ML - machine learning
This is just a documentation of my learning progress. Inspired by object detection for cars with DarkNet (see this TED talk from 2017 by Joseph Redmon) and David’s bachelor work at HCMUTE in connection with a car at the end of 2018 I started to learn more about machine learning.
Posenet runs on TensorFlow.lite in a browser on WebGL even on a smartphone. We tested it in December 2018 in Seoul, Korea. In March 2019 I got TensorFlow.js running with my RX470 with 43 fps.
During 2019 NVIDIA announced the Jetson Nano developer kit and with students from AISVN we try to win one in a competition. Eventually we order a package.
Early 2020 some supply chains delay orders, but we finally have the hardware. Now it needs to be combined - and development stalls until 2024.
Facemesh example
Schedule
In this article Harsheev Desai describes his journey to become a TensorFlow Developer with Certificate in 5 months.
1. Learn Python
2. Learn Machine Learning Theory
- Coursera Machine Learning on Statistics, Calculus and Linear Algebra
3. Learn Data Science Libraries
Some of these libraries are Pandas (data manipulation and analysis), Numpy (support for multi-dimensional arrays and matrices), Matplotlib (plotting) and Scikitlearn (creating ML models).
4. Deep Learning Theory
5. TensorFlow Certificate
One reason for tensorflow can be seen in this graph regarding popularity on stack overflow:
More about the certificate here on medium. It was introduced in March 2020 but by 2024 it no longer exists.
History
- July 2024 Reactivated the https://kreier.github.io/jetson-car/ project. The hardware is from 2019 (NVIDIA) but the software is still Ubuntu 18.04 LTS. Updates brake simple things like
make
andgcc
. - February 2020 The Jetson car is purchased, Wifi module and 7” display as well. Needs completion - without students due to COVID-19
- December 2019 On hackster.io starts a new competition AI at the Edge Challenge where you can win a Jetson Nano. I apply and eventually just buy one from arrow
- March 2019 posenet runs in the browser with new RX470 with 43 fps
- December 2018 TensorFlow.lite in a browser on my iPhone 7 runs at 6 fps, demonstrated in Seoul
- October 2018 Successful installed darknet on ubuntu, object detection works for stills. Don’t have a webcam, video does not work yet.