cancel
Showing results for 
Search instead for 
Did you mean: 

Not able to generate code for my customized input with Deep Learning model

allamjayaprakash
Associate II

I am using the STM32L496G-Disco board. I want to develop an AI model. I am trying to use https://stedgeai-dc.st.com/session. But when I give my data to generate files, launch quantization shows failure, and I do not get any error message in the terminal. Kindly provide me with a proper solution for customized inputs instead of random data. I also converted my data into.npz format.

Here, I am uploading my model and testing data, along with the .ioc file with random input. Getting help on these are very difficult, no help is available in internet even. Model is also available in ZIP file.

2 REPLIES 2
Julian E.
ST Employee

Hello @allamjayaprakash ,

 

Indeed, it seems that there is a bug in the Developer cloud when using your model.

Know that your model is very small already, for now, you can try to skip the quantization.

 

I will update you when I know more.

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.

Hello @allamjayaprakash,

 

It seems that for some, it seems that your model takes quite some time to quantize, and it triggers a timeout in the dev cloud. But sometimes it passes.

I attached the quantized model, I suggest you quantize it manually.

 

Note that as I said in my previous message, the quantized model is bigger than the non-quantized. 

All the quantize and dequantize layers add more weight than it has effect on the weights themselves..

 

Have a good day,

Julian


In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.