Starting AI validation on target with random data...
C:/Users/allamjayaprakash/STM32Cube/Repository/Packs/STMicroelectronics/X-CUBE-AI/9.1.0/Utilities/windows/stedgeai.exe validate --target stm32l4 --name network -m C:/Users/allamjayaprakash/Dropbox/STM32/STM32L496G-DISCO/Updated_Model.h5 --compression lossless --verbosity 1 --allocate-inputs --allocate-outputs --memory-pool C:\Users\ALLAMJ~1\AppData\Local\Temp\mxAI_workspace70879369566600013930323030594161238\mempools.json --workspace C:/Users/ALLAMJ~1/AppData/Local/Temp/mxAI_workspace70879369566600013930323030594161238 --output C:/Users/allamjayaprakash/.stm32cubemx/network_output --mode target --desc serial:COM1:115200 --classifier
ST Edge AI Core v1.0.0-19894
Setting validation data...
generating random data, size=10, seed=42, range=(0, 1)
I[1]: (10, 128, 1, 1)/float32, min/max=[0.005, 1.000], mean/std=[0.498, 0.294], input_1
No output/reference samples are provided
Creating c (debug) info json file C:\Users\ALLAMJ~1\AppData\Local\Temp\mxAI_workspace70879369566600013930323030594161238\network_c_info.json
Exec/report summary (validate)
------------------------------------------------------------------------------------------------------------------------------
model file : C:\Users\allamjayaprakash\Dropbox\STM32\STM32L496G-DISCO\Updated_Model.h5
type : keras
c_name : network
compression : lossless
options : allocate-inputs, allocate-outputs, multi-heaps
optimization : balanced
target/series : stm32l4
memory pool : C:\Users\ALLAMJ~1\AppData\Local\Temp\mxAI_workspace70879369566600013930323030594161238\mempools.json
workspace dir : C:\Users\ALLAMJ~1\AppData\Local\Temp\mxAI_workspace70879369566600013930323030594161238
output dir : C:\Users\allamjayaprakash\.stm32cubemx\network_output
model_fmt : float
model_name : Updated_Model
model_hash : 0xf2ee7bd09a567da89f5684d36b016138
params # : 75,237 items (293.89 KiB)
------------------------------------------------------------------------------------------------------------------------------
input 1/1 : 'input_1', f32(1x128x1), 512 Bytes, activations
output 1/1 : 'dense', f32(1x5), 20 Bytes, activations
macc : 8,753,072
weights (ro) : 302,484 B (295.39 KiB) (1 segment) / +1,536(+0.5%) vs float model
activations (rw) : 9,856 B (9.62 KiB) (1 segment) *
ram (total) : 9,856 B (9.62 KiB) = 9,856 + 0 + 0
------------------------------------------------------------------------------------------------------------------------------
(*) 'input'/'output' buffers can be used from the activations buffer
Memory-pools summary (activations/ domain)
--------------- -------- -------------------------- ---------
name id used buffer#
--------------- -------- -------------------------- ---------
POOL_0_RAM 0 9.62 KiB (4.1%) 12
POOL_1_RAM2 unused - 0
weights_array 2 295.39 KiB (30248400.0%) 10
--------------- -------- -------------------------- ---------
Warning: ['POOL_1_RAM2'] memory pool is not used
Running the Keras model...
Running the STM AI c-model (AI RUNNER)...(name=network, mode=TARGET)
INTERNAL ERROR: E801(HwIOError): Invalid firmware - COM1:115200
