search

Qengineering / BananaPi-M2-Zero-OV5640

Banana Pi M2 zero with OV5640, WiringPi and OpenCV image.
https://qengineering.eu/deep-learning-with-raspberry-pi-and-alternatives.html
BSD 3-Clause "New" or "Revised" License
37 stars 4 forks source link

Mediapipe #7

Open fathysr opened 1 year ago

fathysr commented 1 year ago

Does the mediapipe library work on m2 zero?

Qengineering commented 1 year ago

I'm not sure. Please be so kind and try to install mediapipe to find out. Can you give me the outcome, if you decide to proceed?

fathysr commented 1 year ago

I don't own banana pi but I'm thinking of buying it for the project we're going to do. I have raspberry pi zero but mediapipe is not working.

Qengineering commented 1 year ago

From the first glance it looks as if mediapipe will run on the M2-zero. There are no real showstoppers. The only worry is the amount of RAM. 500MB is not much. https://google.github.io/mediapipe/getting_started/install.html

fathysr commented 1 year ago

I'm thinking of doing image manipulation and this is the most important library in my code. That's why I'm trying to do a detailed research because my budget is limited. Thank you for your help 💯

Qengineering commented 1 year ago

I understand. If I could, I would like to help you further. However, not the installation of mediapipe is your curl pit, but the deep learning software. With the Armbian OS running, you have about 250~300 MB left over for your app. If you need bazel to start the app, you have another memory hungry guest at your table. Try to figure out how much memory your app needs by running htop on the Linux machine where your mediapipe app is running.

fathysr commented 1 year ago

I have no choice but to try. Thank you you're so kind