README.md

---
license: apache-2.0
library_name: edgefirst
pipeline_tag: image-segmentation
tags:
  - edge-ai
  - npu
  - tflite
  - onnx
  - int8
  - yolo
  - gstreamer
  - edgefirst
  - nxp
  - hailo
  - jetson
  - real-time
  - embedded
  - multiplatform
model-index:
  - name: yolo11-seg
    results:
      - task:
          type: image-segmentation
        dataset:
          name: COCO val2017
          type: coco
        metrics:
          - name: "Mask mAP@0.5-0.95 (Nano ONNX FP32)"
            type: map
            value: 35.5
          - name: "Mask mAP@0.5-0.95 (Nano TFLite INT8)"
            type: map
            value: 34.4
---

# YOLO11 Segmentation — EdgeFirst Edge AI

**NXP i.MX 8M Plus** | **NXP i.MX 93** | **NXP i.MX 95** | **NXP Ara240** | **RPi5 + Hailo-8/8L** | **NVIDIA Jetson**
YOLO11 Segmentation models optimized for edge AI deployment across multiple hardware platforms. All sizes from Nano to XLarge, in ONNX FP32 and TFLite INT8 formats, with platform-specific compiled models for NPU acceleration.

Trained on [COCO 2017](https://test.edgefirst.studio/public/projects/2839/home) (80 classes). Part of the [EdgeFirst Model Zoo](https://huggingface.co/spaces/EdgeFirst/Models).
> [!TIP]
> **Training session**: [View on EdgeFirst Studio](https://test.edgefirst.studio/public/projects/2840/experiment/training/list?exp_id=4622) — dataset, training config, metrics, and exported artifacts.

> [!NOTE]
> Newer architecture with attention blocks.

---

## Size Comparison

All models validated on COCO val2017 (5000 images, 80 classes).

| Size | Params | GFLOPs | ONNX Det mAP@0.5-0.95 | INT8 Det mAP@0.5-0.95 | ONNX Mask mAP@0.5-0.95 | INT8 Mask mAP@0.5-0.95 |
|------|--------|--------|------------------------|-----------------------|-------------------------|------------------------|
| Nano | 2.6M | 6.5 | 28.4% | 27.1% | 35.5% | 34.4% |
| Small | 9.4M | 21.5 | — | — | — | — |
| Medium | 20.1M | 68.0 | — | — | — | — |
| Large | 25.3M | 87.6 | — | — | — | — |
| XLarge | 56.9M | 195.0 | — | — | — | — |

---

## On-Target Performance

Full pipeline timing: pre-processing + inference + post-processing.

| Size | Platform | Pre-proc (ms) | Inference (ms) | Post-proc (ms) | Total (ms) | FPS |
|------|----------|---------------|----------------|-----------------|------------|-----|
| — | — | — | — | — | — | — |

*Measured with [EdgeFirst Perception](https://github.com/EdgeFirstAI) stack. Timing includes full GStreamer pipeline overhead.*

---

## Downloads

<details open>
<summary><strong>ONNX FP32</strong> — Any platform with ONNX Runtime.</summary>

| Size | File | Status |
|------|------|--------|
| Nano | `yolo11n-seg-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/onnx/yolo11n-seg-coco.onnx) |
| Small | `yolo11s-seg-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/onnx/yolo11s-seg-coco.onnx) |
| Medium | `yolo11m-seg-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/onnx/yolo11m-seg-coco.onnx) |
| Large | `yolo11l-seg-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/onnx/yolo11l-seg-coco.onnx) |
| XLarge | `yolo11x-seg-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/onnx/yolo11x-seg-coco.onnx) |

</details>

<details>
<summary><strong>TFLite INT8</strong> — CPU or NPU via runtime delegate (i.MX 8M Plus VX Delegate).</summary>

| Size | File | Status |
|------|------|--------|
| Nano | `yolo11n-seg-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/tflite/yolo11n-seg-coco.tflite) |
| Small | `yolo11s-seg-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/tflite/yolo11s-seg-coco.tflite) |
| Medium | `yolo11m-seg-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/tflite/yolo11m-seg-coco.tflite) |
| Large | `yolo11l-seg-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/tflite/yolo11l-seg-coco.tflite) |
| XLarge | `yolo11x-seg-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/tflite/yolo11x-seg-coco.tflite) |

</details>

<details>
<summary><strong>NXP i.MX 95 (eIQ Neutron)</strong> — eIQ Neutron NPU optimized.</summary>

| Size | File | Status |
|------|------|--------|
| Nano | `yolo11n-seg-coco.imx95.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/imx95/yolo11n-seg-coco.imx95.tflite) |
| Small | `yolo11s-seg-coco.imx95.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/imx95/yolo11s-seg-coco.imx95.tflite) |
| Medium | `yolo11m-seg-coco.imx95.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/imx95/yolo11m-seg-coco.imx95.tflite) |
| Large | `yolo11l-seg-coco.imx95.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/imx95/yolo11l-seg-coco.imx95.tflite) |
| XLarge | `yolo11x-seg-coco.imx95.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-seg/resolve/main/imx95/yolo11x-seg-coco.imx95.tflite) |

</details>



---

## Deploy with EdgeFirst Perception

Copy-paste [GStreamer](https://github.com/EdgeFirstAI/gstreamer) pipeline examples for each platform.

### NXP i.MX 8M Plus — Camera to Detection with Vivante NPU

```bash
gst-launch-1.0 \
  v4l2src device=/dev/video0 ! video/x-raw,width=640,height=480 ! \
  edgefirstcameraadaptor ! \
  tensor_filter framework=tensorflow-lite \
    model=yolo11n-seg-coco.tflite \
    custom=Delegate:External,ExtDelegateLib:libvx_delegate.so ! \
  edgefirstsegdecoder ! edgefirstoverlay ! waylandsink
```

### RPi5 + Hailo-8L

```bash
gst-launch-1.0 \
  v4l2src device=/dev/video0 ! video/x-raw,width=640,height=480 ! \
  hailonet hef-path=yolo11n-seg-coco.hailo8l.hef ! \
  hailofilter function-name=yolo11_nms ! \
  hailooverlay ! videoconvert ! autovideosink
```

### NVIDIA Jetson (TensorRT)

```bash
gst-launch-1.0 \
  v4l2src device=/dev/video0 ! video/x-raw,width=640,height=480 ! \
  edgefirstcameraadaptor ! \
  nvinfer config-file-path=yolo11n-seg-coco-config.txt ! \
  edgefirstsegdecoder ! edgefirstoverlay ! nveglglessink
```


*Full pipeline documentation: [EdgeFirst GStreamer Plugins](https://github.com/EdgeFirstAI/gstreamer)*

---

## Foundation (HAL) Python Integration

```python
from edgefirst.hal import Model, TensorImage

# Load model — metadata (labels, decoder config) is embedded in the file
model = Model("yolo11n-seg-coco.tflite")

# Run inference on an image
image = TensorImage.from_file("image.jpg")
results = model.predict(image)

# Access detections
for det in results.detections:
    print(f"{det.label}: {det.confidence:.2f} at {det.bbox}")
```

*[EdgeFirst HAL](https://github.com/EdgeFirstAI/hal) — Hardware abstraction layer with accelerated inference delegates.*

---

## CameraAdaptor

EdgeFirst [CameraAdaptor](https://github.com/EdgeFirstAI/cameraadaptor) enables training and inference directly on native sensor formats (GREY, YUYV, etc.) — skipping the ISP color conversion pipeline entirely. This reduces latency and power consumption on edge devices.

CameraAdaptor variants are included alongside baseline RGB models:

| Variant | Input Format | Use Case |
|---------|-------------|----------|
| `yolo11n-seg-coco.onnx` | RGB (3ch) | Standard camera input |
| `yolo11n-seg-coco-grey.onnx` | GREY (1ch) | Monochrome / IR sensors |
| `yolo11n-seg-coco-yuyv.onnx` | YUYV (2ch) | Raw sensor bypass |

*Train CameraAdaptor models with [EdgeFirst Studio](https://edgefirst.studio) — the CameraAdaptor layer is automatically inserted during training.*

---

## Train Your Own with EdgeFirst Studio

Train on your own dataset with [**EdgeFirst Studio**](https://edgefirst.studio):

- **Free tier** includes YOLO training with automatic INT8 quantization and edge deployment
- Upload datasets via [EdgeFirst Recorder](https://github.com/EdgeFirstAI/recorder) or COCO/YOLO format
- AI-assisted annotation with auto-labeling
- CameraAdaptor integration for native sensor format training
- Deploy trained models to edge devices via [EdgeFirst Client](https://github.com/EdgeFirstAI/client)

---

## See Also

Other models in the [EdgeFirst Model Zoo](https://huggingface.co/spaces/EdgeFirst/Models):

| Model | Task | Best Nano Metric | Link |
|-------|------|-------------------|------|
| YOLOv5 Detection | Detection | 49.6% mAP@0.5 (ONNX) | [EdgeFirst/yolov5-det](https://huggingface.co/EdgeFirst/yolov5-det) |
| YOLOv8 Detection | Detection | 50.2% mAP@0.5 (ONNX) | [EdgeFirst/yolov8-det](https://huggingface.co/EdgeFirst/yolov8-det) |
| YOLOv8 Segmentation | Segmentation | 34.1% Mask mAP@0.5-0.95 (ONNX) | [EdgeFirst/yolov8-seg](https://huggingface.co/EdgeFirst/yolov8-seg) |
| YOLO11 Detection | Detection | 53.4% mAP@0.5 (ONNX) | [EdgeFirst/yolo11-det](https://huggingface.co/EdgeFirst/yolo11-det) |
| YOLO26 Detection | Detection | 54.9% mAP@0.5 (ONNX) | [EdgeFirst/yolo26-det](https://huggingface.co/EdgeFirst/yolo26-det) |
| YOLO26 Segmentation | Segmentation | 37.0% Mask mAP@0.5-0.95 (ONNX) | [EdgeFirst/yolo26-seg](https://huggingface.co/EdgeFirst/yolo26-seg) |

---

## Technical Details

### Quantization Pipeline

All TFLite INT8 models are produced by EdgeFirst's custom quantization pipeline ([details](https://github.com/EdgeFirstAI/studio-ultralytics)):

1. **ONNX Export** — Standard Ultralytics export with `simplify=True`
2. **TF-Wrapped ONNX** — Box coordinates normalized to [0,1] inside DFL decode via `tf_wrapper` (~1.2% better mAP than post-hoc normalization)
3. **Split Decoder** — Boxes, scores, and mask coefficients split into separate output tensors for independent INT8 quantization scales
4. **Smart Calibration** — 500 images selected via greedy coverage maximization from COCO val2017
5. **Full INT8** — `uint8` input (raw pixels), `int8` output (per-tensor scales), MLIR quantizer

### Split Decoder Output Format

**Segmentation** (e.g., yolo11n-seg):
- Boxes: `(1, 4, 8400)` — normalized [0,1] coordinates
- Scores: `(1, 80, 8400)` — class probabilities
- Mask coefficients: `(1, 32, 8400)` — per-anchor mask coefs
- Protos: `(1, 160, 160, 32)` — prototype masks

Each tensor has independent quantization scale and zero-point. EdgeFirst HAL handles dequantization and reassembly automatically.

### Metadata

- **TFLite**: `edgefirst.json`, `labels.txt`, and `edgefirst.yaml` embedded via ZIP (no `tflite-support` dependency)
- **ONNX**: `edgefirst.json` embedded via `model.metadata_props`

No standalone metadata files — models are self-contained.

---

## Limitations

- **COCO bias** — Models trained on COCO (80 classes) inherit its biases: Western-centric scenes, specific object distributions, limited weather/lighting diversity
- **INT8 accuracy loss** — Full-integer quantization typically degrades mAP by 6-12% relative to FP32; actual loss depends on model architecture and dataset
- **Thermal variation** — On-target performance varies with device temperature; sustained inference may throttle on passively-cooled devices
- **Input resolution** — All models expect 640×640 input; other resolutions require letterboxing or may reduce accuracy
- **CameraAdaptor variants** — GREY/YUYV models trade color information for latency; accuracy may differ from RGB baseline depending on the task

---

## Citation

```bibtex
@software{edgefirst_yolo11_seg,
  title = { {YOLO11 Segmentation — EdgeFirst Edge AI} },
  author = {Au-Zone Technologies},
  url = {https://huggingface.co/EdgeFirst/yolo11-seg},
  year = {2026},
  license = {Apache-2.0},
}
```

---

<p align="center">
  <sub>
    <a href="https://edgefirst.studio">EdgeFirst Studio</a> · <a href="https://github.com/EdgeFirstAI">GitHub</a> · <a href="https://doc.edgefirst.ai">Docs</a> · <a href="https://www.au-zone.com">Au-Zone Technologies</a><br>
    Apache 2.0 · © Au-Zone Technologies Inc.
  </sub>
</p>