Join us at TensorFlow World, Oct 28-31. Use code TF20 for 20% off select passes. Register now

tf.contrib.tpu.infeed_enqueue

Defined in generated file: python/ops/gen_tpu_ops.py

An op which feeds a single Tensor value into the computation.

tf.contrib.tpu.infeed_enqueue(
    input,
    shape=[],
    layout=[],
    device_ordinal=-1,
    name=None
)

Args:

  • input: A Tensor. A tensor that will be provided using the infeed mechanism.
  • shape: An optional tf.TensorShape or list of ints. Defaults to []. The shape of the tensor.
  • layout: An optional list of ints. Defaults to []. A vector holding the requested layout in minor-to-major sequence. If a layout attribute is passed, but its values are all -1, the layout will be computed by the infeed operation.
  • device_ordinal: An optional int. Defaults to -1. The TPU device to use. This should be -1 when the Op is running on a TPU device, and >= 0 when the Op is running on the CPU device.
  • name: A name for the operation (optional).

Returns:

The created Operation.