tf.nn.avg_pool

Performs the avg pooling on the input.

Used in the notebooks

Used in the tutorials

Each entry in output is the mean of the corresponding size ksize window in value.

inputTensor of rank N+2, of shape [batch_size] + input_spatial_shape + [num_channels] if data_format does not start with "NC" (default), or [batch_size, num_channels] + input_spatial_shape if data_format starts with "NC". Pooling happens over the spatial dimensions only.
ksizeAn int or list of ints that has length 1, N or N+2. The size of the window for each dimension of the input tensor.
stridesAn int or list of ints that has length 1, N or N+2. The stride of the sliding window for each dimension of the input tensor.
paddingA string, either 'VALID' or 'SAME'. The padding algorithm. See here for more information.
data_formatA string. Specifies the channel dimension. For N=1 it can be either "NWC" (default) or "NCW", for N=2 it can be either "NHWC" (default) or "NCHW" and for N=3 either "NDHWC" (default) or "NCDHW".
nameOptional name for the operation.

A Tensor of format specified by data_format. The average pooled output tensor.