Output
: 6D rotation representation [1,6]. To a rotation matrix: b1 = normalize(v[0:3]); b2 = normalize(v[3:6] - (b1·v[3:6])b1); b3 = cross(b1, b2); R = [b1 b2 b3]. Euler angles follow from R.
Variants
All variants take and return fp32 tensors — swap the
.pte
file, keep your app code.
precision
file
size (MB)
parity vs fp32 eager (worst corr)
Mac median (ms)*
fp32
sixdrepnet_headpose_xnnpack_fp32.pte
157.3
1.000000
7.6
*Mac arm64, single process, median of 10 — a reference point for relative cost
only, not a device number (torch eager fp32 on the same machine: 16.3 ms).
Precisions that did not earn a slot
fp16 is not shipped
: it comes out at 100% of the fp32 file (157.3 MB vs 157.3 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.
int8 is not shipped
: worst-output corr 0.815 against fp32 eager, below the 0.95 bar for this precision. The file converts and runs; the numbers do not hold up, so it is left out rather than shipped with a warning.
Verification (executorch 1.4.0, torch 2.13.0)
Parity is measured against the fp32 eager model on real image input;
corr
is
the correlation over all elements of each output tensor.
Notes (int8)
: int8 is measured but not shipped. Correlation is a weak read on a six-element output, so the check that matters is the angle between the fp32 and int8 rotations: median 46.5 deg over ten faces, worst 104 deg. That is the known failure mode of re-parameterized RepVGG under post-training quantization — its fused branches leave weight ranges too wide for an int8 grid — and it needs quantization-aware training rather than anything on the export side.
Runs of mlboydaisuke 6DRepNet-HeadPose-ExecuTorch on huggingface.co
45
Total runs
0
24-hour runs
-6
3-day runs
-22
7-day runs
-18
30-day runs
More Information About 6DRepNet-HeadPose-ExecuTorch huggingface.co Model
More 6DRepNet-HeadPose-ExecuTorch license Visit here:
6DRepNet-HeadPose-ExecuTorch huggingface.co is an AI model on huggingface.co that provides 6DRepNet-HeadPose-ExecuTorch's model effect (), which can be used instantly with this mlboydaisuke 6DRepNet-HeadPose-ExecuTorch model. huggingface.co supports a free trial of the 6DRepNet-HeadPose-ExecuTorch model, and also provides paid use of the 6DRepNet-HeadPose-ExecuTorch. Support call 6DRepNet-HeadPose-ExecuTorch model through api, including Node.js, Python, http.
6DRepNet-HeadPose-ExecuTorch huggingface.co is an online trial and call api platform, which integrates 6DRepNet-HeadPose-ExecuTorch's modeling effects, including api services, and provides a free online trial of 6DRepNet-HeadPose-ExecuTorch, you can try 6DRepNet-HeadPose-ExecuTorch online for free by clicking the link below.
mlboydaisuke 6DRepNet-HeadPose-ExecuTorch online free url in huggingface.co:
6DRepNet-HeadPose-ExecuTorch is an open source model from GitHub that offers a free installation service, and any user can find 6DRepNet-HeadPose-ExecuTorch on GitHub to install. At the same time, huggingface.co provides the effect of 6DRepNet-HeadPose-ExecuTorch install, users can directly use 6DRepNet-HeadPose-ExecuTorch installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
6DRepNet-HeadPose-ExecuTorch install url in huggingface.co: