tf.dequantize(input, min_range, max_range, mode=None, name=None)

tf.dequantize(input, min_range, max_range, mode=None, name=None)

See the guide: Tensor Transformations > Slicing and Joining

Dequantize the 'input' tensor into a float Tensor.

[min_range, max_range] are scalar floats that specify the range for the 'input' data. The 'mode' attribute controls exactly which calculations are used to convert the float values to their quantized equivalents.

In 'MIN_COMBINED' mode, each value of the tensor will undergo the following:

if T == qint8, in[i] += (range(T) + 1)/ 2.0
out[i] = min_range + (in[i]* (max_range - min_range) / range(T))

here range(T) = numeric_limits<T>::max() - numeric_limits<T>::min()

MIN_COMBINED Mode Example

If the input comes from a QuantizedRelu6, the output type is quint8 (range of 0-255) but the possible range of QuantizedRelu6 is 0-6. The min_range and max_range values are therefore 0.0 and 6.0. Dequantize on quint8 will take each value, cast to float, and multiply by 6 / 255. Note that if quantizedtype is qint8, the operation will additionally add each value by 128 prior to casting.

If the mode is 'MIN_FIRST', then this approach is used:

number_of_steps = 1 << (# of bits in T)
range_adjust = number_of_steps / (number_of_steps - 1)
range = (range_max - range_min) * range_adjust
range_scale = range / number_of_steps
const double offset_input = static_cast<double>(input) - lowest_quantized;
result = range_min + ((input - numeric_limits<T>::min()) * range_scale)

Args:

  • input: A Tensor. Must be one of the following types: qint8, quint8, qint16, quint16, qint32.
  • min_range: A Tensor of type float32. The minimum scalar value possibly produced for the input.
  • max_range: A Tensor of type float32. The maximum scalar value possibly produced for the input.
  • mode: An optional string from: "MIN_COMBINED", "MIN_FIRST". Defaults to "MIN_COMBINED".
  • name: A name for the operation (optional).

Returns:

A Tensor of type float32.

Defined in tensorflow/python/ops/gen_array_ops.py.