diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py index c8cbb5ef00b7dac4ae3f833d3d98653e17bee2ab..f6b4348d250a9d99541932fcfefd386584d0d1e5 100644 --- a/python/paddle/fluid/layers/nn.py +++ b/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, + `_ . + 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.