nik/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-10-18 07:29:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

perf(axelera): quantize uint8->int8 in one wrapping pass

Browse Source 
resized - 128 in uint8 wraps mod 256, then astype(int8) yields exactly
px - 128 (verified for all 0..255, equivalent to the int16+clip path)
without the intermediate int16 array or clip pass.
This commit is contained in:
patrykorwat 2026-08-23 20:51:44 +00:00
parent 92112cf909
commit 44cc8bf4fc
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
frigate/detectors/plugins/axelera.py
View File

@ -369,8 +369,9 @@ class _AxeleraRuntimeInference:
(self._new_w, self._new_h),
interpolation=cv2.INTER_LINEAR,
)
q = resized.astype(np.int16) - 128 # uint8 [0,255] -> int8 [-128,127]
q = np.clip(q, -128, 127).astype(np.int8)
# uint8 - 128 wraps mod 256, then cast to int8 == px - 128 (exactly),
# in one pass over the resized frame (no int16/clip intermediates)
q = (resized - np.uint8(128)).astype(np.int8)
buf = self._in_buf
buf.fill(INPUT_Q_ZERO)
y0, y1 = self._pad_t, self._pad_t + self._new_h