W3cubDocs

/TensorFlow Python

tf.nn.quantized_max_pool

tf.nn.quantized_max_pool(
    input,
    min_input,
    max_input,
    ksize,
    strides,
    padding,
    name=None
)

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

See the guide: Neural Network > Candidate Sampling

Produces the max pool of the input tensor for quantized types.

Args:

  • input: A Tensor. Must be one of the following types: qint8, quint8, qint32, qint16, quint16. The 4D (batch x rows x cols x depth) Tensor to MaxReduce over.
  • min_input: A Tensor of type float32. The float value that the lowest quantized input value represents.
  • max_input: A Tensor of type float32. The float value that the highest quantized input value represents.
  • ksize: A list of ints. The size of the window for each dimension of the input tensor. The length must be 4 to match the number of dimensions of the input.
  • strides: A list of ints. The stride of the sliding window for each dimension of the input tensor. The length must be 4 to match the number of dimensions of the input.
  • padding: A string from: "SAME", "VALID". The type of padding algorithm to use.
  • name: A name for the operation (optional).

Returns:

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

  • output: A Tensor. Has the same type as input.
  • min_output: A Tensor of type float32.
  • max_output: A Tensor of type float32.

© 2018 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/python/tf/nn/quantized_max_pool