# pool2d¶

paddle.fluid.layers.nn. pool2d ( input, pool_size=- 1, pool_type='max', pool_stride=1, pool_padding=0, global_pooling=False, use_cudnn=True, ceil_mode=False, name=None, exclusive=True, data_format='NCHW' ) [source]

This operation calculates the pooling output based on the input, pooling_type and pool_size, pool_stride, pool_padding parameters. Input(X) and Output(Out) are in NCHW or NHWC 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. Parameters(pool_size, pool_stride, pool_padding) hold two integer elements. These two elements represent height and width, respectively. The input(X) size and output(Out) size may be different.

Example:

Input:

X shape: $(N, C, H_{in}, W_{in})$

Output:

Out shape: $(N, C, H_{out}, W_{out})$

For pool_padding = “SAME”: $$H_{out} = \frac{(H_{in} + strides[0] - 1)}{strides[0]}$$ $$W_{out} = \frac{(W_{in} + strides[1] - 1)}{strides[1]}$$

For pool_padding = “VALID”: $$H_{out} = \frac{(H_{in} - ksize[0] + strides[0])}{strides[0]}$$ $$W_{out} = \frac{(W_{in} - ksize[1] + strides[1])}{strides[1]}$$

For ceil_mode = false: $$H_{out} = \frac{(H_{in} - ksize[0] + pad_height_top + pad_height_bottom}{strides[0]} + 1$$ $$W_{out} = \frac{(W_{in} - ksize[1] + pad_width_left + pad_width_right}{strides[1]} + 1$$

For ceil_mode = true: $$H_{out} = \frac{(H_{in} - ksize[0] + pad_height_top + pad_height_bottom + strides[0] - 1)}{strides[0]} + 1$$ $$W_{out} = \frac{(W_{in} - ksize[1] + pad_width_left + pad_width_right + strides[1] - 1)}{strides[1]} + 1$$

For exclusive = false: $$hstart = i * strides[0] - pad_height_top$$ $$hend = hstart + ksize[0]$$ $$wstart = j * strides[1] - pad_width_left$$ $$wend = wstart + ksize[1]$$ $$Output(i ,j) = \frac{sum(Input[hstart:hend, wstart:wend])}{ksize[0] * ksize[1]}$$

For exclusive = true: $$hstart = max(0, i * strides[0] - pad_height_top)$$ $$hend = min(H, hstart + ksize[0])$$ $$wstart = max(0, j * strides[1] - pad_width_left)$$ $$wend = min(W, wstart + ksize[1])$$ $$Output(i ,j) = \frac{sum(Input[hstart:hend, wstart:wend])}{(hend - hstart) * (wend - wstart)}$$

Parameters
• input (Variable) – The input tensor of pooling operator which is a 4-D tensor with shape [N, C, H, W]. The format of input tensor is “NCHW” or “NHWC”, 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 data type if float32 or float64.

• pool_size (int|list|tuple) – The pool kernel size. If pool kernel size is a tuple or list, it must contain two integers, (pool_size_Height, pool_size_Width). Otherwise, the pool kernel size will be a square of an int.

• pool_type – (string), pooling type, can be “max” for max-pooling and “avg” for average-pooling

• pool_stride (int|list|tuple) – The pool stride size. If pool stride size is a tuple or list, it must contain two integers, (pool_stride_Height, pool_stride_Width). Otherwise, the pool stride size will be a square of an int.

• global_pooling (bool) – (bool) Whether to use the global pooling. If global_pooling = true, kernel size and paddings will be ignored. Default False

• use_cudnn (bool) – (bool) Only used in cudnn kernel, need install cudnn. Default False

• ceil_mode (bool) – (bool) Whether to use the ceil function to calculate output height and width. False is the default. If it is set to False, the floor function will be used. Default False

• name (str, optional) – For detailed information, please refer to Name. Usually name is no need to set and None by default.

• exclusive (bool) – Whether to exclude padding points in average pooling mode, default is true.

• data_format (string) – The data format of the input and output data. An optional string from: “NCHW”, “NHWC”. The default is “NCHW”. When it is “NCHW”, the data is stored in the order of: [batch_size, input_channels, input_height, input_width].

Returns

The output tensor of pooling result. The data type is same as input tensor.

Return type

Variable

Raises
• ValueError – If pool_type is not “max” nor “avg”.

• ValueError – If global_pooling is False and pool_size is -1.

• TypeError – If use_cudnn is not a bool value.

• ValueError – If data_format is not “NCHW” or “NHWC”.

• ValueError – If pool_padding is a string, but not “SAME” or “VALID”.

• ValueError – If pool_padding is “VALID”, but ceil_mode is True.

• ValueError – If pool_padding is a list or tuple, but the elements in the batch or channel dimensions are non-zero.

• ShapeError – If the input is not a 4-D or 5-D Tensor.

• ShapeError – If the dimension of input minus the size of pool_stride is not 2.

• ShapeError – If the size of pool_size and pool_stride is not equal.

• ShapeError – If the output’s shape calculated is not greater than 0.

Examples

import paddle.fluid as fluid

data = fluid.data(name='data', shape=[None, 3, 32, 32], dtype='float32')

# max pool2d
pool2d = fluid.layers.pool2d(
input = data,
pool_size = 2,
pool_type = "max",
pool_stride = 1,
global_pooling=False)

# average pool2d
pool2d = fluid.layers.pool2d(
input = data,
pool_size = 2,
pool_type = "avg",
pool_stride = 1,
global_pooling=False)

# global average pool2d
pool2d = fluid.layers.pool2d(
input = data,
pool_size = 2,
pool_type = "avg",
pool_stride = 1,
global_pooling=True)

# Attr(pool_padding) is a list with 4 elements, Attr(data_format) is "NCHW".
out_1 = fluid.layers.pool2d(
input = data,
pool_size = 3,
pool_type = "avg",
pool_stride = 1,
pool_padding = [1, 2, 1, 0],
data_format = "NCHW")

# Attr(pool_padding) is a string, Attr(data_format) is "NCHW".
out_2 = fluid.layers.pool2d(
input = data,
pool_size = 3,
pool_type = "avg",
pool_stride = 1,