tf.raw_ops.QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize

Computes quantized depthwise Conv2D with Bias, Relu and Requantize.

tf.raw_ops.QuantizedDepthwiseConv2DWithBiasAndReluAndRequantize(
    input,
    filter,
    bias,
    min_input,
    max_input,
    min_filter,
    max_filter,
    min_freezed_output,
    max_freezed_output,
    strides,
    padding,
    out_type=tf.dtypes.quint8,
    dilations=[1, 1, 1, 1],
    padding_list=[],
    name=None
)

inputA Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. The original input tensor.
filterA Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. The original filter tensor.
biasA Tensor. Must be one of the following types: float32, qint32. The original bias tensor.
min_inputA Tensor of type float32. The float value that the minimum quantized input value represents.
max_inputA Tensor of type float32. The float value that the maximum quantized input value represents.
min_filterA Tensor of type float32. The float value that the minimum quantized filter value represents.
max_filterA Tensor of type float32. The float value that the maximum quantized filter value represents.
min_freezed_outputA Tensor of type float32. The minimum float value of the output tensor.
max_freezed_outputA Tensor of type float32. The maximum float value of the output tensor.
stridesA list of ints. List of stride values.
paddingA string from: "SAME", "VALID".
out_typeAn optional tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16. Defaults to tf.quint8. The type of the output.
dilationsAn optional list of ints. Defaults to [1, 1, 1, 1]. List of dilation values.
padding_listAn optional list of ints. Defaults to [].
nameA name for the operation (optional).

A tuple of Tensor objects (output, min_output, max_output).
outputA Tensor of type out_type.
min_outputA Tensor of type float32.
max_outputA Tensor of type float32.