This forum uses cookies
This forum makes use of cookies to store your login information if you are registered, and your last visit if you are not. Cookies are small text documents stored on your computer; the cookies set by this forum can only be used on this website and pose no security risk. Cookies on this forum also track the specific topics you have read and when you last read them. Please confirm whether you accept or reject these cookies being set.

A cookie will be stored in your browser regardless of choice to prevent you being asked this question again. You will be able to change your cookie settings at any time using the link in the footer.

Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Tinker edge T vs Raspberry pi 4B
#1
Hello, I build custom Convolution Neural Networks using tensorflow, keras etc as a hobby. I am using usually RaspberryPi, Nvidia Jetson nano etc. I am thinking of buying a device with TPU just for faster training as a first stage. I have a few questions to ask:

1) Will I see acceleration running the same code on Rpi 4B an the same code running on Tinker Edge T?
2) Does Tinker edge T support keras, tensorflow, pyTorch etc?
3) What are the differences between Tinker Edge T and Google Coral Dev?
4) Does it support Ubuntu?
5) Is there source code to learn how to use UART, I2C, SPI, etc?

Thank you
Reply
#2
1) Will I see acceleration running the same code on Rpi 4B an the same code running on Tinker Edge T?
-> If it is a general software tool, it should be able to run on each device.

2) Does Tinker edge T support keras, tensorflow, pyTorch etc?
-> If those can run on general CPU architecture, Tinker Edge T's CPU would also support like other platforms.
But if you are talking about Edge TPU, this ML accelerator only can support by TensorFlow Lite. (by Google)

3) What are the differences between Tinker Edge T and Google Coral Dev?
--> Both are using the same SoC & Edge TPU. But Tinker Edge T have more USB 3.0 (Type-A), and two MIPI-CSI ports, etc.
Also, we are using DC as the power input, enabling stable system operation and full I/O performance, even with multiple connected devices.

4) Does it support Ubuntu?
-> No, only Mendel OS, but it is Debian-based OS as same as Ubuntu is Debian-based too.

5) Is there source code to learn how to use UART, I2C, SPI, etc?
-> Bus functions are based-on general standard API, and here have some sample codes.
https://tinker-board.asus.com/doc_et.html#started
[-] The following 1 user Likes Tinker Board's post:
  • hobbyistprogrammer
Reply


Forum Jump:


Users browsing this thread: 1 Guest(s)