# OS error with OpenMV cam H7

**URL:** <https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498>\
**Category:** OpenMV Boards\
**Created:** [November 1, 2021, 9:28am UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498 "2021-11-01T09:28:09Z")\
**Posts on this page:** 11\
**Page:** 1

<div class="post-metadata">

**Author:** ![mvitswd](https://avatars.discourse-cdn.com/v4/letter/m/4bbf92/32.png) [@mvitswd](https://forums.openmv.io/u/mvitswd)\
**Post date:** [November 1, 2021, 9:28am UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/1 "2021-11-01T09:28:09Z")

</div>

Hi,  
I have an OpenMV cam H7 (non plus) and I am trying to deploy a model trained with Edge Impulse. I have tried different models and got a model  
small enough that can fit in the device. I have used a small image input (48x48) and a mobilenet V2 0.1.  
I copied the tensorflow lite and labels files to the SD card and run the python code, but I always get OS error and no other info:

Traceback (most recent call last):  
File “”, line 21, in  
OSError:  
MicroPython: v1.15-r57 OpenMV: v4.1.1 HAL: v1.9.0 BOARD: OPENMV4-STM32H743  
Type “help()” for more information.

is there a way to get more debug/error info?

I am happy to upload the code (as a new user I can’t).

Thanks,  
Matteo

---

<div class="post-metadata">

**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\
**Post date:** [November 4, 2021, 3:04pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/2 "2021-11-04T15:04:03Z")

</div>

Hi, I can’t tell what the error is. When the above is happening it means that the TensorFlow library did not return an error string for the error but just threw an error.

How is your model different from the normal TensorFlow models on edge impulse?

---

<div class="post-metadata">

**Author:** ![mvitswd](https://avatars.discourse-cdn.com/v4/letter/m/4bbf92/32.png) [@mvitswd](https://forums.openmv.io/u/mvitswd)\
**Post date:** [November 4, 2021, 3:52pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/3 "2021-11-04T15:52:30Z")

</div>

Hi @kwagyeman,  
it is a fairly standard model created using transfer learning from edge impulse. Do you have any suggestions on how to upload the model? I can’t upload it to this message since I am a new user.

Thanks,  
Matteo

---

<div class="post-metadata">

**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\
**Post date:** [November 4, 2021, 5:02pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/4 "2021-11-04T17:02:57Z")

</div>

Just put it in a zip file.

---

<div class="post-metadata">

**Author:** ![mvitswd](https://avatars.discourse-cdn.com/v4/letter/m/4bbf92/32.png) [@mvitswd](https://forums.openmv.io/u/mvitswd)\
**Post date:** [November 4, 2021, 5:57pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/5 "2021-11-04T17:57:45Z")

</div>

Hi @kwagyeman  
unfortunately I can’t upload a file as new user.

I have uploaded it to gdrive [model](https://drive.google.com/file/d/1x2otUwMlkXJftuFDfMKasIm2jHlg7DkF/view?usp=sharing)

Thanks and regards,  
Matteo

---

<div class="post-metadata">

**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\
**Post date:** [November 4, 2021, 6:40pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/6 "2021-11-04T18:40:18Z")

</div>

Hi sorry, I don’t actually have any way of debugging this issue. The only thing I can offer is that we’re almost done porting to the new version of TF Lite. I don’t actually have any tools to determine what the error is either. However, the OpenMV Cam firmware is running an older version of TF Lite. So, I’m guessing the error is related to Edge Impulse updating their system.

---

<div class="post-metadata">

**Author:** ![thedigitalguru](https://avatars.discourse-cdn.com/v4/letter/t/d6d6ee/32.png) [@thedigitalguru](https://forums.openmv.io/u/thedigitalguru)\
**Post date:** [November 6, 2021, 7:19pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/7 "2021-11-06T19:19:32Z")

</div>

I have this same exact issue. I have upgraded to windows 11 from windows 10 but idk why it specifically gives me the same traceback in the same line, line 21

---

<div class="post-metadata">

**Author:** ![thedigitalguru](https://avatars.discourse-cdn.com/v4/letter/t/d6d6ee/32.png) [@thedigitalguru](https://forums.openmv.io/u/thedigitalguru)\
**Post date:** [November 6, 2021, 7:21pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/8 "2021-11-06T19:21:50Z")

</div>

how long until done porting to the new version of TF lite? I can try again then

---

<div class="post-metadata">

**Author:** ![kwagyeman](https://yyz1.discourse-cdn.com/flex029/user_avatar/forums.openmv.io/kwagyeman/32/4_2.png) [@kwagyeman](https://forums.openmv.io/u/kwagyeman)\
**Post date:** [November 8, 2021, 3:32pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/9 "2021-11-08T15:32:46Z")

</div>

I finished all the porting work. However, the latest version of it has segfaults in it. The person detector network does run 6x faster though.

I have to switch to a more stable branch again and I just haven’t found time. I hope to have time to do the changes and merge everything next week.

---

<div class="post-metadata">

**Author:** ![jlutzwpi](https://avatars.discourse-cdn.com/v4/letter/j/ba8739/32.png) [@jlutzwpi](https://forums.openmv.io/u/jlutzwpi)\
**Post date:** [December 22, 2021, 4:17pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/10 "2021-12-22T16:17:23Z")

</div>

I get the same error. Trying to run an Edge Impulse model (300 kb size) from an SD card.

The only error I received is the same one as Matteo gets when the python script attempts to classify with tensorflow.

---

<div class="post-metadata">

**Author:** ![jlutzwpi](https://avatars.discourse-cdn.com/v4/letter/j/ba8739/32.png) [@jlutzwpi](https://forums.openmv.io/u/jlutzwpi)\
**Post date:** [December 22, 2021, 5:50pm UTC](https://forums.openmv.io/t/os-error-with-openmv-cam-h7/6498/11 "2021-12-22T17:50:51Z")

</div>

For what it’s worth, I was just able to follow this tutorial and get the python scrip to run in the OpenMV IDE:

> **[Mega or Mini? Image Classification on the 1MB OpenMV Cam H7](https://www.hackster.io/ishotjr/mega-or-mini-image-classification-on-the-1mb-openmv-cam-h7-be57ac)**
>
> Edge Impulse published a tutorial on how to add sight to the 32MB OpenMV Cam H7 Plus - but can we get it to work on the 1MB H7 model? 🤔 By Ish Ot Jr..

Looks like the MobileNetV2 0.1 model fits on the H7 R2.
