Quantized Batch normalization.
tf.raw_ops.QuantizedBatchNormWithGlobalNormalization(
t,
t_min,
t_max,
m,
m_min,
m_max,
v,
v_min,
v_max,
beta,
beta_min,
beta_max,
gamma,
gamma_min,
gamma_max,
out_type,
variance_epsilon,
scale_after_normalization,
name=None
)
This op is deprecated and will be removed in the future. Prefer
tf.nn.batch_normalization
.
Args | |
---|---|
t
|
A Tensor . Must be one of the following types: qint8 , quint8 , qint32 , qint16 , quint16 .
A 4D input Tensor.
|
t_min
|
A Tensor of type float32 .
The value represented by the lowest quantized input.
|
t_max
|
A Tensor of type float32 .
The value represented by the highest quantized input.
|
m
|
A Tensor . Must have the same type as t .
A 1D mean Tensor with size matching the last dimension of t.
This is the first output from tf.nn.moments,
or a saved moving average thereof.
|
m_min
|
A Tensor of type float32 .
The value represented by the lowest quantized mean.
|
m_max
|
A Tensor of type float32 .
The value represented by the highest quantized mean.
|
v
|
A Tensor . Must have the same type as t .
A 1D variance Tensor with size matching the last dimension of t.
This is the second output from tf.nn.moments,
or a saved moving average thereof.
|
v_min
|
A Tensor of type float32 .
The value represented by the lowest quantized variance.
|
v_max
|
A Tensor of type float32 .
The value represented by the highest quantized variance.
|
beta
|
A Tensor . Must have the same type as t .
A 1D beta Tensor with size matching the last dimension of t.
An offset to be added to the normalized tensor.
|
beta_min
|
A Tensor of type float32 .
The value represented by the lowest quantized offset.
|
beta_max
|
A Tensor of type float32 .
The value represented by the highest quantized offset.
|
gamma
|
A Tensor . Must have the same type as t .
A 1D gamma Tensor with size matching the last dimension of t.
If "scale_after_normalization" is true, this tensor will be multiplied
with the normalized tensor.
|
gamma_min
|
A Tensor of type float32 .
The value represented by the lowest quantized gamma.
|
gamma_max
|
A Tensor of type float32 .
The value represented by the highest quantized gamma.
|
out_type
|
A tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16 .
|
variance_epsilon
|
A float . A small float number to avoid dividing by 0.
|
scale_after_normalization
|
A bool .
A bool indicating whether the resulted tensor
needs to be multiplied with gamma.
|
name
|
A name for the operation (optional). |
Returns | |
---|---|
A tuple of Tensor objects (result, result_min, result_max).
|
|
result
|
A Tensor of type out_type .
|
result_min
|
A Tensor of type float32 .
|
result_max
|
A Tensor of type float32 .
|