{ }
View source on GitHub |
Performs fractional average pooling on the input.
tf.nn.fractional_avg_pool(
value,
pooling_ratio,
pseudo_random=False,
overlapping=False,
seed=0,
name=None
)
Fractional average pooling is similar to Fractional max pooling in the pooling region generation step. The only difference is that after pooling regions are generated, a mean operation is performed instead of a max operation in each pooling region.
Returns |
---|
A tuple of Tensor
objects (output
, row_pooling_sequence
,
col_pooling_sequence
).
output: Output Tensor
after fractional avg pooling. Has the same type as
value
.
row_pooling_sequence: A Tensor
of type int64
.
col_pooling_sequence: A Tensor
of type int64
.
References | |
---|---|
Fractional Max-Pooling: Graham, 2015 (pdf) |