Give the inference engine a denoiser role, kept off the Hexagon

Browse Source

The learned demosaic-and-denoise (denoise.md) runs through the engine like
every other model. fp16 cost it nothing measurable (0.00 dB at every ISO on
validation tiles), so it takes TensorRT's and MIGraphX's fp16 like the
detectors. int8 cost it 6 to 9 dB, far past a 0.5 dB gate, so the Hexagon
refuses the role outright rather than relying on no int8 sibling existing,
and the tablet runs it on the CPU.

...

This commit is contained in:

dtourolle

2026-10-03 10:39:14 -04:00

parent d4248bc0dd

commit eb91fa02c2

2 changed files with 15 additions and 7 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

docs/dev/traceability.md

+6 -6

File diff suppressed because one or more lines are too long