tf.quantization.fake_quant_with_min_max_vars_per_channel

Concatenates quantized tensors along one dimension.

View aliases

Compat aliases for migration

tf.compat.v1.quantization.quantized_concat, tf.compat.v1.quantized_concat

tf.quantization.quantized_concat(
    concat_dim, values, input_mins, input_maxes, name=None
)

Args
`concat_dim`	A `Tensor` of type `int32`. 0-D. The dimension along which to concatenate. Must be in the range [0, rank(values)).
`values`	A list of at least 2 `Tensor` objects with the same type. The `N` Tensors to concatenate. Their ranks and types must match, and their sizes must match in all dimensions except `concat_dim`.
`input_mins`	A list with the same length as `values` of `Tensor` objects with type `float32`. The minimum scalar values for each of the input tensors.
`input_maxes`	A list with the same length as `values` of `Tensor` objects with type `float32`. 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`	A `Tensor`. Has the same type as `values`.
`output_min`	A `Tensor` of type `float32`.
`output_max`	A `Tensor` of type `float32`.

TensorFlow

tf.quantization / fake_quant_with_min_max_vars_per_channel_gradient

View aliases

Args

Returns

TensorFlow

tf

tf.audio

tf.autograph

tf.bitwise

tf.compat

tf.config

tf.data

tf.debugging

tf.distribute

tf.dtypes

tf.errors

tf.estimator

tf.experimental

tf.feature_column

tf.graph_util

tf.image

tf.initializers

tf.io

tf.keras

tf.linalg

tf.lite

tf.lookup

tf.losses

tf.math

tf.metrics

tf.nest

tf.nn

tf.optimizers

tf.quantization

tf.queue

tf.ragged

tf.random

tf.raw_ops

tf.saved_model

tf.sets

tf.signal

tf.sparse

tf.strings

tf.summary

tf.sysconfig

tf.test

tf.tpu

tf.train

tf.version

tf.xla

tf.quantization / fake_quant_with_min_max_vars_per_channel_gradient

View aliases

Args

Returns