---
license: mit
tags:
  - face-detection
  - onnx
  - insightface
  - scrfd
  - object-detection
  - computer-vision
pipeline_tag: object-detection
---

# SCRFD det_500m — buffalo_s weights, dynamic batch (640×640)

Drop-in replacement for the InsightFace `buffalo_s` face detector (`det_500m.onnx`) with
**batch=1 fixed to dynamic batch**. Pass N frames in a single forward pass; each frame's
output is bit-identical to running the model N times individually.

---

## Background

PR [deepinsight/insightface#1781](https://github.com/deepinsight/insightface/pull/1781)
fixed the SCRFD export script to produce dynamic batch axes, but the distributed
`buffalo_s` model pack was never re-exported. Calling the original session with N > 1 frames
crashes:

```
[ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Got invalid dimensions for input: input.1
index: 0  Got: 2  Expected: 1
```

This model is the fixed version. Tracked in
[deepinsight/insightface#2878](https://github.com/deepinsight/insightface/issues/2878).

> **Note on existing workarounds**: [alonsorobots/scrfd_320_batched](https://huggingface.co/alonsorobots/scrfd_320_batched)
> is a re-export at 320×320. This model uses the original buffalo_s weights at **640×640**,
> which preserves small-face detection quality.

---

## How the fix works

Every output path in the original SCRFD graph ends with:

```
Conv [N,C,H,W] → Transpose perm=[2,3,0,1] → Reshape [-1, K]
```

The Transpose moves the batch dim between spatial and channel dims; the Reshape then
flattens everything together — interleaving frames. Three targeted ONNX graph edits fix it:

1. **Input batch dim → dynamic** (`1` → `"batch"`)
2. **9 output Transpose nodes**: `perm [2,3,0,1]` → `perm [0,2,3,1]` (batch stays outermost)
3. **3 Reshape initializers**: `[-1, K]` → `[0, -1, K]` (`0` copies the batch dim → `[N, anchors, K]`)

Source + surgery script: [ceyxasm/insightface-det-batch-fix](https://github.com/ceyxasm/insightface-det-batch-fix)

---

## Usage

```python
import cv2, numpy as np, onnxruntime as ort
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="ceyxprime/scrfd_640_batched", filename="det_500m_fixed.onnx")

sess = ort.InferenceSession(model_path, providers=["CUDAExecutionProvider"])
inp_name = sess.get_inputs()[0].name

def preprocess(path):
    img = cv2.imread(path)
    return cv2.dnn.blobFromImage(
        cv2.resize(img, (640, 640)), 1.0 / 128.0, (640, 640),
        (127.5, 127.5, 127.5), swapRB=True,
    )[0]  # (3, 640, 640)

# N images → one forward pass
batch = np.stack([preprocess(p) for p in image_paths])   # (N, 3, 640, 640)
outputs = sess.run(None, {inp_name: batch})

# outputs: 9 tensors — 3 scales (stride 8/16/32) × 3 heads (cls, reg, kps)
# outputs[i][n] = frame n's result for head i
# Anchor counts at 640×640: 12800 / 3200 / 800 per scale
for n in range(len(image_paths)):
    cls_s8 = outputs[0][n]   # (12800, 1)  scores, stride 8
    reg_s8 = outputs[3][n]   # (12800, 4)  box deltas, stride 8
    kps_s8 = outputs[6][n]   # (12800, 10) keypoints, stride 8
    # run your anchor decoding + NMS per frame as usual
```

Or reproduce from the original model:

```bash
pip install onnx onnxruntime insightface
python -c "import insightface; insightface.app.FaceAnalysis(name='buffalo_s').prepare(ctx_id=-1)"
# then:
git clone https://github.com/ceyxasm/insightface-det-batch-fix
cd insightface-det-batch-fix
python fix_det_batch.py \
    --model ~/.insightface/models/buffalo_s/det_500m.onnx \
    --out   det_500m_fixed.onnx
```

---

## Validation

Same image duplicated 5× in one forward pass (`validate_5frames.py`):

| Comparison | Max diff |
|---|---|
| ORT B=1 vs onnx2torch B=1 | ≤ 2e-5 (float backend noise) |
| ORT B=1 vs each of 5 batched frames | identical to above |
| onnx2torch B=1 vs each of 5 batched frames | **0.000000** |
| All cross-frame pairs | **0.000000** |

All 9 output heads pass.

---

## Model details

| Property | Value |
|---|---|
| Architecture | SCRFD-500MF |
| Input | `[N, 3, 640, 640]`, float32, normalised `(x - 127.5) / 128.0` |
| Outputs | 9 tensors: cls×3, reg×3, kps×3 (strides 8, 16, 32) |
| Weights | buffalo_s (not identical to public SCRFD500.pth) |
| Framework | ONNX (opset 11) |
| Fixed from | `~/.insightface/models/buffalo_s/det_500m.onnx` |