Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow
Autor: | Martin Wattenberg, James Wexler, Dilip Krishnan, Doug Fritz, Fernanda B. Viégas, Jimbo Wilson, Kanit Wongsuphasawat, Dandelion Mane, Daniel Smilkov |
---|---|
Rok vydání: | 2018 |
Předmět: |
Theoretical computer science
Source code Computer science Dataflow media_common.quotation_subject 02 engineering and technology computer.software_genre Graph drawing 0202 electrical engineering electronic engineering information engineering media_common Graph database Artificial neural network business.industry Deep learning 020207 software engineering Computer Graphics and Computer-Aided Design Graph Visualization Debugging Signal Processing Graph (abstract data type) 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business computer Software |
Zdroj: | IEEE Transactions on Visualization and Computer Graphics. 24:1-12 |
ISSN: | 1077-2626 |
Popis: | We present a design study of the TensorFlow Graph Visualizer, part of the TensorFlow machine intelligence platform. This tool helps users understand complex machine learning architectures by visualizing their underlying dataflow graphs. The tool works by applying a series of graph transformations that enable standard layout techniques to produce a legible interactive diagram. To declutter the graph, we decouple non-critical nodes from the layout. To provide an overview, we build a clustered graph using the hierarchical structure annotated in the source code. To support exploration of nested structure on demand, we perform edge bundling to enable stable and responsive cluster expansion. Finally, we detect and highlight repeated structures to emphasize a model's modular composition. To demonstrate the utility of the visualizer, we describe example usage scenarios and report user feedback. Overall, users find the visualizer useful for understanding, debugging, and sharing the structures of their models. |
Databáze: | OpenAIRE |
Externí odkaz: |