Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/afondiel/Introduction-to-On-Device-AI-DLAI

A comprehensive set of notes and resources for a crash course on deploying AI models on edge devices, provided by DeepLearningAI and taught by Krishna Sridhar from Qualcomm.
https://github.com/afondiel/Introduction-to-On-Device-AI-DLAI

edge-ai edge-computing edge-ml edge-vision embedded-ai embedded-ml lightweight-models on-device-ai on-device-deep-learning on-device-ml qualcomm smol-models

Last synced: about 2 months ago
JSON representation

A comprehensive set of notes and resources for a crash course on deploying AI models on edge devices, provided by DeepLearningAI and taught by Krishna Sridhar from Qualcomm.

Host: GitHub
URL: https://github.com/afondiel/Introduction-to-On-Device-AI-DLAI
Owner: afondiel
Created: 2024-10-25T15:18:18.000Z (3 months ago)
Default Branch: main
Last Pushed: 2024-12-04T15:22:25.000Z (2 months ago)
Last Synced: 2024-12-04T16:32:25.487Z (2 months ago)
Topics: edge-ai, edge-computing, edge-ml, edge-vision, embedded-ai, embedded-ml, lightweight-models, on-device-ai, on-device-deep-learning, on-device-ml, qualcomm, smol-models
Language: Jupyter Notebook
Homepage: https://learn.deeplearning.ai/courses/introduction-to-on-device-ai/lesson/1/introduction
Size: 7.81 MB
Stars: 1
Watchers: 1
Forks: 0
Open Issues: 0
Metadata Files:
- Readme: README.md

Awesome Lists containing this project

awesome-smol - Introduction to On-Device AI - Qualcomm
awesome-smol - Introduction to On-Device AI - Qualcomm

README

        # **Introduction to On-Device AI - Qualcomm (DeepLearningAI)**

## Overview

This is a comprehensive set of notes and resources for a crash course on deploying AI models on edge devices, provided by [DeepLearning.AI](https://www.DeepLearning.AI) and taught by [Krishna Sridhar](https://www.linkedin.com/in/srikris) from [Qualcomm](https://www.qualcomm.com).

**What you'll Learn**

- Learn to deploy AI models on edge devices like smartphones, using their local compute power for faster and more secure inference.

- Explore model conversion by, converting your PyTorch/TensorFlow models for device compatibility, and quantize them to achieve performance gains while reducing model size.

- Learn about device integration, including runtime dependencies, and how GPU, NPU, and CPU compute unit utilization affect performance.

**Prerequisites**

This course is designed for `beginner` AI developers, ML engineers, data scientists, and mobile developers looking to deploy optimized models on edge devices. Familiarity with `Python`, as well as `PyTorch` or `TensorFlow` is recommended.

## Course Outline

- [Introduction](./lab/chapters/slides/00_Intro/)    

- [Why On-Device?](./lab/chapters/slides/01_Why_on_device/)

- [Deploying Segmentation Models On-Device](./lab/chapters/slides/02_Deploying_Segmentation_Models_On_Device/)

- [Preparing for On-Device Deployment](./lab/chapters/slides/03_Preparing_for_on_device_deployment/)

- [Quantizing Models](./lab/chapters/slides/04_Quantizing_Models/)

- [Device Integration](./lab/chapters/slides/05_Device_Integration/)

- [Conclusion](./lab/chapters/slides/06_Conclusion/)

## Lab: Chapters & Notebooks

|Chapters|Notebooks|Demos|

|--|--|--|

|[Introduction](./lab/chapters/slides/00_Intro/)|-|-|

|[Why On-Device?](./lab/chapters/slides/01_Why_on_device/)|-|-|

|[Deploying Segmentation Models On-Device](./lab/chapters/slides/02_Deploying_Segmentation_Models_On_Device/)|[L2_Student.ipynb](./lab/notebooks/L2/L2_Student.ipynb)| - [ffnet_40 (on-device)](https://aihub.qualcomm.com/mobile/models/ffnet_40s) 
 - [ffnet_54s (on-device)](https://aihub.qualcomm.com/mobile/models/ffnet_54s)
 - [ffnet_78s (on-device)](https://aihub.qualcomm.com/mobile/models/ffnet_78s)
 - [ffnet_78s_lowres (on-device)](https://aihub.qualcomm.com/mobile/models/ffnet_78s_lowres)
 - [ffnet_122s_lowres (on-device)](https://aihub.qualcomm.com/mobile/models/ffnet_122ns_lowres)|

|[Preparing for On-Device Deployment](./lab/chapters/slides/03_Preparing_for_on_device_deployment/)|[L3_Student.ipynb](./lab/notebooks/L3/L3_Student.ipynb)|-|

|[Quantizing Models](./lab/chapters/slides/04_Quantizing_Models/)|[L4_Student.ipynb](./lab/notebooks/L4/L4_Student.ipynb)|-|

|[Device Integration (Final App)](./lab/chapters/slides/05_Device_Integration/)| [App/Project Guidelines](./lab/notebooks/final_demo/Appendix-Building_the_App.ipynb) |[Final Demo](./lab/notebooks/final_demo/)|

|[Conclusion](./lab/chapters/slides/06_Conclusion/)| - |-|

## Disclaimer

For important details about this repository's content, please review the [DISCLAIMER.md](./DISCLAIMER.md).

## References

- [Main course - DeepLearning.AI](https://www.deeplearning.ai/short-courses/introduction-to-on-device-ai/)