Aliases:
tf.quantization.quantized_concat
tf.quantized_concat
tf.quantization.quantized_concat(
concat_dim,
values,
input_mins,
input_maxes,
name=None
)
Defined in generated file: tensorflow/python/ops/gen_array_ops.py
.
Concatenates quantized tensors along one dimension.
Args:
concat_dim
: ATensor
of typeint32
. 0-D. The dimension along which to concatenate. Must be in the range [0, rank(values)).values
: A list of at least 2Tensor
objects with the same type. TheN
Tensors to concatenate. Their ranks and types must match, and their sizes must match in all dimensions exceptconcat_dim
.input_mins
: A list with the same length asvalues
ofTensor
objects with typefloat32
. The minimum scalar values for each of the input tensors.input_maxes
: A list with the same length asvalues
ofTensor
objects with typefloat32
. The maximum scalar values for each of the input tensors.name
: A name for the operation (optional).
Returns:
A tuple of Tensor
objects (output, output_min, output_max).
output
: ATensor
. Has the same type asvalues
.output_min
: ATensor
of typefloat32
.output_max
: ATensor
of typefloat32
.