https://github.com/mit-han-lab/tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
https://github.com/mit-han-lab/tinyengine

c codegenerator cpp deep-learning edge-computing microcontroller neural-architecture-search pytorch quantization tinyml

Last synced: about 13 hours ago
JSON representation

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

• Host: GitHub
• URL: https://github.com/mit-han-lab/tinyengine
• Owner: mit-han-lab
• License: mit
• Created: 2022-08-24T19:42:28.000Z (over 2 years ago)
• Default Branch: main
• Last Pushed: 2024-11-27T18:51:37.000Z (6 months ago)
• Last Synced: 2025-03-18T11:38:51.901Z (about 2 months ago)
• Topics: c, codegenerator, cpp, deep-learning, edge-computing, microcontroller, neural-architecture-search, pytorch, quantization, tinyml
• Language: C
• Homepage: https://mcunet.mit.edu
• Size: 235 MB
• Stars: 843
• Watchers: 21
• Forks: 137
• Open Issues: 36
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - mit-han-lab/tinyengine - 算法协同设计框架。TinyEngine和TinyNAS共同设计以适应严格的内存预算，项目特色包括：内存高效、高性能、支持微控制器上的深度学习，并提供推理和训练演示。MCUNetV1、MCUNetV2和MCUNetV3分别在NeurIPS2020、NeurIPS 2021和NeurIPS 2022上发表。 (其他_机器学习与深度学习)