About GWang.3

GWang.3 · 2021-04-11

I'm trying to use STM32AI quantize -q .json to quantize a Keras .H5. However, I never got it working.Version: STM32 XCUBE-AI 6.0.0tensorflow: I tried tf 2.0 and tf 1.15 installed Platform. tried on both window and Linux (ubuntu 18.04)Command line:C:\...

GWang.3 · 2021-04-07

I am trying to follow the DM00570145 and validate on target (STM32F746 Discovery Board, XCUBE-AI 6.0.0, toolchain: STM32CUBE IDE), I cannot get the output listed on Figure 61. "Layer by layer results - Validation on target", especially the "ms" runni...

GWang.3 · 2020-12-15

I used TouchGFX generator 4.15.0 to create a simple project (from GUI Template) on STM32F746 Discovery board, inside TouchGFX generator, "Run Simulator", "Run on Target" and "Generate Code" all are working correctly. However, when I tried to open the...

GWang.3 · 2021-04-15

I was able to figure it out. The STM XCUBE-AI uses its own Python packages and Python version. When we are creating customized dataset, we can only use available packages in that folder \6.0.0\Utilities.

GWang.3 · 2021-04-15

Actually, it didn't solve my problem. I tried the example Mnist, it is working fine. However, the same approach didn't work for cfg_kws_ss_sa.json and also cfg_kws_ua_ua.json. I also created my own Har.json. Here is my json file:{ "model_name": "H...

GWang.3 · 2021-04-11

Method 1: #include <stdio.h> float f1; char buffer[20]; sprintf(buffer,"%7.2f\n",f1); However, sprintf may not be thread-safe.Method 2: - thread-safe approach// display f1 in %7.2f format, assuming fl>=0float f1;uint32_t f1_int,f1_frac;f1_int =f1...

GWang.3 · 2021-04-08

never mind, I was able to figure it out. (do not choose "automatic compilation and download"). Please close this topic.

GWang.3 · 2021-04-07

I was not able to close this topic since I didn't initiate this topic. Thanks, Houda.

User statistics

User Activity

stm32ai quantize error?

Validation on Target - running time layer by layer

Issues of TouchGFX Generator 4.15.0 on STM32F746 Discovery Board, Toolchain Keil MDK

Re: stm32ai quantize error?

Re: stm32ai quantize error?

Re: How to print Float values on Keil IDE

Re: Validation on Target - running time layer by layer

Re: Platform Settings Tab missing on configuration of X-CUBE-AI