Update model card for yolo11-det

README.md

@@ -0,0 +1,348 @@
+---
+license: apache-2.0
+library_name: edgefirst
+pipeline_tag: object-detection
+tags:
+  - edge-ai
+  - npu
+  - tflite
+  - onnx
+  - int8
+  - yolo
+  - gstreamer
+  - edgefirst
+  - nxp
+  - hailo
+  - jetson
+  - real-time
+  - embedded
+  - multiplatform
+model-index:
+  - name: yolo11-det
+    results:
+      - task:
+          type: object-detection
+        dataset:
+          name: COCO val2017
+          type: coco
+        metrics:
+          - name: "mAP@0.5 (Nano ONNX FP32)"
+            type: map_50
+            value: 53.4
+          - name: "mAP@0.5-0.95 (Nano ONNX FP32)"
+            type: map
+            value: 37.9
+          - name: "mAP@0.5 (Nano TFLite INT8)"
+            type: map_50
+            value: 50.1
+          - name: "mAP@0.5-0.95 (Nano TFLite INT8)"
+            type: map
+            value: 34.5
+---
+
+# YOLO11 Detection — EdgeFirst Edge AI
+
+<p align="center">
+  <img src="assets/demo.jpg" alt="YOLO11 Detection demo" width="640">
+</p>
+
+**NXP i.MX 8M Plus** | **NXP i.MX 93** | **NXP i.MX 95** | **NXP Ara240** | **RPi5 + Hailo-8/8L** | **NVIDIA Jetson**
+YOLO11 Detection 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/1123/datasets/gallery/main?dataset=4819) (80 classes). Part of the [EdgeFirst Model Zoo](https://huggingface.co/EdgeFirst).
+> **Training session**: [View on EdgeFirst Studio](https://test.edgefirst.studio/public/projects/1123/experiment/training/details?train_session_id=9506) — 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 FP32 mAP@0.5 | ONNX FP32 mAP@0.5-0.95 | TFLite INT8 mAP@0.5 | TFLite INT8 mAP@0.5-0.95 |
+|------|--------|--------|--------------------|-------------------------|----------------------|--------------------------|
+| Nano | 2.6M | 6.5 | 53.4% | 37.9% | 50.1% | 34.5% |
+| 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
+
+### Universal Formats
+
+<details>
+<summary><strong>ONNX FP32</strong> — Any platform with ONNX Runtime</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/onnx/yolo11n-det-coco.onnx) |
+| Small | `yolo11s-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/onnx/yolo11s-det-coco.onnx) |
+| Medium | `yolo11m-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/onnx/yolo11m-det-coco.onnx) |
+| Large | `yolo11l-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/onnx/yolo11l-det-coco.onnx) |
+| XLarge | `yolo11x-det-coco.onnx` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/onnx/yolo11x-det-coco.onnx) |
+
+</details>
+
+<details>
+<summary><strong>TFLite INT8</strong> — Any platform with TFLite (i.MX 8M Plus uses VX delegate)</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/tflite/yolo11n-det-coco-int8.tflite) |
+| Small | `yolo11s-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/tflite/yolo11s-det-coco-int8.tflite) |
+| Medium | `yolo11m-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/tflite/yolo11m-det-coco-int8.tflite) |
+| Large | `yolo11l-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/tflite/yolo11l-det-coco-int8.tflite) |
+| XLarge | `yolo11x-det-coco-int8.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/tflite/yolo11x-det-coco-int8.tflite) |
+
+</details>
+
+### Platform-Specific
+
+<details>
+<summary><strong>NXP i.MX 93</strong> — Ethos-U NPU via ARM VELA compiler.</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx93/yolo11n-det-coco.tflite) |
+| Small | `yolo11s-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx93/yolo11s-det-coco.tflite) |
+| Medium | `yolo11m-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx93/yolo11m-det-coco.tflite) |
+| Large | `yolo11l-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx93/yolo11l-det-coco.tflite) |
+| XLarge | `yolo11x-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx93/yolo11x-det-coco.tflite) |
+
+</details>
+
+<details>
+<summary><strong>NXP i.MX 95</strong> — eIQ Neutron NPU optimized.</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx95/yolo11n-det-coco.tflite) |
+| Small | `yolo11s-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx95/yolo11s-det-coco.tflite) |
+| Medium | `yolo11m-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx95/yolo11m-det-coco.tflite) |
+| Large | `yolo11l-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx95/yolo11l-det-coco.tflite) |
+| XLarge | `yolo11x-det-coco.tflite` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/imx95/yolo11x-det-coco.tflite) |
+
+</details>
+
+<details>
+<summary><strong>NXP Ara240</strong> — Kinara DVM compiled model.</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/ara240/yolo11n-det-coco.dvm) |
+| Small | `yolo11s-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/ara240/yolo11s-det-coco.dvm) |
+| Medium | `yolo11m-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/ara240/yolo11m-det-coco.dvm) |
+| Large | `yolo11l-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/ara240/yolo11l-det-coco.dvm) |
+| XLarge | `yolo11x-det-coco.dvm` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/ara240/yolo11x-det-coco.dvm) |
+
+</details>
+
+<details>
+<summary><strong>RPi5 + Hailo-8/8L</strong> — Hailo-8L (13 TOPS) and Hailo-8 (26 TOPS).</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/hailo/yolo11n-det-coco.hef) |
+| Small | `yolo11s-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/hailo/yolo11s-det-coco.hef) |
+| Medium | `yolo11m-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/hailo/yolo11m-det-coco.hef) |
+| Large | `yolo11l-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/hailo/yolo11l-det-coco.hef) |
+| XLarge | `yolo11x-det-coco.hef` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/hailo/yolo11x-det-coco.hef) |
+
+</details>
+
+<details>
+<summary><strong>NVIDIA Jetson</strong> — Jetson FP16 and INT8 engines.</summary>
+
+| Size | File | Download |
+|------|------|----------|
+| Nano | `yolo11n-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/jetson/yolo11n-det-coco.engine) |
+| Small | `yolo11s-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/jetson/yolo11s-det-coco.engine) |
+| Medium | `yolo11m-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/jetson/yolo11m-det-coco.engine) |
+| Large | `yolo11l-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/jetson/yolo11l-det-coco.engine) |
+| XLarge | `yolo11x-det-coco.engine` | [Download](https://huggingface.co/EdgeFirst/yolo11-det/resolve/main/jetson/yolo11x-det-coco.engine) |
+
+</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-det-coco-int8.tflite \
+    custom=Delegate:External,ExtDelegateLib:libvx_delegate.so ! \
+  edgefirstdetdecoder ! 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-det-coco-h8l.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-det-coco-config.txt ! \
+  edgefirstdetdecoder ! 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-det-coco-int8.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-det-coco.onnx` | RGB (3ch) | Standard camera input |
+| `yolo11n-det-coco-grey.onnx` | GREY (1ch) | Monochrome / IR sensors |
+| `yolo11n-det-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
+> - One-click deployment to edge devices via [EdgeFirst Client](https://github.com/EdgeFirstAI/client)
+
+---
+
+## See Also
+
+Other models in the [EdgeFirst Model Zoo](https://huggingface.co/EdgeFirst):
+
+| 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 Segmentation | Segmentation | 35.5% Mask mAP@0.5-0.95 (ONNX) | [EdgeFirst/yolo11-seg](https://huggingface.co/EdgeFirst/yolo11-seg) |
+| 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
+
+**Detection** (e.g., yolo11n):
+- Boxes: `(1, 4, 8400)` — normalized [0,1] coordinates
+- Scores: `(1, 80, 8400)` — class probabilities
+
+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_det,
+  title = { {YOLO11 Detection — EdgeFirst Edge AI} },
+  author = {Au-Zone Technologies},
+  url = {https://huggingface.co/EdgeFirst/yolo11-det},
+  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>