tf.fake_quant_with_min_max_vars_gradient

tf.fake_quant_with_min_max_vars_gradient

tf.fake_quant_with_min_max_vars_gradient

fake_quant_with_min_max_vars_gradient(
    gradients,
    inputs,
    min,
    max,
    num_bits=None,
    name=None
)

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

See the guide: Tensor Transformations > Fake quantization

Compute gradients for a FakeQuantWithMinMaxVars operation.

Args:

• gradients: A Tensor of type float32. Backpropagated gradients above the FakeQuantWithMinMaxVars operation.
• inputs: A Tensor of type float32. Values passed as inputs to the FakeQuantWithMinMaxVars operation. min, max: Quantization interval, scalar floats.
• min: A Tensor of type float32.
• max: A Tensor of type float32.
• num_bits: An optional int. Defaults to 8. The bitwidth of the quantization; between 2 and 8, inclusive.
• name: A name for the operation (optional).

Returns:

A tuple of Tensor objects (backprops_wrt_input, backprop_wrt_min, backprop_wrt_max).

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