Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization
arXiv:2004.11250
Abstract
High-end mobile platforms rapidly serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications. However, the constrained computation and storage resources on these devices still pose significant challenges for real-time DNN inference executions. To address this problem, we propose a set of hardware-friendly structured model pruning and compiler optimization techniques to accelerate DNN executions on mobile devices. This demo shows that these optimizations can enable real-time mobile execution of multiple DNN applications, including style transfer, DNN coloring and super resolution.
arXiv commentaccepted by the IJCAI-PRICAI 2020 Demonstrations Track
References in corpus (8)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Learning Structured Sparsity in Deep Neural Networks
- Wide Activation for Efficient and Accurate Image Super-Resolution
- Exploring the Regularity of Sparse Structure in Convolutional Neural Networks
- An Entropy-based Pruning Method for CNN Compression
- Multi-style Generative Network for Real-time Transfer
- AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates