OpenMV H7 with MicroSD Card

[joaop]

I was using a 16gb MicroSD card to load i model for image classifcation :

but, i try one code to search the MicroSD card to see the files :

import os
print(os.listdir("/sd"))  # Lista os arquivos dentro do microSD

But, this error appears :

can someone help me to solve this problem ?

[kwagyeman]

Hi, the folder name is “/sdcard”.

Your OpenMV Cam with the latest firmware runs this on startup: openmv/scripts/libraries/_boot.py at master · openmv/openmv

[joaop]

So i use the base code from edge impulse when i generate the model for classifcation images, but i can’t load the model, do you know any command can i load. And i use “/sdcard”, but the error continues. And what is the maximum RAM openMV H7 can work ?

[kwagyeman]

Hi, the H7 can’t load a 674KB network. It doesn’t have enough RAM. Please use the H7 Plus. You can try building the model into the H7’s firmware. However, even then it’s still too big.

[joaop]

net = tf.load("trained.tflite", load_to_fb=True)  # load_to_fb=True pode ajudar para modelos grandes

On the forum, it says that the command exists, but the error says it doesn’t? I made the model using edge impulse

[kwagyeman]

Hi, we removed that module last year.

Please see the porting guide:

OpenMV Firmware v4.5.6 and up TensorFlow Porting Guide

Hi all, In our latest firmware, 4.5.6, we’ve completely updated how our TensorFlow API works. This is a breaking change. But, the functionality increase is worth it. Here are the details: The “tf” module is now gone (although there may be an alias to it for a while). You should now start using the new “ml” module. This will be where we keep any machine-learning code in the firmware. We decided to do the module renaming because as we support more MCUs with CNN accelerators (NPUs), it will not a…

And update your firmware to the latest.