Rapid-INR: Storage Efficient CPU-Free DNN Training Using Implicit Neural Representation
Authors:
- 28 October 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Abstract
Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous research has demonstrated the effectiveness of using neural networks as INR for image compression, showcasing comparable performance to traditional methods such as JPEG. However, INR holds potential for various applications beyond image compression. This paper introduces Rapid-INR, a novel approach that utilizes INR for encoding and compressing images, thereby accelerating neural network training in computer vision tasks. Our methodology involves storing the whole dataset directly in INR format on a GPU, mitigating the significant data communication overhead between the CPU and GPU during training. Additionally, the decoding process from INR to RGB format is highly parallelized and executed on-the-fly. To further enhance compression, we propose iterative and dynamic pruning, as well as layer-wise quantization, building upon previous work. We evaluate our framework on the image classification task, utilizing the ResNet-18 backbone network and three commonly used datasets with varying image sizes. Rapid-INR reduces memory consumption to only 5% of the original dataset size and achieves a maximum 6× speedup over the PyTorch training pipeline, as well as a maximum 1.2× speedup over the DALI training pipeline, with only a marginal decrease in accuracy. Importantly, Rapid-INR can be readily applied to other computer vision tasks and backbone networks with reasonable engineering efforts. Our implementation code is publicly available at https://github.com/sharc-lab/Rapid-INR.Keywords
All Related Versions
Funding Information
- National Science Foundation (2202329)
This publication has 11 references indexed in Scilit:
- Implicit Neural Representations for Image Compression2022
- NeRFCommunications of the ACM, 2021
- Synthetic data in machine learning for medicine and healthcareNature Biomedical Engineering, 2021
- pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis2021
- A Review on Natural Language Processing: Back to Basics2021
- A survey of deep learning techniques for autonomous drivingJournal of Field Robotics, 2019
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation2019
- Occupancy Networks: Learning 3D Reconstruction in Function Space2019
- Deep Residual Learning for Image Recognition2016
- Automated Flower Classification over a Large Number of Classes2008