class tf.Operation

See the guide: Building Graphs > Core graph data structures

Represents a graph node that performs computation on tensors.

An Operation is a node in a TensorFlow Graph that takes zero or more Tensor objects as input, and produces zero or more Tensor objects as output. Objects of type Operation are created by calling a Python op constructor (such as tf.matmul) or tf.Graph.create_op.

For example c = tf.matmul(a, b) creates an Operation of type "MatMul" that takes tensors a and b as input, and produces c as output.

After the graph has been launched in a session, an Operation can be executed by passing it to is a shortcut for calling tf.get_default_session().run(op).



The Operation objects on which this op has a control dependency.

Before this op is executed, TensorFlow will ensure that the operations in self.control_inputs have finished executing. This mechanism can be used to run ops sequentially for performance reasons, or to ensure that the side effects of an op are observed in the correct order.


A list of Operation objects.


The name of the device to which this op has been assigned, if any.


The string name of the device to which this op has been assigned, or an empty string if it has not been assigned to a device.


The Graph that contains this operation.


The list of Tensor objects representing the data inputs of this op.


The full name of this operation.


Returns a serialized NodeDef representation of this operation.


A NodeDef protocol buffer.


Returns the OpDef proto that represents the type of this op.


An OpDef protocol buffer.


The list of Tensor objects representing the outputs of this op.


Returns the call stack from when this operation was constructed.


The type of the op (e.g. "MatMul").


__init__(node_def, g, inputs=None, output_types=None, control_inputs=None, input_types=None, original_op=None, op_def=None)

Creates an Operation.

NOTE: This constructor validates the name of the Operation (passed as Valid Operation names match the following regular expression:



  • node_def: node_def_pb2.NodeDef. NodeDef for the Operation. Used for attributes of node_def_pb2.NodeDef, typically name, op, and device. The input attribute is irrelevant here as it will be computed when generating the model.
  • g: Graph. The parent graph.
  • inputs: list of Tensor objects. The inputs to this Operation.
  • output_types: list of DType objects. List of the types of the Tensors computed by this operation. The length of this list indicates the number of output endpoints of the Operation.
  • control_inputs: list of operations or tensors from which to have a control dependency.
  • input_types: List of DType objects representing the types of the tensors accepted by the Operation. By default uses [x.dtype.base_dtype for x in inputs]. Operations that expect reference-typed inputs must specify these explicitly.
  • original_op: Optional. Used to associate the new Operation with an existing Operation (for example, a replica with the op that was replicated).
  • op_def: Optional. The op_def_pb2.OpDef proto that describes the op type that this Operation represents.


  • TypeError: if control inputs are not Operations or Tensors, or if node_def is not a NodeDef, or if g is not a Graph, or if inputs are not tensors, or if inputs and input_types are incompatible.
  • ValueError: if the node_def name is not valid.


Returns the list of colocation groups of the op.


Returns the value of the attr of this op with the given name.


  • name: The name of the attr to fetch.


The value of the attr, as a Python object.


  • ValueError: If this op does not have an attr with the given name.

run(feed_dict=None, session=None)

Runs this operation in a Session.

Calling this method will execute all preceding operations that produce the inputs needed for this operation.

N.B. Before invoking, its graph must have been launched in a session, and either a default session must be available, or session must be specified explicitly.


  • feed_dict: A dictionary that maps Tensor objects to feed values. See for a description of the valid feed values.
  • session: (Optional.) The Session to be used to run to this operation. If none, the default session will be used.


DEPRECATED: Use outputs.

Defined in tensorflow/python/framework/