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'm attempting to take a model, built similarly to the MNIST Tutorial, which switches some dense layers with convolutional layers to run on Loihi 2. This runs fine via simulator but when running on Loihi 2 hardware I realized that NcL2ModelConv's connection with PySpikeInputModel is not supported just yet.
Error when running on Loihi 2: Execution error No support for (source, destination) pairs of type '(PySpikeInputModel, NcL2ModelConv)' yet
I'm curious if the only way to currently run a process with convolutional layers on Loihi 2 is by manually creating an .hdf5 file and using lava.lib.dl.netx to load the model, or if there is a better alternative? Thanks!
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
-
I'm attempting to take a model, built similarly to the MNIST Tutorial, which switches some dense layers with convolutional layers to run on Loihi 2. This runs fine via simulator but when running on Loihi 2 hardware I realized that NcL2ModelConv's connection with PySpikeInputModel is not supported just yet.
Error when running on Loihi 2:
Execution error No support for (source, destination) pairs of type '(PySpikeInputModel, NcL2ModelConv)' yet
I'm curious if the only way to currently run a process with convolutional layers on Loihi 2 is by manually creating an .hdf5 file and using
lava.lib.dl.netx
to load the model, or if there is a better alternative? Thanks!Beta Was this translation helpful? Give feedback.
All reactions