diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec index d28eb0a8088b41c7dfdd24c39580c8dd2f655bda..056463205ab44495235a6a7218624e55a30b2c56 100644 --- a/paddle/fluid/API.spec +++ b/paddle/fluid/API.spec @@ -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.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.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.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')) diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py index ea028b056620629ba18619f3e6fc2e0c654ed1fb..d868fa9f56c0de3cbc5e3b0dd1af25292416e861 100644 --- a/python/paddle/fluid/layers/nn.py +++ b/python/paddle/fluid/layers/nn.py @@ -205,16 +205,23 @@ def fc(input, **Fully Connected Layer** 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 - each input tensor, which represents a fully connected weight matrix from - each input unit to each output unit. The fully connected layer multiplies - each input tensor with its coresponding weight to produce an output Tensor. - If multiple input tensors are given, the results of multiple multiplications - will be sumed up. If bias_attr 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. + one or multiple tensors as its inputs(input can be a list of Variable, see + Args in detail). It creates a variable called weights for each input tensor, + which represents a fully connected weight matrix from each input unit to + each output unit. The fully connected layer multiplies each input tensor + with its corresponding weight to produce an output Tensor with shape [M, `size`], + where M is batch size. If multiple input tensors are given, the results of + multiple output tensors with shape [M, `size`] will be summed up. If bias_attr + 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:: @@ -222,13 +229,31 @@ def fc(input, In the above equation: - * :math:`N`: Number of the input. - * :math:`X_i`: The input tensor. - * :math:`W`: The weights created by this layer. + * :math:`N`: Number of the input. N equals to len(input) if input is list of Variable. + * :math:`X_i`: The i-th input tensor. + * :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:`Act`: The activation function. * :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: input (Variable|list of Variable): The input tensor(s) of this layer, and the dimension of the input tensor(s) is at least 2. @@ -260,8 +285,14 @@ def fc(input, Examples: .. code-block:: python + # when input is single tensor data = fluid.layers.data(name="data", shape=[32, 32], dtype="float32") 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())