Computes gradient of the FractionalMaxPool function.
tf.raw_ops.FractionalMaxPoolGrad(
orig_input, orig_output, out_backprop, row_pooling_sequence,
col_pooling_sequence, overlapping=False, name=None
)
Args | |
---|---|
orig_input
|
A Tensor . Must be one of the following types: float32 , float64 , int32 , int64 .
Original input for fractional_max_pool
|
orig_output
|
A Tensor . Must have the same type as orig_input .
Original output for fractional_max_pool
|
out_backprop
|
A Tensor . Must have the same type as orig_input .
4-D with shape [batch, height, width, channels] . Gradients
w.r.t. the output of fractional_max_pool .
|
row_pooling_sequence
|
A Tensor of type int64 .
row pooling sequence, form pooling region with
col_pooling_sequence.
|
col_pooling_sequence
|
A Tensor of type int64 .
column pooling sequence, form pooling region with
row_pooling sequence.
|
overlapping
|
An optional bool . Defaults to False .
When set to True, it means when pooling, the values at the boundary
of adjacent pooling cells are used by both cells. For example:
If the pooling sequence is [0, 2, 4], then 16, at index 2 will be used twice. The result would be [20, 16] for fractional max pooling. |
name
|
A name for the operation (optional). |
Returns | |
---|---|
A Tensor . Has the same type as orig_input .
|