未验证 提交 38898c28 编写于 作者: T Tao Luo 提交者: GitHub

Merge pull request #16212 from Aurelius84/develop

improve layers.fc api doc
...@@ -68,7 +68,7 @@ paddle.fluid.initializer.MSRAInitializer.__init__ (ArgSpec(args=['self', 'unifor ...@@ -68,7 +68,7 @@ paddle.fluid.initializer.MSRAInitializer.__init__ (ArgSpec(args=['self', 'unifor
paddle.fluid.initializer.force_init_on_cpu (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', '6d0f3e22c90d9d500d36ff57daf056ee')) paddle.fluid.initializer.force_init_on_cpu (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', '6d0f3e22c90d9d500d36ff57daf056ee'))
paddle.fluid.initializer.init_on_cpu (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', 'a6d7011ca3d8c0d454dac3a56eae0c29')) paddle.fluid.initializer.init_on_cpu (ArgSpec(args=[], varargs=None, keywords=None, defaults=None), ('document', 'a6d7011ca3d8c0d454dac3a56eae0c29'))
paddle.fluid.initializer.NumpyArrayInitializer.__init__ (ArgSpec(args=['self', 'value'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754')) paddle.fluid.initializer.NumpyArrayInitializer.__init__ (ArgSpec(args=['self', 'value'], varargs=None, keywords=None, defaults=None), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
paddle.fluid.layers.fc (ArgSpec(args=['input', 'size', 'num_flatten_dims', 'param_attr', 'bias_attr', 'act', 'is_test', 'name'], varargs=None, keywords=None, defaults=(1, None, None, None, False, None)), ('document', '1929058262994f212620599c63aea6bd')) paddle.fluid.layers.fc (ArgSpec(args=['input', 'size', 'num_flatten_dims', 'param_attr', 'bias_attr', 'act', 'is_test', 'name'], varargs=None, keywords=None, defaults=(1, None, None, None, False, None)), ('document', '424e898365195e3ccbc2e7dc8b63605e'))
paddle.fluid.layers.embedding (ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32')), ('document', '89c2c55a0b0656b106064048e068e77a')) paddle.fluid.layers.embedding (ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32')), ('document', '89c2c55a0b0656b106064048e068e77a'))
paddle.fluid.layers.dynamic_lstm (ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None)), ('document', 'dfbb624f85015df29e994ca6999e8ff6')) paddle.fluid.layers.dynamic_lstm (ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None)), ('document', 'dfbb624f85015df29e994ca6999e8ff6'))
paddle.fluid.layers.dynamic_lstmp (ArgSpec(args=['input', 'size', 'proj_size', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name', 'h_0', 'c_0', 'cell_clip', 'proj_clip'], varargs=None, keywords=None, defaults=(None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'tanh', 'float32', None, None, None, None, None)), ('document', 'b4b608b986eb9617aa0525e1be21d32d')) paddle.fluid.layers.dynamic_lstmp (ArgSpec(args=['input', 'size', 'proj_size', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name', 'h_0', 'c_0', 'cell_clip', 'proj_clip'], varargs=None, keywords=None, defaults=(None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'tanh', 'float32', None, None, None, None, None)), ('document', 'b4b608b986eb9617aa0525e1be21d32d'))
......
...@@ -205,16 +205,23 @@ def fc(input, ...@@ -205,16 +205,23 @@ def fc(input,
**Fully Connected Layer** **Fully Connected Layer**
This function creates a fully connected layer in the network. It can take This function creates a fully connected layer in the network. It can take
multiple tensors as its inputs. It creates a variable called weights for one or multiple tensors as its inputs(input can be a list of Variable, see
each input tensor, which represents a fully connected weight matrix from Args in detail). It creates a variable called weights for each input tensor,
each input unit to each output unit. The fully connected layer multiplies which represents a fully connected weight matrix from each input unit to
each input tensor with its coresponding weight to produce an output Tensor. each output unit. The fully connected layer multiplies each input tensor
If multiple input tensors are given, the results of multiple multiplications with its corresponding weight to produce an output Tensor with shape [M, `size`],
will be sumed up. If bias_attr is not None, a bias variable will be created where M is batch size. If multiple input tensors are given, the results of
and added to the output. Finally, if activation is not None, it will be applied multiple output tensors with shape [M, `size`] will be summed up. If bias_attr
to the output as well. is not None, a bias variable will be created and added to the output.
Finally, if activation is not None, it will be applied to the output as well.
When the input is single tensor:
This process can be formulated as follows: .. math::
Out = Act({XW + b})
When the input are multiple tensors:
.. math:: .. math::
...@@ -222,13 +229,31 @@ def fc(input, ...@@ -222,13 +229,31 @@ def fc(input,
In the above equation: In the above equation:
* :math:`N`: Number of the input. * :math:`N`: Number of the input. N equals to len(input) if input is list of Variable.
* :math:`X_i`: The input tensor. * :math:`X_i`: The i-th input tensor.
* :math:`W`: The weights created by this layer. * :math:`W_i`: The i-th weights matrix corresponding i-th input tensor.
* :math:`b`: The bias parameter created by this layer (if needed). * :math:`b`: The bias parameter created by this layer (if needed).
* :math:`Act`: The activation function. * :math:`Act`: The activation function.
* :math:`Out`: The output tensor. * :math:`Out`: The output tensor.
See below for an example.
.. code-block:: text
Given:
data_1.data = [[[0.1, 0.2],
[0.3, 0.4]]]
data_1.shape = (1, 2, 2) # 1 is batch_size
data_2 = [[[0.1, 0.2, 0.3]]]
data_2.shape = (1, 1, 3)
out = fluid.layers.fc(input=[data_1, data_2], size=2)
Then:
out.data = [[0.18669507, 0.1893476]]
out.shape = (1, 2)
Args: Args:
input (Variable|list of Variable): The input tensor(s) of this layer, and the dimension of input (Variable|list of Variable): The input tensor(s) of this layer, and the dimension of
the input tensor(s) is at least 2. the input tensor(s) is at least 2.
...@@ -260,8 +285,14 @@ def fc(input, ...@@ -260,8 +285,14 @@ def fc(input,
Examples: Examples:
.. code-block:: python .. code-block:: python
# when input is single tensor
data = fluid.layers.data(name="data", shape=[32, 32], dtype="float32") data = fluid.layers.data(name="data", shape=[32, 32], dtype="float32")
fc = fluid.layers.fc(input=data, size=1000, act="tanh") fc = fluid.layers.fc(input=data, size=1000, act="tanh")
# when input are multiple tensors
data_1 = fluid.layers.data(name="data_1", shape=[32, 32], dtype="float32")
data_2 = fluid.layers.data(name="data_2", shape=[24, 36], dtype="float32")
fc = fluid.layers.fc(input=[data_1, data_2], size=1000, act="tanh")
""" """
helper = LayerHelper("fc", **locals()) helper = LayerHelper("fc", **locals())
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册