Structured Model Pruning of Convolutional Networks on Tensor Processing Units
The deployment of convolutional neural networks is often hindered by high computational and storage requirements. Structured model pruning is a promising approach to alleviate these requirements. Using the VGG-16 model as an example, we measure the accuracy-efficiency trade-off for various structured model pruning methods and datasets (CIFAR-10 and ImageNet) on Tensor Processing Units (TPUs). To measure the actual performance of models, we develop a structured model pruning library for TensorFlow2 to modify models in place (instead of adding mask layers). We show that structured model pruning can significantly improve model memory usage and speed on TPUs without losing accuracy, especially for small datasets (e.g., CIFAR-10).
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Speedup deep learning models on GPU by taking advantage of efficient unstructured pruning and bit-width reduction
This work is focused on the pruning of some convolutional neural networks (CNNs) and improving theirs efficiency on graphic processing units (GPU) by using a direct sparse algorithm. The Nvidia deep neural network (cuDnn…
GPUQuantizationDirichlet Pruning for Neural Network Compression
We introduce Dirichlet pruning, a novel post-processing technique to transform a large neural network model into a compressed one. Dirichlet pruning is a form of structured pruning that assigns the Dirichlet distribution…
Neural Network CompressionVariational InferenceDesigning Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition
Deep neural networks (DNNs) are nowadays witnessing a major success in solving many pattern recognition tasks including skeleton-based classification. The deployment of DNNs on edge-devices, endowed with limited time and…
Gesture RecognitionHand Gesture RecognitionHand-Gesture RecognitionTowards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression. However, these two techniques are traditionally deployed in an isolated manner, leading to significa…
Neural Network CompressionTensor DecompositionTowards Efficient Deep Spiking Neural Networks Construction with Spiking Activity based Pruning
The emergence of deep and large-scale spiking neural networks (SNNs) exhibiting high performance across diverse complex datasets has led to a need for compressing network models due to the presence of a significant numbe…
Model CompressionNetwork PruningSparse Learning