tf.raw_ops.QuantizedConv2DPerChannel

Computes QuantizedConv2D per channel.

tf.raw_ops.QuantizedConv2DPerChannel(
    input, filter, min_input, max_input, min_filter, max_filter, strides, padding,
    out_type=tf.dtypes.qint32, dilations=[1, 1, 1, 1], name=None
)

Args:

  • input: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. The original input tensor.
  • filter: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. The original filter tensor.
  • min_input: A Tensor of type float32. The minimum value of the input tensor
  • max_input: A Tensor of type float32. The maximum value of the input tensor.
  • min_filter: A Tensor of type float32. The minimum value of the filter tensor.
  • max_filter: A Tensor of type float32. The maximum value of the filter tensor.
  • strides: A list of ints. list of stride values.
  • padding: A string from: "SAME", "VALID".
  • out_type: An optional tf.DType from: tf.qint8, tf.quint8, tf.qint32, tf.qint16, tf.quint16. Defaults to tf.qint32. The quantized type of output tensor that needs to be converted.
  • dilations: An optional list of ints. Defaults to [1, 1, 1, 1]. list of dilation values.
  • name: A name for the operation (optional).

Returns:

A tuple of Tensor objects (output, min_output, max_output).

  • output: A Tensor of type out_type.
  • min_output: A Tensor of type float32.
  • max_output: A Tensor of type float32.