tensorflow:: ops:: QuantizedConcat
#include <array_ops.h>
Concatenates quantized tensors along one dimension.
Summary
Args:
- scope: A Scope object
- concat_dim: 0-D. The dimension along which to concatenate. Must be in the range [0, rank(values)).
- values: The
N
Tensors to concatenate. Their ranks and types must match, and their sizes must match in all dimensions exceptconcat_dim
. - input_mins: The minimum scalar values for each of the input tensors.
- input_maxes: The maximum scalar values for each of the input tensors.
Returns:
Output
output: ATensor
with the concatenation of values stacked along theconcat_dim
dimension. This tensor's shape matches that ofvalues
except inconcat_dim
where it has the sum of the sizes.Output
output_min: The float value that the minimum quantized output value represents.Output
output_max: The float value that the maximum quantized output value represents.
Constructors and Destructors |
|
---|---|
QuantizedConcat(const ::tensorflow::Scope & scope, ::tensorflow::Input concat_dim, ::tensorflow::InputList values, ::tensorflow::InputList input_mins, ::tensorflow::InputList input_maxes)
|
Public attributes |
|
---|---|
operation
|
|
output
|
|
output_max
|
|
output_min
|
Public attributes
operation
Operation operation
output
::tensorflow::Output output
output_max
::tensorflow::Output output_max
output_min
::tensorflow::Output output_min
Public functions
QuantizedConcat
QuantizedConcat( const ::tensorflow::Scope & scope, ::tensorflow::Input concat_dim, ::tensorflow::InputList values, ::tensorflow::InputList input_mins, ::tensorflow::InputList input_maxes )