Add conv3d Python API

python/paddle/fluid/layers/nn.py

@@ -1305,8 +1305,6 @@ def conv2d(input,
           conv2d = fluid.layers.conv2d(
               input=data, num_filters=2, filter_size=3, act="relu")
     """
-    if stride is None:
-        stride = [1, 1]
 
     num_channels = input.shape[1]
 
@@ -1369,6 +1367,172 @@ def conv2d(input,
     return helper.append_activation(pre_act)
 
 
+def conv3d(input,
+           num_filters,
+           filter_size,
+           stride=1,
+           padding=0,
+           dilation=1,
+           groups=None,
+           param_attr=None,
+           bias_attr=None,
+           use_cudnn=True,
+           use_mkldnn=False,
+           act=None,
+           name=None):
+    """
+    **Convlution3D Layer**
+
+    The convolution3D layer calculates the output based on the input, filter
+    and strides, paddings, dilations, groups parameters. Input(Input) and
+    Output(Output) are in NCHW format. Where N is batch size, C is the number of
+    channels, H is the height of the feature, and W is the width of the feature.
+    The details of convolution layer, please refer UFLDL's `convolution,
+    <http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>`_ .
+    If bias attribution and activation type are provided, bias is added to the
+    output of the convolution, and the corresponding activation function is
+    applied to the final result.
+
+    For each input :math:`X`, the equation is:
+
+    .. math::
+
+        Out = \sigma (W \\ast X + b)
+
+    In the above equation:
+
+    * :math:`X`: Input value, a tensor with NCHW format.
+    * :math:`W`: Filter value, a tensor with MCHW format.
+    * :math:`\\ast`: Convolution operation.
+    * :math:`b`: Bias value, a 2-D tensor with shape [M, 1].
+    * :math:`\\sigma`: Activation function.
+    * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be
+                   different.
+
+    Example:
+
+        - Input:
+
+          Input shape: :math:`(N, C_{in}, D_{in}, H_{in}, W_{in})`
+
+          Filter shape: :math:`(C_{out}, C_{in}, D_f, H_f, W_f)`
+
+        - Output:
+          Output shape: :math:`(N, C_{out}, D_{out}, H_{out}, W_{out})`
+
+        Where
+
+        .. math::
+
+            D_{out}&= \\frac{(D_{in} + 2 * paddings[0] - (dilations[0] * (D_f - 1) + 1))}{strides[0]} + 1 \\\\
+            H_{out}&= \\frac{(H_{in} + 2 * paddings[1] - (dilations[1] * (H_f - 1) + 1))}{strides[1]} + 1 \\\\
+            W_{out}&= \\frac{(W_{in} + 2 * paddings[2] - (dilations[2] * (W_f - 1) + 1))}{strides[2]} + 1
+
+    Args:
+        input (Variable): The input image with [N, C, D, H, W] format.
+            num_filters(int): The number of filter. It is as same as the output
+            image channel.
+        filter_size (int|tuple|None): The filter size. If filter_size is a tuple,
+            it must contain two integers, (filter_size_D, filter_size_H, filter_size_W).
+            Otherwise, the filter will be a square.
+        stride (int|tuple): The stride size. If stride is a tuple, it must
+            contain two integers, (stride_D, stride_H, stride_W). Otherwise, the
+            stride_D = stride_H = stride_W = stride. Default: stride = 1.
+        padding (int|tuple): The padding size. If padding is a tuple, it must
+            contain two integers, (padding_D, padding_H, padding_W). Otherwise, the
+            padding_D = padding_H = padding_W = padding. Default: padding = 0.
+        dilation (int|tuple): The dilation size. If dilation is a tuple, it must
+            contain two integers, (dilation_D, dilation_H, dilation_W). Otherwise, the
+            dilation_D = dilation_H = dilation_W = dilation. Default: dilation = 1.
+        groups (int): The groups number of the Conv3d Layer. According to grouped
+            convolution in Alex Krizhevsky's Deep CNN paper: when group=2,
+            the first half of the filters is only connected to the first half
+            of the input channels, while the second half of the filters is only
+            connected to the second half of the input channels. Default: groups=1
+        param_attr (ParamAttr): The parameters to the Conv3d Layer. Default: None
+        bias_attr (ParamAttr): Bias parameter for the Conv3d layer. Default: None
+        use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn
+            library is installed. Default: True
+        use_mkldnn (bool): Use mkldnn kernels or not.
+        act (str): Activation type. Default: None
+        name (str|None): A name for this layer(optional). If set None, the layer
+            will be named automatically.
+
+    Returns:
+        Variable: The tensor variable storing the convolution and \
+                  non-linearity activation result.
+
+    Raises:
+        ValueError: If the shapes of input, filter_size, stride, padding and
+                    groups mismatch.
+
+    Examples:
+        .. code-block:: python
+
+          data = fluid.layers.data(
+              name='data', shape=[3, 12, 32, 32], dtype='float32')
+          conv2d = fluid.layers.conv3d(
+              input=data, num_filters=2, filter_size=3, act="relu")
+    """
+
+    l_type = 'conv3d'
+
+    helper = LayerHelper(l_type, **locals())
+    dtype = helper.input_dtype()
+
+    num_channels = input.shape[1]
+
+    if groups is None:
+        num_filter_channels = num_channels
+    else:
+        if num_channels % groups != 0:
+            raise ValueError("num_channels must be divisible by groups.")
+        num_filter_channels = num_channels / groups
+
+    filter_size = utils.convert_to_list(filter_size, 3, 'filter_size')
+    stride = utils.convert_to_list(stride, 3, 'stride')
+    padding = utils.convert_to_list(padding, 3, 'padding')
+    dilation = utils.convert_to_list(dilation, 3, 'dilation')
+
+    if not isinstance(use_cudnn, bool):
+        raise ValueError("use_cudnn should be True or False")
+
+    input_shape = input.shape
+    filter_shape = [num_filters, num_filter_channels] + filter_size
+
+    def _get_default_param_initializer():
+        std = (2.0 / (filter_size[0]**3 * num_channels))**0.5
+        return Normal(0.0, std, 0)
+
+    filter_param = helper.create_parameter(
+        attr=helper.param_attr,
+        shape=filter_shape,
+        dtype=dtype,
+        default_initializer=_get_default_param_initializer())
+
+    pre_bias = helper.create_tmp_variable(dtype)
+
+    helper.append_op(
+        type=l_type,
+        inputs={
+            'Input': input,
+            'Filter': filter_param,
+        },
+        outputs={"Output": pre_bias},
+        attrs={
+            'strides': stride,
+            'paddings': padding,
+            'dilations': dilation,
+            'groups': groups,
+            'use_cudnn': use_cudnn,
+            'use_mkldnn': use_mkldnn
+        })
+
+    pre_act = helper.append_bias_op(pre_bias, dim_start=1, dim_end=3)
+
+    return helper.append_activation(pre_act)
+
+
 def sequence_pool(input, pool_type):
     """
     This function add the operator for sequence pooling.