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
Hi,
My Masters project involves creating a CNN for super resolution and deploying it to a PYNQ FPGA. For this I plan to use FINN, PyTorch and Brevitas. Is it possible to quantise Deconvolution or PixelShuffle layers with Brevitas. Is it also possible to do the same with Depthwise Separable Convolutional layers?
If not I would welcome suggestions on alternative layers or libraries
Thanks guys and gals.
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
-
Hi,
My Masters project involves creating a CNN for super resolution and deploying it to a PYNQ FPGA. For this I plan to use FINN, PyTorch and Brevitas. Is it possible to quantise Deconvolution or PixelShuffle layers with Brevitas. Is it also possible to do the same with Depthwise Separable Convolutional layers?
If not I would welcome suggestions on alternative layers or libraries
Thanks guys and gals.
Beta Was this translation helpful? Give feedback.
All reactions