Loading…
Loading…
File: glintr100_int8.onnx (104.6 MB) — INT8-quantized face-recognition backbone
outputting a 512-dimensional embedding from a 112×112 aligned face.
glintr100.onnx (~260 MB) is not included — get it from
fal/AuraFace-v1 if needed.The FP32 glintr100.onnx was quantized to INT8 with onnxruntime quantization
(per-channel weight quantization; compute graph otherwise unchanged):
same input data [N, 3, 112, 112] float32, same output 1333 [1, 512].
File size: ~260 MB → ~105 MB. Expect a small accuracy drop versus FP32, typical
for INT8 quantization.
Licensed under the Apache License 2.0 (same as the base model). You may use, modify, and distribute this file provided you preserve attribution to the AuraFace authors, keep this modification notice, and comply with the full license text.
| Item | Value |
|---|---|
| Task | Face feature extraction → 512-d embedding (cosine similarity for recognition) |
Input data |
[N, 3, 112, 112], float32, aligned RGB face, normalized per InsightFace convention |
Output 1333 |
[N, 512], float32 (L2-normalize before comparing) |
import onnxruntime as ort
import numpy as np
sess = ort.InferenceSession("glintr100_int8.onnx",
providers=["CPUExecutionProvider"])
face = np.random.rand(1, 3, 112, 112).astype(np.float32) # aligned + normalized face
emb = sess.run(None, {"data": face})[0]
emb = emb / np.linalg.norm(emb, axis=1, keepdims=True) # cosine-sim ready
Prefer the standard InsightFace pipeline (FaceAnalysis(name="auraface")) for
detection + alignment; see the base model card.
fal/AuraFace-v1