Difference between revisions of "Data Flow Graph (DFG)"

From
Jump to: navigation, search
Line 8: Line 8:
 
[http://www.google.com/search?q=Data+Flow+Graph+DFG+deep+machine+learning+ML+artificial+intelligence ...Google search]
 
[http://www.google.com/search?q=Data+Flow+Graph+DFG+deep+machine+learning+ML+artificial+intelligence ...Google search]
  
 +
* [[Visualization]]
 +
* [[TensorBoard]]
 
* [http://idl.cs.washington.edu/papers/tfgraph/ Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow | K. Wongsuphasawat, D. Smilkov, J. Wexler, J. Wilson, D. Mané, D. Fritz, D. Krishnan, F. B. Viégas, & M. Wattenberg - UW Interactive Data Lab]
 
* [http://idl.cs.washington.edu/papers/tfgraph/ Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow | K. Wongsuphasawat, D. Smilkov, J. Wexler, J. Wilson, D. Mané, D. Fritz, D. Krishnan, F. B. Viégas, & M. Wattenberg - UW Interactive Data Lab]
  

Revision as of 21:51, 22 February 2019

YouTube search... ...Google search

A data-flow graph (DFG) is a graph which represents a data dependencies between a number of operations. Any algorithm consists of a number of ordered operations.

  • Node: In TensorFlow, each node represents the instantion of an operation. Each operation has >= inputs and >= 0 outputs.
  • Edges: In TensorFlow, there are two types of edge:
    • Normal Edges: They are carriers of data structures (tensors), where an output of one operation (from one node) becomes the input for another operation.
    • Special Edges: These edges are not data carriers between the output of a node (operator) and the input of another node. A special edge indicates a control dependency between two nodes. Let's suppose we have two nodes A and B and a special edges connecting A to B; it means that B will start its operation only when the operation in A ends. Special edges are used in Data Flow Graph to set the happens-before relationship between operations on the tensors.

tfgraph.png