Convolution merging and branching support in Loihi2 to implement multi-head YOLO #871
Unanswered
gwgknudayanga
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
** In last year summer INRC 2023, under the "
** Deep Learning Applications for Loihi 2" it was mentioned that the convolution merging and branching support is going to able available very soon. Are these capabilities available now? If available could you please provide some examples and related resources which shows the usage of them?
** In my case, i trained tiny-yolov3 spiking neural network in slayer for DVS346 data for civil infrasture damage detection. Now i would like to map the network to loihi2. But i don't how the branching to two heads should be implemented in loihi2 (When mapping from slayer to netx). Also i don't know how the torch.concat (which concatenate feature maps from different layers) should be mapped from slayer to netx/loihi2.
Thanks and Rgds,
Udayanga
Beta Was this translation helpful? Give feedback.
All reactions