Return to search

Pruning Convolution Neural Network (SqueezeNet) for Efficient Hardware Deployment

<p>In recent years, deep learning models have become popular in
the real-time embedded application, but there are many complexities for
hardware deployment because of limited resources such as memory, computational
power, and energy. Recent research in the field of deep learning focuses on
reducing the model size of the Convolution Neural Network (CNN) by various
compression techniques like Architectural compression, Pruning, Quantization,
and Encoding (e.g., Huffman encoding). Network pruning is one of the promising
technique to solve these problems.</p>

<p>This thesis proposes methods to
prune the convolution neural network (SqueezeNet) without introducing network
sparsity in the pruned model. </p>

<p>This thesis proposes three methods to prune the CNN to
decrease the model size of CNN without a significant drop in the accuracy of
the model.</p>

<p>1: Pruning based on Taylor expansion of change in cost
function Delta C.</p>

<p>2: Pruning based on L<sub>2</sub> normalization of activation maps.</p>

<p>3: Pruning based on a combination of method 1 and method 2.</p><p>The proposed methods use various
ranking methods to rank the convolution kernels and prune the lower ranked
filters afterwards SqueezeNet model is fine-tuned by backpropagation. Transfer
learning technique is used to train the SqueezeNet on the CIFAR-10 dataset.
Results show that the proposed approach reduces the SqueezeNet model by 72%
without a significant drop in the accuracy of the model (optimal pruning
efficiency result). Results also show that Pruning based on a combination of
Taylor expansion of the cost function and L<sub>2</sub> normalization of activation maps
achieves better pruning efficiency compared to other individual pruning
criteria and most of the pruned kernels are from mid and high-level layers. The
Pruned model is deployed on BlueBox 2.0 using RTMaps software and model
performance was evaluated.</p><p></p>

  1. 10.25394/pgs.7418480.v1
Identiferoai:union.ndltd.org:purdue.edu/oai:figshare.com:article/7418480
Date17 January 2019
CreatorsAkash Gaikwad (5931047)
Source SetsPurdue University
Detected LanguageEnglish
TypeText, Thesis
RightsCC BY 4.0
Relationhttps://figshare.com/articles/Pruning_Convolution_Neural_Network_SqueezeNet_for_Efficient_Hardware_Deployment/7418480

Page generated in 0.0026 seconds