You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I've been using the RadioML CNN notebook as my reference to implement a model on an FPGA. I followed the standard structure to generate the bitstream and I've managed to get it running on the FPGA (AMD Zynq™ UltraScale+™ MPSoC ZCU104). The challenge I'm facing now is that the accuracy on the FPGA is only about 14%, even though the model itself achieves around 70% accuracy. So I'm looking for help in figuring out where I might be going wrong.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
I've been using the RadioML CNN notebook as my reference to implement a model on an FPGA. I followed the standard structure to generate the bitstream and I've managed to get it running on the FPGA (AMD Zynq™ UltraScale+™ MPSoC ZCU104). The challenge I'm facing now is that the accuracy on the FPGA is only about 14%, even though the model itself achieves around 70% accuracy. So I'm looking for help in figuring out where I might be going wrong.
Here is my code:
Beta Was this translation helpful? Give feedback.
All reactions