Getting Started with STM32Cube.AI

[@sorrefly]

This is literally awesome. I'm using it to classify EMG response in muscular contraction for prosthesis hand

[@dhruvsheth7260]

STM32 Rocks

[@embedded2523]

Hi，the code is successfully generated and built on cubeide，download to the board and it passed the validation on desktop.However it says fatal error Stm32f4xx_hal.h No such file or dictionary when I click the validation on target.What may lead to this happen , please help me.

[@fernando.liozzi.41878]

Hello thank you very much. I did a course on neural networks with keras in EDX, and I can now train, save and load my networks on an STM32F4VE, with compression 8. The verification with my data set works well. And now how do I continue? How do I send my data to the STM32 to make predictions? Thanks

[@ElectroFreak2000]

There seems to be very little information on actually using the models on an STM board. You need to load the example template instead of the validation program at the start of the process and there is info in those files on functions etc. but it is very confusing.

[@SonefromChina]

very good! i was working on tensorflow and cmsis-nn convert for months, thanks for this tool , maybe it can finish my work in days

[@shubhamsharmaa001]

Let me know when you completed it successfully i need a little guidance

[@stmicroelectronics]

great ! thanks for the feedback.

[@wuqiwang1716]

@@stmicroelectronics I want to know what decide the minimum RAM, because i change the model a lot, but the minimum RAM dosn't decrease much and exceed my chip RAM size

[@wuqiwang1716]

@@stmicroelectronics and if there is forum or blog places for learning and exhange ideas?

[@stmicroelectronics]

@@wuqiwang1716 hi - we really recommend to check out community.st.com/s/topic/0TO0X0000003iUqWAI/machine-learning-ai for questions on this topic.

[@AkshitSharma1824]

the output of the model shows that it is running with the inputs (10,90,3,1).it is not clear from this output where these inputs came from or how they were generated.

[@johnhe6833]

Actually, I follow the step in the video and face a problem when I validate on desktop. It shows there are 12r errors.

[@ttaylor9916]

@3:10 get error "invalid network".

[@fernando.liozzi.41878]

Hi, once I passed the verification on the microcontroller. How does the thing go? How do I enter data by usart, i2c, spi, etc. and that the neural network make the prediction? This only loads verification modules. I want prediction modules. Greetings.

[@linben8110]

I have the same question as yours.

[@fernando.liozzi.41878]

@@linben8110 www.st.com/content/ccc/resource/technical/document/user_manual/group1/69/bb/ec/5d/78/16/43/ce/DM00570145/files/DM00570145.pdf/jcr:content/translations/en.DM00570145.pdf

[@fernando.liozzi.41878]

@@linben8110 Please, see page 15, and help me understand please. Thanks and regards.

[@ElectroFreak2000]

@@linben8110 Everyone wants to know the answer to this !!!!

[@baichuan9777]

How did you pass verification on the microcontroller? Did you change the pins according to your own board? How?

[@POLIVERITO]

Hi. I have a STM32F103C8T6 board. Could I do an application of IA? the easiest.... Would you mind helping me please?

[@al567al]

Where can I get the file " har_github_test_vectors.csv" ?

[@stmicroelectronics]

hi - we really recommend to check out community.st.com/s/topic/0TO0X0000003iUqWAI/machine-learning-ai for questions on this topic. To try to solve your immediate issue: In the video, we extracted few vectors from Shanahwax's HAR-CNN-Keras/testData.npy into a .csv file. Please find attached the test .csv file I used. Only 12 out the full 4956 sample vectors were considered. If you want to test the full test dataset, you can use the following python commands to convert testData.npy into a .csv file that can be used with X-CUBE-AI: >>> test_x = np.load('testData.npy') >>> test_x.shape (4956, 90, 3, 1) >>> test_x = test_x.reshape(4956, 90*3) >>> test_x.shape (4956, 270) >>> np.savetxt("testData.csv", test_x, delimiter=",")

[@sailfromsurigao]

Does this mean that STM32Cube.AI can be used on most STM32 MCU's for Image Processing, including STM32F407?

[@stmicroelectronics]

Hello! Visit our online community to find answers to your technical questions and share ideas with our developers and ST experts : community.st.com

[@TheS1l3ntOne]

What mcu family is best for autopilot for drones

[@sammertens0007]

Hi, I have a STM32L053. Is it not compatible ?

[@coolchriss]

regarding the explanation you need an MCU with 1MB flash memory at least. you need to mention the rest of the MCU part number to decide whether is compatible or not

[@linben8110]

I follow the all instructions but get stuck on analyze step at 5:54. It shows up a "please wait" window and does nothing. The progress bar is even freezed.

[@embedded2523]

check out your keras version, may be too advanced?

[@bhuvaneshs.k638]

How to collect real time data not CSV... Using SPI Interface of accelerometer

[@jsonslim]

Hello! I'm trying to load Keras model but it always fails with "Invalid network" Error. What is might be wrong? I've downloaded model from link on the video

[@ajayrajan8882]

clone the repo using -> git clone --recursive "LINK of the REPO", then go inot the downloaded directory and "rm -rf .git", Now try. It should work

[@wuqiwang1716]

I creat my own model, the minimum flash is 2.83Mbytes, when i choose compression of4 or 8, it dosn't get much smaller, still around 2.6Mbytes

[@karan_rathore]

This is bug in STM32CubeMX. After compressing by 4, the size of model will be around 770kb but updated sometimes. you can find that compatible boards will appear in the list. Choose your board and start the project

[@karan_rathore]

I am following this video this, i have successfully generated the code, validate it on desktop, build the code and flash using Truestudio it into STM32L476RB board. But when I try to validate it om my board it gives me error : board not found or invalid firmware or restart the board I have also tried using different USART port, but no success. I have aslo flash the code using CubeProgrammer. but still same error on validating. CubeMX is able locate the port on which board is present but gives same error

[@stmicroelectronics]

hi! for detailed technical questions we recommend that you go to the community at community.st.com/s/topic/0TO0X0000003iUqWAI/machine-learning-ai

[@jujumen]

i have the same issue. Any solution yet?

[@sindujatenth]

I have the same issue

[@ajayrajan8882]

@@johnnycashftw Seems like the firmware of your board is outdated. Please download ST-LINK utility and upgrade the firmware to the latest version. Then try.