Ask questions and find answers on how to deploy, debug, and optimize AI models on ST microcontrollers, microprocessors, and smart sensors.
Hello ST Community members, Are you a data scientist or machine learning engineer with experience deploying neural networks on edge or embedded devices? The ST team invites you to join a 45-minute remote usability session to provide technical feedb...
@stm@Julian E. I get the following error.Attached are the model and npz files for quantization. Quantization with int8 shows following errors: Executing with: {'model': '/tmp/quantization-service/280b5700-3751-4fba-a647-f57a80bf0b73/stm32_mnist.keras...
Hello all,im currently trying to fine tune a mobileNetV2 model that is pretrained on imageNet on my own dataset.However when im adapting the user_config.yaml i dont know how to switch between mobileNetV2 1.0 and mobileNetV2 1.4 as i would like to see...
Hi there,I am newbie at edge AI, and I was runing the demo "motor vibration" in nanoEdgeAI.For me, the nanoEdgeAI is really a excellent work, I can easy understand the most part of the work flow by run an demo, even I am just a new guy.However, when ...
I am using STM32N6570-DK board.I wanted to use resnet50 model for Image Classification I generated files using stedgeai using the command : stedgeai generate --model resnet50_v2_224_int8.tflite --target stm32n6 --st-neural-art default@user_neuralart_...
Hi,I'm using the STEVAL-STWINKT1B and the automode to log data, with the FPSNSDATALOG2 firmware. I'm reaching out because, although the logger seems to run for multiple hours, I only get a few minutes (or at best a couple of hours) of data saved on t...
Hello,i want to adapt the STM32N6GettingStartedImageClassification Project (https://github.com/STMicroelectronics/STM32N6-GettingStarted-ImageClassification/tree/main) with a second model, so i can build a proper ai pipeline.The coding isnt the probl...
Hi,Currently, I want to use TFLM library to do the inference rather than Cube.AI. For me, what I am doing is:1. download the latest tflm library2. build it with commands: "make -f tensorflow/lite/micro/tools/make/Makefile TARGET=cortex_m_generic TARG...
Hello ST team, I have logged raw data by using hsdatalog_GUI.py in STM32CubeFunctionPack_DATALOG2_V2.1.1 from STEVAL-STWINKT1b board to PC and seen the FFT diagram in GUI. The acquired raw data was saved locally in an automatically generated folder....
Error output when trying to quantize CNN2d_ST_HandPosture_8classes_hand_posture_ST_VL53L8CX_handposture_dataset.h5 in STM Edge AI Developer Cloud. For example, the error "Could not find cuda drivers on your machine, GPU will not be used." Why do I ne...
Hi, I am implementing the new STM32 project in that I am initialized Display and camera interfaceLTDC interface enabled turning on the backlight by making PQ6 pin high and in TouchGFX created a project selected STM32N6570-DK board while run the targe...
