InstantNet: Automated Generation and Deployment of Instantaneously Switchable-Precision Networks
arXiv:2104.10853
Abstract
The promise of Deep Neural Network (DNN) powered Internet of Thing (IoT) devices has motivated a tremendous demand for automated solutions to enable fast development and deployment of efficient (1) DNNs equipped with instantaneous accuracy-efficiency trade-off capability to accommodate the time-varying resources at IoT devices and (2) dataflows to optimize DNNs' execution efficiency on different devices. Therefore, we propose InstantNet to automatically generate and deploy instantaneously switchable-precision networks which operate at variable bit-widths. Extensive experiments show that the proposed InstantNet consistently outperforms state-of-the-art designs.
Accepted at DAC 2021
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Neural Architecture Search with Reinforcement Learning
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Scalable Methods for 8-bit Training of Neural Networks
- Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search
- AutoGAN-Distiller: Searching to Compress Generative Adversarial Networks
- FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
- Joint Neural Architecture Search and Quantization
- AdaBits: Neural Network Quantization with Adaptive Bit-Widths
- Switchable Precision Neural Networks
- CPT: Efficient Deep Neural Network Training via Cyclic Precision