Pooling Layers¶
-
class
npdl.layers.
MeanPooling
(pool_size)[source][source]¶ Average pooling operation for spatial data.
Parameters: - pool_size : tuple of 2 integers,
factors by which to downscale (vertical, horizontal). (2, 2) will halve the image in each dimension.
Returns: - 4D numpy.array
with shape (nb_samples, channels, pooled_rows, pooled_cols) if dim_ordering=’th’ or 4D tensor with shape: (samples, pooled_rows, pooled_cols, channels) if dim_ordering=’tf’.
-
class
npdl.layers.
MaxPooling
(pool_size)[source][source]¶ Max pooling operation for spatial data.
Parameters: - pool_size : tuple of 2 integers,
factors by which to downscale (vertical, horizontal). (2, 2) will halve the image in each dimension.
Returns: - 4D numpy.array
with shape (nb_samples, channels, pooled_rows, pooled_cols) if dim_ordering=’th’ or 4D tensor with shape: (samples, pooled_rows, pooled_cols, channels) if dim_ordering=’tf’.