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
Posted Content
Learning Filter Basis for Convolutional Neural Network Compression.
TL;DR: In this paper, the authors proposed to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers and then using the learned basis to approximate the original filters for the forward pass.
Journal ArticleDOI
Inference-aware convolutional neural network pruning
TL;DR: In this paper , a Bayesian optimization-based method for automatically determining the appropriate number of filters for each convolutional layer was proposed to reduce the number of parameters to be pruned without significantly affecting the model performance.
Proceedings ArticleDOI
Width transfer: on the (in)variance of width optimization
TL;DR: In this article, the authors proposed width transfer, a technique that harnesses the assumption that the optimized widths (or channel counts) are regular across sizes and depths, and achieved up to 320× reduction in width optimization overhead without compromising the top-1 accuracy on ImageNet.
Posted Content
Deep discriminant analysis for task-dependent compact network search
TL;DR: This paper proposes an iterative and proactive approach for classification tasks which alternates between a pushing step, with an objective to simultaneously maximize class separation, penalize co-variances, and push deep discriminants into alignment with a compact set of neurons, and a pruning step, which discards less useful or even interfering neurons.
Posted Content
EPNAS: Efficient Progressive Neural Architecture Search
TL;DR: Efficient Progressive Neural Architecture Search (EPNAS) is a neural architecture search (NAS) that efficiently handles large search space through a novel progressive search policy with performance prediction based on REINFORCE~\cite{this http URL}.
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.