Conversation
Jarkko Sakkinen
jarkko
I think I try tiling with inference because that improves cache coherency. E.g. preprocess bitmap to 2x2, 4x4 or perhaps even 8x8 tiles (i have to try them all out).
Image becomes brutal for human viewer but as per *hypothesis* cache misses reduce by some percentage. I don't know what the vision model thinks bitmap having this organization but my plain guess is that it might even work.
Image becomes brutal for human viewer but as per *hypothesis* cache misses reduce by some percentage. I don't know what the vision model thinks bitmap having this organization but my plain guess is that it might even work.
0
0
0