AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Yihui He,Ji Lin,Zhijian Liu,Hanrui Wang,Li-Jia Li,Song Han +5 more
- pp 784-800
Reads0
Chats0
TLDR
This paper proposes AutoML for Model Compression (AMC) which leverages reinforcement learning to efficiently sample the design space and can improve the model compression quality and achieves state-of-the-art model compression results in a fully automated way without any human efforts.Abstract:
Model compression is an effective technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted features and require domain experts to explore the large design space trading off among model size, speed, and accuracy, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Model Compression (AMC) which leverages reinforcement learning to efficiently sample the design space and can improve the model compression quality. We achieved state-of-the-art model compression results in a fully automated way without any human efforts. Under 4\(\times \) FLOPs reduction, we achieved 2.7% better accuracy than the hand-crafted model compression method for VGG-16 on ImageNet. We applied this automated, push-the-button compression pipeline to MobileNet-V1 and achieved a speedup of 1.53\(\times \) on the GPU (Titan Xp) and 1.95\(\times \) on an Android phone (Google Pixel 1), with negligible loss of accuracy.read more
Citations
More filters
Journal ArticleDOI
Layer-adaptive Structured Pruning Guided by Latency
TL;DR: In this article , a global importance score (LAMP) is derived from unstructured pruning to structured pruning, and a group knapsack solver is used to maximize the LAMP score under latency constraints.
Posted Content
Network Pruning using Adaptive Exemplar Filters.
TL;DR: In this paper, an adaptive exemplar filter was proposed to simplify the pruning algorithm and achieved state-of-the-art performance on VGGNet-16 and ResNet-152.
Posted Content
Group Fisher Pruning for Practical Network Compression
Liyang Liu,Shilong Zhang,Zhanghui Kuang,Aojun Zhou,Jing-Hao Xue,Xinjiang Wang,Yimin Chen,Wenming Yang,Qingmin Liao,Wayne Zhang +9 more
TL;DR: In this article, the authors proposed a general channel pruning approach that can be applied to various complicated structures, such as residual connections, group/depth-wise convolution and feature pyramid networks.
RepSGD: Channel Pruning Using Reparamerization for Accelerating Convolutional Neural Networks
TL;DR: In this paper , a new point-wise convolution layer is added to the standard convolutional layer to produce filter redundancy, and the redundant filters are pruned using the original gradient.
Proceedings ArticleDOI
An Algorithm for Automated Search Model with Pruning Structure based on Big Data
TL;DR: In this article , a compressed pruning scheme for convolutional neural networks based on automated search is proposed to address the problem that convolution neural networks consume many computational resources under large data.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Posted Content
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Batch Normalization as mentioned in this paper normalizes layer inputs for each training mini-batch to reduce the internal covariate shift in deep neural networks, and achieves state-of-the-art performance on ImageNet.
Dissertation
Learning Multiple Layers of Features from Tiny Images
TL;DR: In this paper, the authors describe how to train a multi-layer generative model of natural images, using a dataset of millions of tiny colour images, described in the next section.