tf.quantize_and_dequantize_v4
Stay organized with collections
Save and categorize content based on your preferences.
Returns the gradient of QuantizeAndDequantizeV4.
tf.quantize_and_dequantize_v4(
input, input_min, input_max, signed_input=True, num_bits=8, range_given=False,
round_mode='HALF_TO_EVEN', narrow_range=False, axis=-1, name=None
)
This is almost identical to QuantizeAndDequantizeV2, except that it returns a
gradient of 1 for inputs that are within the quantization range, or 0 otherwise.
Args |
|---|
input
|
A Tensor. Must be one of the following types: bfloat16, half, float32, float64.
|
input_min
|
A Tensor. Must have the same type as input.
|
input_max
|
A Tensor. Must have the same type as input.
|
signed_input
|
An optional bool. Defaults to True.
|
num_bits
|
An optional int. Defaults to 8.
|
range_given
|
An optional bool. Defaults to False.
|
round_mode
|
An optional string from: "HALF_TO_EVEN", "HALF_UP". Defaults to "HALF_TO_EVEN".
|
narrow_range
|
An optional bool. Defaults to False.
|
axis
|
An optional int. Defaults to -1.
|
name
|
A name for the operation (optional).
|
Returns |
|---|
A Tensor. Has the same type as input.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2021-02-18 UTC.
[null,null,["Last updated 2021-02-18 UTC."],[],[],null,["# tf.quantize_and_dequantize_v4\n\n\u003cbr /\u003e\n\nReturns the gradient of `QuantizeAndDequantizeV4`.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.quantize_and_dequantize_v4`](https://www.tensorflow.org/api_docs/python/tf/quantize_and_dequantize_v4)\n\n\u003cbr /\u003e\n\n tf.quantize_and_dequantize_v4(\n input, input_min, input_max, signed_input=True, num_bits=8, range_given=False,\n round_mode='HALF_TO_EVEN', narrow_range=False, axis=-1, name=None\n )\n\nThis is almost identical to QuantizeAndDequantizeV2, except that it returns a\ngradient of 1 for inputs that are within the quantization range, or 0 otherwise.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------|-------------------------------------------------------------------------------------------|\n| `input` | A `Tensor`. Must be one of the following types: `bfloat16`, `half`, `float32`, `float64`. |\n| `input_min` | A `Tensor`. Must have the same type as `input`. |\n| `input_max` | A `Tensor`. Must have the same type as `input`. |\n| `signed_input` | An optional `bool`. Defaults to `True`. |\n| `num_bits` | An optional `int`. Defaults to `8`. |\n| `range_given` | An optional `bool`. Defaults to `False`. |\n| `round_mode` | An optional `string` from: `\"HALF_TO_EVEN\", \"HALF_UP\"`. Defaults to `\"HALF_TO_EVEN\"`. |\n| `narrow_range` | An optional `bool`. Defaults to `False`. |\n| `axis` | An optional `int`. Defaults to `-1`. |\n| `name` | A name for the operation (optional). |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor`. Has the same type as `input`. ||\n\n\u003cbr /\u003e"]]
