Edge AI

cancel
Showing results for 
Search instead for 
Did you mean: 

Forum Posts

INTERNAL ERROR: The edge 1842-1843 not in graph.

When the cubeai tool is used to analyze the model, the unquantized model can be analyzed normally, but the static quantization analysis can make mistakes. I use the onnx model. The following is my quantified model. I hope someone can help me.

wg by Associate II
  • 524 Views
  • 0 replies
  • 0 kudos

INTERNAL ERROR: index 1 is out of bounds for axis 0 with size 1

I'm trying to use the benchmarking tool in the developer cloud (https://stm32ai-cs.st.com).I have a model exported in several formats (fp32, fp16, full 8 bit, etc.)The input shape is (1, 128, 384, 3).The model works fine and other tools like Edge Imp...

SDunn.2 by Associate
  • 462 Views
  • 0 replies
  • 0 kudos

STM32H747I-EVAL camera

STM32H747I-EVAL  Could conectar a some kind of camera to use FP-AI-VISION1_V3.1.0? I don't see the conector to B-CAMS-OMV

wjian.2 by Associate II
  • 3551 Views
  • 1 replies
  • 0 kudos

STM32Cube.AI Max File Size

When using the STM32Cube.AI online tool to benchmark chips for running a neural net the max file size is limited to 32MiB. I have a models that is 93MiB, is there a way to run a model this size? What is the reason for the size limit? Is it related to...

PNada.3 by Associate II
  • 821 Views
  • 0 replies
  • 0 kudos