I cloned the project Tutorial: Adding sight to your sensors, updated all firmware and build Arduino library with the EON Optimized model. Compilation is ok:
Sketch uses 735288 bytes (37%) of program storage space. Maximum is 1966080 bytes.
Global variables use 76880 bytes (14%) of dynamic memory, leaving 446744 bytes for local variables. Maximum is 523624 bytes.
dfu-util 0.10-dev
But uploading fails:
Warning: Invalid DFU suffix signature
A valid DFU suffix will be required in a future dfu-util release
No DFU capable USB device available
Failed uploading: uploading error: exit status 74
Any ideas? Thanks!
The Nicla Vision has to be in bootloader mode: so double press the reset button. Solved.
Now the problem is that the sketch runs with this error (apparently something to do with TensorFlow Lite?)
15:49:31.362 → Starting inferencing in 2 seconds…
15:49:33.371 → Taking photo…
15:49:33.409 → ERR: failed to allocate tensor arena
15:49:33.409 → Failed to allocate TFLite arena (error code 1)
15:49:33.409 → ERR: Failed to run classifier (-6)
15:49:33.409 →
15:49:33.409 → Starting inferencing in 2 seconds…
15:49:35.407 → Taking photo…
15:49:35.438 → ERR: failed to allocate tensor arena
15:49:35.438 → Failed to allocate TFLite arena (error code 1)
15:49:35.438 → ERR: Failed to run classifier (-6)
It means that the TFLite interpreter was not able to allocate memory for its arena, which is where it runs in circles performing its computations. Try reducing your Impulse input image size down to 64x64 in the Create Impulse page and select grayscale on the Create Impulse - Image page.
1 Like
