# Amebapro2 AI Model Conversion - Issue
**URL:** https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022
**Category:** AI
**Tags:** rtl8735b, evb-amb82
**Created:** [June 9, 2024, 7:48pm UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022 "2024-06-09T19:48:43Z")
**Posts on this page:** 6
**Page:** 1
### Author:  [@moschtrain](https://forum.amebaiot.com/u/moschtrain)
#### Post date: [June 9, 2024, 7:48pm UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022/1 "2024-06-09T19:48:43Z")
Hi,
> **[Amebapro2 AI Convert Model – Realtek IoT/Wi-Fi MCU Solutions](https://www.amebaiot.com/en/amebapro2-ai-convert-model/)**
i’m trying to convert a yolov7-tiny trained model ([darknet](https://github.com/pjreddie/darknet/issues/2557)) to a NB file but get and error that it doesn’t work:
Error: Using your cfg and weights files can not export binary file, you can see more details on the attached zip file.
[application.zip](https://forum.amebaiot.com/uploads/short-url/5e3T4EATcOJJJOGa3Xi0FWAAcs1.zip) (26,7 KB)
```auto
some "parts" of the export log:
2024-05-26 00:49:40.484591: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory
2024-05-26 00:49:43.791105: W tensorflow/stream_executor/cuda/cuda_driver.cc:312] failed call to cuInit: UNKNOWN ERROR (303)
2024-05-26 00:49:43.791130: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (5fec6c973be1): /proc/driver/nvidia/version does not exist
```
Can you please check the attached zip/log that came with “your” email and let me know the problem?
I also tried to convert a model that i used in december. In december it worked fine but now i’m getting the error with this as well - so something must be work with your conversion service
Thanks for your help
---
### Author:  [@Kelvin\_Huang](https://forum.amebaiot.com/u/Kelvin_Huang)
#### Post date: [June 10, 2024, 6:33am UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022/2 "2024-06-10T06:33:44Z")
Hi,
Can I check if you selected YOLOv7-TINY-Pytorch? Please use YOLO-TINY for darknet object detection models.
Thank you.
---
### Author:  [@moschtrain](https://forum.amebaiot.com/u/moschtrain)
#### Post date: [June 10, 2024, 8:03am UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022/3 "2024-06-10T08:03:42Z")
yes of course, i selected YOLO-TINY for conversion
BTW: tried it right now again. Same issue
[application.zip](https://forum.amebaiot.com/uploads/short-url/5D6AbPL6GWc6sKc87A9sJrbE7qo.zip) (26,7 KB)
---
### Author:  [@Kelvin\_Huang](https://forum.amebaiot.com/u/Kelvin_Huang)
#### Post date: [June 11, 2024, 4:50am UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022/4 "2024-06-11T04:50:22Z")
Hi @moschtrain,
Can you give it a try again? Have you succeeded in any conversion yesterday?
Thank you.
---
### Author:  [@moschtrain](https://forum.amebaiot.com/u/moschtrain)
#### Post date: [June 11, 2024, 7:42pm UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022/5 "2024-06-11T19:42:30Z")
Hi Kelvin,
yes i tried it yesterday with INT16 conversion and it worked (INT8 conv wasn’t working as described). Unfortunately the frame rate of the amb82-mini was too slow (~1-2 fps).
Today i tired the INT8 conversion again and it worked too. Frame rate is ok now. BTW: no changes to my weights and cfg files… Did you fix something on the backend?
Thanks for your help
---
### Author:  [@Kelvin\_Huang](https://forum.amebaiot.com/u/Kelvin_Huang)
#### Post date: [June 12, 2024, 1:30am UTC](https://forum.amebaiot.com/t/amebapro2-ai-model-conversion-issue/3022/6 "2024-06-12T01:30:54Z")
Hi @moschtrain,
My colleague have troubleshooted the issue and fixed on the server side.
Thanks for your feedback to allow us to know there exists this issue.