tf.nn.quantized_conv2d
tf.nn.quantized_conv2d
tf.nn.quantized_conv2d
quantized_conv2d( input, filter, min_input, max_input, min_filter, max_filter, strides, padding, out_type=None, name=None )
Defined in tensorflow/python/ops/gen_nn_ops.py
.
See the guide: Neural Network > Candidate Sampling
Computes a 2D convolution given quantized 4D input and filter tensors.
The inputs are quantized tensors where the lowest value represents the real number of the associated minimum, and the highest represents the maximum. This means that you can only interpret the quantized output in the same way, by taking the returned minimum and maximum values into account.
Args:
-
input
: ATensor
. Must be one of the following types:qint8
,quint8
,qint16
,quint16
,qint32
. -
filter
: ATensor
. Must be one of the following types:qint8
,quint8
,qint16
,quint16
,qint32
. filter's input_depth dimension must match input's depth dimensions. -
min_input
: ATensor
of typefloat32
. The float value that the lowest quantized input value represents. -
max_input
: ATensor
of typefloat32
. The float value that the highest quantized input value represents. -
min_filter
: ATensor
of typefloat32
. The float value that the lowest quantized filter value represents. -
max_filter
: ATensor
of typefloat32
. The float value that the highest quantized filter value represents. -
strides
: A list ofints
. The stride of the sliding window for each dimension of the input tensor. -
padding
: Astring
from:"SAME", "VALID"
. The type of padding algorithm to use. -
out_type
: An optionaltf.DType
from:tf.qint8, tf.quint8, tf.qint16, tf.quint16, tf.qint32
. Defaults totf.qint32
. -
name
: A name for the operation (optional).
Returns:
A tuple of Tensor
objects (output, min_output, max_output).
-
output
: ATensor
of typeout_type
. -
min_output
: ATensor
of typefloat32
. The float value that the lowest quantized output value represents. -
max_output
: ATensor
of typefloat32
. The float value that the highest quantized output value represents.
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/nn/quantized_conv2d