mlboydaisuke commited on
Commit
0af3b50
·
verified ·
1 Parent(s): 5fce5da

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -29,6 +29,12 @@ All variants take and return fp32 tensors — swap the `.pte` file, keep your ap
29
  \*Mac arm64, single process, median of 10 — a reference point for relative cost
30
  only, not a device number (torch eager fp32 on the same machine: 85.0 ms).
31
 
 
 
 
 
 
 
32
  ## Verification (executorch 1.4.0, torch 2.13.0)
33
 
34
  Parity is measured against the fp32 eager model on random input; `corr` is
 
29
  \*Mac arm64, single process, median of 10 — a reference point for relative cost
30
  only, not a device number (torch eager fp32 on the same machine: 85.0 ms).
31
 
32
+ ### Checked in the task's own units
33
+
34
+ Correlation is a first filter. These are the numbers that decide:
35
+
36
+ - **int8 (dynamic)** — delta-1 against the fp32 build is 0.994 median over ten real images and 0.975 at worst — for reference, depth models report delta-1 near 0.95 against ground truth, so the quantization error sits well inside the model's own error.
37
+
38
  ## Verification (executorch 1.4.0, torch 2.13.0)
39
 
40
  Parity is measured against the fp32 eager model on random input; `corr` is