Activations may exeed the size of all SRAM segments

[ACapo]

I am trying to deploy a pre-trained Mobilenet model using STMCubeMX.ai, but I am facing some issue that I want to report.

Here the link of the project

https://github.com/alessandrocapotondi/mobilenet_stmcube_ai

Here the model I am using:

https://github.com/alessandrocapotondi/mobilenet_stmcube_ai/blob/master/keras_model/mobilenet_160_0_25.h5

Here the resource usage of my model:

600KB RAM for the activations and 1.79MB of weights. Unfortunally despite the "Green Light" given by the tool for the deployment on the STMH7432ZI on the device there is no segment that can fit such ammont of contigous data.

/* Specify the memory areas */
MEMORY
{
DTCMRAM (xrw) : ORIGIN = 0x20000000, LENGTH = 128K
RAM_D1 (xrw) : ORIGIN = 0x24000000, LENGTH = 512K
RAM_D2 (xrw) : ORIGIN = 0x30000000, LENGTH = 288K
RAM_D3 (xrw) : ORIGIN = 0x38000000, LENGTH = 64K
ITCMRAM (xrw) : ORIGIN = 0x00000000, LENGTH = 64K
FLASH (rx) : ORIGIN = 0x8000000, LENGTH = 2048K
}

Best,

Alessandro

[jean-michel.d]

​Hello,

You have absolutly rights, unfortunaltly this check is currently not correctly supporting by the X-CUBE-AI tools.

br,

Jean-Michel

[ACapo]

Really thanks for your support!

[Bassett.David]

As an aside - I like your test image!!!

[ACapo]

:>