mlboydaisuke commited on
Commit
6f17816
·
verified ·
1 Parent(s): f271ce1

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -21,7 +21,6 @@ All variants take and return fp32 tensors — swap the `.pte` file, keep your ap
21
  | precision | file | size (MB) | parity vs fp32 eager (worst corr) | Mac median (ms)* |
22
  |-----------|------|-----------|------------------------------------|------------------|
23
  | fp32 | `u2net_xnnpack_fp32.pte` | 176.0 | 1.000000 | 56.5 |
24
- | int8 | `u2net_xnnpack_int8.pte` | 44.3 | 0.980186 | 33.0 |
25
 
26
  \*Mac arm64, single process, median of 10 — a reference point for relative cost
27
  only, not a device number (torch eager fp32 on the same machine: 138.5 ms).
@@ -29,6 +28,7 @@ only, not a device number (torch eager fp32 on the same machine: 138.5 ms).
29
  ### Precisions that did not earn a slot
30
 
31
  - **fp16 is not shipped**: it comes out at 100% of the fp32 file (176.0 MB vs 176.0 MB), so it buys nothing. XNNPACK serializes convolution weights as fp32 no matter what dtype the graph carries, so on a conv-heavy model fp16 saves no disk and only adds cast operations. Reach for int8 here, not fp16.
 
32
 
33
  ## Verification (executorch 1.4.0, torch 2.13.0)
34
 
 
21
  | precision | file | size (MB) | parity vs fp32 eager (worst corr) | Mac median (ms)* |
22
  |-----------|------|-----------|------------------------------------|------------------|
23
  | fp32 | `u2net_xnnpack_fp32.pte` | 176.0 | 1.000000 | 56.5 |
 
24
 
25
  \*Mac arm64, single process, median of 10 — a reference point for relative cost
26
  only, not a device number (torch eager fp32 on the same machine: 138.5 ms).
 
28
  ### Precisions that did not earn a slot
29
 
30
  - **fp16 is not shipped**: it comes out at 100% of the fp32 file (176.0 MB vs 176.0 MB), so it buys nothing. XNNPACK serializes convolution weights as fp32 no matter what dtype the graph carries, so on a conv-heavy model fp16 saves no disk and only adds cast operations. Reach for int8 here, not fp16.
31
+ - **int8 is not shipped**: mask IoU 0.814 median and 0.212 at worst against fp32. The int8 build systematically shrinks weak saliency: on a photo where fp32 marks 2.2% of pixels foreground it marks 0.5%. On images with an unambiguous subject it agrees closely (0.99), but that is not a promise this model can make.
32
 
33
  ## Verification (executorch 1.4.0, torch 2.13.0)
34