proposal
personal information
Name : Zitong Li
Time zone : UTC+8
Mail : cnlizitong@gmail.com or 202030481167@mail.scut.edu.cn
IRC : @lzt0828:matrix.org
School : South China University of Technology
Skill : C++, java, python, HTML, CSS, JavaScript, git, Some basic machine learning and AI knowledge (gradient descent, neural networks, etc.)
ABOUT project
Project name : GPT with OpenCV
Overview : Tune GPT on latest OpenCV; create examples/blog on how to use GPT to leverage DNN and other OpenCV functionality; create an OpenAI GPT API assuming we get such access off the waitlist.
Benefit : Adjust and optimize GPT in the latest opencv, so that the corresponding functions of GPT can be used normally in opencv and enhance the performance of opencv. At the same time, I will write relevant operational and technical documents for other contributors and users to read. Finally, if possible, I will write an API that users can use to adjust their models, and at the same time use the functions of GPT to help them train the models and install them on the corresponding hardware.
Deliverables
1.Tuning GPT on OpenCV 4.7+ code and Github bases.
2.Documentation and blog or YouTube videos of using GPT to leverage OpenCV functions and internals of OpenCV.
3.Assuming we get early access to the GPT API, create an API that has useful functionality to OpenCV and its applications. Potentially have some DNN models where users can tune the models to their data that they provide, but GPT would know how to trains such models and get them on given hardware like OAK cameras, Mac, Windows, Linux.
PLAN
May 4th to May 28th | Establish contact with mentors, read project-related documents and codes, and get started quickly. |
---|---|
May 29th to July 10th | Estimate and plan the overall progress of the project, adjust GPT on the basis of opencv4.7+, and write related documents and videos on how to use GPT in opencv, so that users and other contributors can understand the situation. ( Mid-term acceptance) |
July 11th to August 21st | Create an API that has useful functionality to OpenCV and its applications. Users can tune the models to their data that they provide, but GPT would know how to trains such models and get them on given hardware. ( Final acceptance) |
communication
I think the most important factor in this activity is to maintain real-time communication with the mentor, and I can make sure that I can keep in touch with the mentor. Mentors can contact me in various ways, such as email, matrix, etc. If necessary, the mentor can also communicate with me by voice from 3:00 pm to 9:00 pm (UTC+8).
qualification
Why join this project : The needs of this project matched the skills I had and I thought the project would be interesting and as a newcomer to GSoC for the first time I thought this project would be a good start for me.
how will i benefit : As a novice, I will gain the experience of participating in the open source community, which is the most important thing. At the same time I can consolidate my existing skills and learn new ones.
After the project is completed : After this project ends, I will be an experienced open source contributor and I will continue to contribute to the opencv community.
my skills : The language I know best is C++, and I also have some knowledge of front-end development, such as HTML, CSS, JavaScript, and I have systematically studied machine learning and artificial intelligence at school, and I have a certain understanding of some necessary knowledge and concepts, which will help me get started quickly in projects.
Have I developed free software before? : No, this will be my first experience.
Something else : As a novice, I have a very strong desire to learn, if my ability is not enough to meet the needs of the project, please don’t worry, just give me some documents and learning materials, I will learn them as soon as possible. Please don’t worry that I will lose contact in the progress of the project. I can guarantee that during the project, the mentor can get in touch with me at any time, and I will actively report the progress I have made and the difficulties I have encountered, and actively communicate with the mentor.