maxout

paddle.fluid.layers.maxout(x, groups, name=None, axis=1)[source]

MaxOut Operator.

Assumed the input shape is (N, Ci, H, W). The output shape is (N, Co, H, W). Then \(Co = Ci / groups\) and the operator formula is as follows:

$$ y_{si+j} = max_{k} x_{gsi + sk + j} $$ $$ g = groups $$ $$ s = \frac{input.size}{num\_channels} $$ $$ 0 \le i < \frac{num\_channels}{groups} $$ $$ 0 \le j < s $$ $$ 0 \le k < groups $$

Please refer to Paper: - Maxout Networks: http://www.jmlr.org/proceedings/papers/v28/goodfellow13.pdf - Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks: https://arxiv.org/pdf/1312.6082v4.pdf

Parameters
  • x (Variable) – A 4-D Tensor with data type of float32 or float64. The data format is NCHW or NHWC. Where N is batch size, C is the number of channels, H and W is the height and width of feature.

  • groups (int) – Specifies how many groups the input tensor will be split into at the channel dimension. And the number of output channel is the number of channels divided by groups.

  • axis (int, optional) – Specifies the index of channel dimension where maxout will be performed. It should be 1 when data format is NCHW, -1 or 3 when data format is NHWC. Default: 1.

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

Returns

A 4-D Tensor with same data type and data format with input Tensor.

Return type

Variable

Raises

ValueError – If axis is not 1, -1 or 3.

Examples

import paddle.fluid as fluid
input = fluid.data(
    name='data',
    shape=[None, 256, 32, 32],
    dtype='float32')
out = fluid.layers.maxout(input, groups=2)