# Module: tf.quantization

<br />

Public API for tf.quantization namespace.

## Functions

[`dequantize(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/dequantize): Dequantize the 'input' tensor into a float or bfloat16 Tensor.

[`fake_quant_with_min_max_args(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/fake_quant_with_min_max_args): Fake-quantize the 'inputs' tensor, type float to 'outputs' tensor of same shape and type.

[`fake_quant_with_min_max_args_gradient(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/fake_quant_with_min_max_args_gradient): Compute gradients for a FakeQuantWithMinMaxArgs operation.

[`fake_quant_with_min_max_vars(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/fake_quant_with_min_max_vars): Fake-quantize the 'inputs' tensor of type float via global float scalars

[`fake_quant_with_min_max_vars_gradient(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/fake_quant_with_min_max_vars_gradient): Compute gradients for a FakeQuantWithMinMaxVars operation.

[`fake_quant_with_min_max_vars_per_channel(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/fake_quant_with_min_max_vars_per_channel): Fake-quantize the 'inputs' tensor of type float via per-channel floats

[`fake_quant_with_min_max_vars_per_channel_gradient(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/fake_quant_with_min_max_vars_per_channel_gradient): Compute gradients for a FakeQuantWithMinMaxVarsPerChannel operation.

[`quantize(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/quantize): Quantize the 'input' tensor of type float to 'output' tensor of type 'T'.

[`quantize_and_dequantize(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/quantize_and_dequantize): Quantizes then dequantizes a tensor. (deprecated)

[`quantize_and_dequantize_v2(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/quantize_and_dequantize_v2): Quantizes then dequantizes a tensor.

[`quantized_concat(...)`](https://www.tensorflow.org/versions/r2.13/api_docs/python/tf/quantization/quantized_concat): Concatenates quantized tensors along one dimension.