Exception: Only binarized weights supported when use deploy_bw.prototxt in FINN

[saraballeri]

Hi,
I would to generate an hardware design through FINN, passing it a prototxt of any BNN.
I don't understand if the folder https://github.com/zhaoweicai/hwgq/tree/master/examples/imagenet already contains prototxts suitable for FINN (as well as caffemodels in https://github.com/zhaoweicai/hwgq#models).
As the guide of FINN says, I have tried to run:
python FINN/bin/finn --device=pynqz1 --prototxt=FINN/inputs/deploy_bw.prototxt --mode=estimate
in which deploy_bw.prototxt is the prototxt contained in https://github.com/zhaoweicai/hwgq/tree/master/examples/imagenet/alex-hwgq-3ne-clip-poly-320k
but i get the exception:
....
File "/home/user/FINN/FINN/backend/fpga/backend_fpga.py", line 64, in passConvertToFPGALayers ret += [layers_fpga.FPGABipolarConvThresholdLayer(L)] File "/home/user/FINN/FINN/backend/fpga/layers_fpga.py", line 337, in __init__ raise Exception("Only binarized weights supported") Exception: Only binarized weights supported

Can you clarify me this doubt?
Thanks,
Sara

[maltanar]

Hi Sara,

As you can see from the error output this is not a HWGQ issue but a FINN issue, so this issue belongs to the FINN GitHub repo.

[saraballeri]

Yes, i saw there. But then all your prototxts and caffemodels are binarized? 1 bit weight and 1 bit activation?
Thanks,
Sara