368,  0.03171402, -0.17922515]])

named_sublayers ( prefix='', include_self=False, layers_set=None )

named_sublayers¶

Returns an iterator over all sublayers in the Layer, yielding tuple of name and sublayer. The duplicate sublayer will only be yielded once.

Parameters

• prefix (str, optional) – Prefix to prepend to all parameter names. Default: ‘’.

• include_self (bool, optional) – Whether include the Layer itself. Default: False.

• layers_set (set, optional) – The set to record duplicate sublayers. Default: None.

Yields

(string, Layer) – Tuple of name and Layer

Examples

>>> import paddle

>>> fc1 = paddle.nn.Linear(10, 3)
>>> fc2 = paddle.nn.Linear(3, 10, bias_attr=False)
>>> model = paddle.nn.Sequential(fc1, fc2)
>>> for prefix, layer in model.named_sublayers():
...     print(prefix, layer)
0 Linear(in_features=10, out_features=3, dtype=float32)
1 Linear(in_features=3, out_features=10, dtype=float32)

parameters ( include_sublayers=True )

parameters¶

Returns a list of all Parameters from current layer and its sub-layers.

Parameters

include_sublayers (bool, optional) – Whether to return the parameters of the sublayer. If True, the returned list contains the parameters of the sublayer. Default: True.

Returns

list of Tensor, a list of Parameters.

Examples

>>> import paddle
>>> paddle.seed(100)

>>> linear = paddle.nn.Linear(1, 1)
>>> print(linear.parameters())
[Parameter containing:
Tensor(shape=[1, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[0.18551230]]), Parameter containing:
Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=False,
[0.])]

register_buffer ( name, tensor, persistable=True )

register_buffer¶

Registers a tensor as buffer into the layer.

buffer is a non-trainable tensor and will not be updated by optimizer, but is necessary for evaluation and inference. For example, the mean and variance in BatchNorm layers. The registered buffer is persistable by default, and will be saved into state_dict alongside parameters. If set persistable=False, it registers a non-persistable buffer, so that it will not be a part of state_dict .

Buffers can be accessed as attributes using given names.

Parameters

• name (string) – name of the buffer. The buffer can be accessed from this layer using the given name

• tensor (Tensor) – the tensor to be registered as buffer.

• persistable (bool) – whether the buffer is part of this layer’s state_dict.

Returns

None

Examples

>>> import numpy as np
>>> import paddle

>>> linear = paddle.nn.Linear(10, 3)
>>> value = np.array([0]).astype("float32")
>>> buffer = paddle.to_tensor(value)
>>> linear.register_buffer("buf_name", buffer, persistable=True)

>>> # get the buffer by attribute.
>>> print(linear.buf_name)
Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
[0.])

register_forward_post_hook ( hook )

register_forward_post_hook¶

Register a forward post-hook for Layer. The hook will be called after forward function has been computed.

It should have the following form, input and output of the hook is input and output of the Layer respectively. User can use forward post-hook to change the output of the Layer or perform information statistics tasks on the Layer.

hook(Layer, input, output) -> None or modified output

Parameters

hook (function) – a function registered as a forward post-hook

Returns

HookRemoveHelper, a HookRemoveHelper object that can be used to remove the added hook by calling hook_remove_helper.remove() .

Examples

>>> import paddle
>>> import numpy as np

>>> # the forward_post_hook change the output of the layer: output = output * 2
>>> def forward_post_hook(layer, input, output):
...     # user can use layer, input and output for information statistics tasks
...
...     # change the output
...     return output * 2
...
>>> linear = paddle.nn.Linear(13, 5)

>>> # register the hook
>>> forward_post_hook_handle = linear.register_forward_post_hook(forward_post_hook)

>>> value1 = np.arange(26).reshape(2, 13).astype("float32")
>>> in1 = paddle.to_tensor(value1)

>>> out0 = linear(in1)

>>> # remove the hook
>>> forward_post_hook_handle.remove()

>>> out1 = linear(in1)

>>> # hook change the linear's output to output * 2, so out0 is equal to out1 * 2.
>>> assert (out0.numpy() == (out1.numpy()) * 2).any()

register_forward_pre_hook ( hook )

register_forward_pre_hook¶

Register a forward pre-hook for Layer. The hook will be called before forward function has been computed.

It should have the following form, input of the hook is input of the Layer, hook can either return a tuple or a single modified value in the hook. We will wrap the value into a tuple if a single value is returned(unless that value is already a tuple). User can use forward pre-hook to change the input of the Layer or perform information statistics tasks on the Layer.

hook(Layer, input) -> None or modified input

Parameters

hook (function) – a function registered as a forward pre-hook

Returns

HookRemoveHelper, a HookRemoveHelper object that can be used to remove the added hook by calling hook_remove_helper.remove() .

Examples

>>> import paddle
>>> import numpy as np

>>> # the forward_pre_hook change the input of the layer: input = input * 2
>>> def forward_pre_hook(layer, input):
...     # user can use layer and input for information statistics tasks
...
...     # change the input
...     input_return = (input[0] * 2)
...     return input_return
...
>>> linear = paddle.nn.Linear(13, 5)

>>> # register the hook
>>> forward_pre_hook_handle = linear.register_forward_pre_hook(forward_pre_hook)

>>> value0 = np.arange(26).reshape(2, 13).astype("float32")
>>> in0 = paddle.to_tensor(value0)
>>> out0 = linear(in0)

>>> # remove the hook
>>> forward_pre_hook_handle.remove()

>>> value1 = value0 * 2
>>> in1 = paddle.to_tensor(value1)
>>> out1 = linear(in1)

>>> # hook change the linear's input to input * 2, so out0 is equal to out1.
>>> assert (out0.numpy() == out1.numpy()).any()

set_dict ( state_dict, use_structured_name=True )

set_dict¶

Set parameters and persistable buffers from state_dict. All the parameters and buffers will be reset by the tensor in the state_dict

Parameters

• state_dict (dict) – Dict contains all the parameters and persistable buffers.

• use_structured_name (bool, optional) – If true, use structured name as key, otherwise, use parameter or buffer name as key. Default: True.

Returns

A list of str containing the missing keys unexpected_keys(list):A list of str containing the unexpected keys

Return type

missing_keys(list)

Examples

>>> import paddle

>>> emb = paddle.nn.Embedding(10, 10)

>>> state_dict = emb.state_dict()
>>> paddle.save(state_dict, "paddle_dy.pdparams")
>>> para_state_dict = paddle.load("paddle_dy.pdparams")
>>> emb.set_state_dict(para_state_dict)

set_state_dict ( state_dict, use_structured_name=True )

set_state_dict¶

Set parameters and persistable buffers from state_dict. All the parameters and buffers will be reset by the tensor in the state_dict

Parameters

• state_dict (dict) – Dict contains all the parameters and persistable buffers.

• use_structured_name (bool, optional) – If true, use structured name as key, otherwise, use parameter or buffer name as key. Default: True.

Returns

A list of str containing the missing keys unexpected_keys(list):A list of str containing the unexpected keys

Return type

missing_keys(list)

Examples

>>> import paddle

>>> emb = paddle.nn.Embedding(10, 10)

>>> state_dict = emb.state_dict()
>>> paddle.save(state_dict, "paddle_dy.pdparams")
>>> para_state_dict = paddle.load("paddle_dy.pdparams")
>>> emb.set_state_dict(para_state_dict)

state_dict ( destination=None, include_sublayers=True, structured_name_prefix='', use_hook=True, keep_vars=True )

state_dict¶

Get all parameters and persistable buffers of current layer and its sub-layers. And set them into a dict

Parameters

• destination (dict, optional) – If provide, all the parameters and persistable buffers will be set to this dict . Default: None.

• include_sublayers (bool, optional) – If true, also include the parameters and persistable buffers from sublayers. Default: True.

• use_hook (bool, optional) – If true, the operations contained in _state_dict_hooks will be appended to the destination. Default: True.

• keep_vars (bool, optional) – If false, the returned tensors in the state dict are detached from autograd. Default: True.

Returns

a dict contains all the parameters and persistable buffers.

Return type

dict

Examples

>>> import paddle

>>> emb = paddle.nn.Embedding(10, 10)

>>> state_dict = emb.state_dict()
>>> paddle.save( state_dict, "paddle_dy.pdparams")

sublayers ( include_self=False )

sublayers¶

Returns a list of sub layers.

Parameters

include_self (bool, optional) – Whether return self as sublayers. Default: False.

Returns

list of Layer, a list of sub layers.

Examples

>>> import paddle

>>> class MyLayer(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self._linear = paddle.nn.Linear(1, 1)
...         self._dropout = paddle.nn.Dropout(p=0.5)
...
...     def forward(self, input):
...         temp = self._linear(input)
...         temp = self._dropout(temp)
...         return temp
...
>>> mylayer = MyLayer()
>>> print(mylayer.sublayers())
[Linear(in_features=1, out_features=1, dtype=float32), Dropout(p=0.5, axis=None, mode=upscale_in_train)]

to ( device=None, dtype=None, blocking=None )

to¶

Cast the parameters and buffers of Layer by the give device, dtype and blocking.

Parameters

• device (str|paddle.CPUPlace()|paddle.CUDAPlace()|paddle.CUDAPinnedPlace()|paddle.XPUPlace()|None, optional) – The device of the Layer which want to be stored.

• None (If) –

• string (the device is the same with the original Tensor. If device is) –

• cpu (it can be) –

• xpu:x (gpu:x and) –

• the (where x is) –

• Default (index of the GPUs or XPUs.) – None.

• dtype (str|numpy.dtype|paddle.dtype|None, optional) – The type of the data. If None, the dtype is the same with the original Tensor. Default: None.

• blocking (bool|None, optional) – If False and the source is in pinned memory, the copy will be asynchronous with respect to the host. Otherwise, the argument has no effect. If None, the blocking is set True. Default: None.

Returns

self

Examples

>>> import paddle
>>> paddle.seed(2023)

>>> linear=paddle.nn.Linear(2, 2)
>>> linear.weight
>>> print(linear.weight)
Parameter containing:
Tensor(shape=[2, 2], dtype=float32, place=Place(gpu:0), stop_gradient=False,
[[ 0.89611185,  0.04935038],
 [-0.58883440,  0.99266374]])

>>> linear.to(dtype='float64')
>>> linear.weight
>>> print(linear.weight)
Parameter containing:
Tensor(shape=[2, 2], dtype=float64, place=Place(gpu:0), stop_gradient=False,
[[ 0.89611185,  0.04935038],
 [-0.58883440,  0.99266374]])

>>> linear.to(device='cpu')
>>> linear.weight
>>> print(linear.weight)
Parameter containing:
Tensor(shape=[2, 2], dtype=float64, place=Place(cpu), stop_gradient=False,
[[ 0.89611185,  0.04935038],
 [-0.58883440,  0.99266374]])

>>> 
>>> linear.to(device=paddle.CUDAPinnedPlace(), blocking=False)
>>> linear.weight
>>> print(linear.weight)
Tensor(shape=[2, 2], dtype=float64, place=Place(gpu_pinned), stop_gradient=False,
[[ 0.89611185,  0.04935038],
 [-0.58883440,  0.99266374]])

to_static_state_dict ( destination=None, include_sublayers=True, structured_name_prefix='', use_hook=True, keep_vars=True )

to_static_state_dict¶

Get all parameters and buffers of current layer and its sub-layers. And set them into a dict

Parameters

• destination (dict, optional) – If provide, all the parameters and persistable buffers will be set to this dict . Default: None.

• include_sublayers (bool, optional) – If true, also include the parameters and persistable buffers from sublayers. Default: True.

• use_hook (bool, optional) – If true, the operations contained in _state_dict_hooks will be appended to the destination. Default: True.

• keep_vars (bool, optional) – If false, the returned tensors in the state dict are detached from autograd. Default: True.

Returns

dict, a dict contains all the parameters and persistable buffers.

Examples

>>> import paddle

>>> emb = paddle.nn.Embedding(10, 10)

>>> state_dict = emb.to_static_state_dict()
>>> paddle.save( state_dict, "paddle_dy.pdparams")

train ( )

train¶

Sets this Layer and all its sublayers to training mode. This only effects certain modules like Dropout and BatchNorm.

Returns

None

Examples

>>> import paddle
>>> paddle.seed(100)

>>> class MyLayer(paddle.nn.Layer):
...     def __init__(self):
...         super().__init__()
...         self._linear = paddle.nn.Linear(1, 1)
...         self._dropout = paddle.nn.Dropout(p=0.5)
...
...     def forward(self, input):
...         temp = self._linear(input)
...         temp = self._dropout(temp)
...         return temp
...
>>> x = paddle.randn([10, 1], 'float32')
>>> mylayer = MyLayer()
>>> mylayer.eval()  # set mylayer._dropout to eval mode
>>> out = mylayer(x)
>>> mylayer.train()  # set mylayer._dropout to train mode
>>> out = mylayer(x)
>>> print(out)
Tensor(shape=[10, 1], dtype=float32, place=Place(cpu), stop_gradient=False,
[[-3.44879317],
 [ 0.        ],
 [ 0.        ],
 [-0.73825276],
 [ 0.        ],
 [ 0.        ],
 [ 0.64444798],
 [-3.22185946],
 [ 0.        ],
 [-0.68077987]])