FakeQuantWithMinMaxVarsGradient

tensorflow C++ API

tensorflow::ops::FakeQuantWithMinMaxVarsGradient

Compute gradients for a FakeQuantWithMinMaxVars operation.

Summary

Arguments:

• scope: A Scope object
• gradients: Backpropagated gradients above the FakeQuantWithMinMaxVars operation.
• inputs: Values passed as inputs to the FakeQuantWithMinMaxVars operation. min, max: Quantization interval, scalar floats.

Optional attributes (seeAttrs):

• num_bits: The bitwidth of the quantization; between 2 and 8, inclusive.

Returns:

• Output backprops_wrt_input: Backpropagated gradients w.r.t. inputs: gradients * (inputs >= min && inputs <= max).
• Output backprop_wrt_min: Backpropagated gradients w.r.t. min parameter: sum(gradients * (inputs < min)).
• Output backprop_wrt_max: Backpropagated gradients w.r.t. max parameter: sum(gradients * (inputs > max)).

FakeQuantWithMinMaxVarsGradient block

Source link :https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_array_ops.cpp

Argument:

• Scope scope : A Scope object (A scope is generated automatically each page. A scope is not connected.)
• Input inputs: A Tensor of type float.
• Input min : A Tensor of type float.
• Input max : A Tensor of type float.
• Attr attrs : An optional attribute value
  • num_bits : An optional int. Defaults to 8.

Attrs use ex)

Output:

• output : Output object of FakeQuantWithMinMaxVarsGradient class object.

Result:

• std::vector(Tensor) backprops_wrt_input: A Tensorof type float32. Backpropagated gradients w.r.t. inputs:gradients * inputs >= min && inputs <= max).
• std::vector(Tensor) backprop_wrt_min : A Tensorof type float32 . Backpropagated gradients w.r.t. min parameter: sum(gradients * (inputs < min)).
• std::vector(Tensor) backprop_wrt_max : A Tensor of type float32 . Backpropagated gradients w.r.t. max parameter: sum(gradients * (inputs > max)).

Using Method