Towards Efficient Visual Simplification of Computational Graphs in Deep Neural Networks

12/21/2022
by   Rusheng Pan, et al.
0

A computational graph in a deep neural network (DNN) denotes a specific data flow diagram (DFD) composed of many tensors and operators. Existing toolkits for visualizing computational graphs are not applicable when the structure is highly complicated and large-scale (e.g., BERT [1]). To address this problem, we propose leveraging a suite of visual simplification techniques, including a cycle-removing method, a module-based edge-pruning algorithm, and an isomorphic subgraph stacking strategy. We design and implement an interactive visualization system that is suitable for computational graphs with up to 10 thousand elements. Experimental results and usage scenarios demonstrate that our tool reduces 60 recognizing and diagnosing DNN models. Our contributions are integrated into an open-source DNN visualization toolkit, namely, MindInsight [2].

READ FULL TEXT

page 1

page 2

page 4

page 5

page 7

page 8

page 9

page 11

research
08/12/2016

Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks

Deep neural network (DNN) models have recently obtained state-of-the-art...
research
09/14/2021

Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

While the recent advances in deep neural networks (DNN) bring remarkable...
research
08/15/2020

Skyline: Interactive In-Editor Computational Performance Profiling for Deep Neural Network Training

Training a state-of-the-art deep neural network (DNN) is a computational...
research
07/06/2020

EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

Finding out the computational redundant part of a trained Deep Neural Ne...
research
04/28/2005

k-core decomposition: a tool for the visualization of large scale networks

We use the k-core decomposition to visualize large scale complex network...
research
08/13/2020

Deep-Lock: Secure Authorization for Deep Neural Networks

Trained Deep Neural Network (DNN) models are considered valuable Intelle...
research
05/28/2020

Traditional Method Inspired Deep Neural Network for Edge Detection

Recently, Deep-Neural-Network (DNN) based edge prediction is progressing...

Please sign up or login with your details

Forgot password? Click here to reset