Update model card for yolo11-seg
Browse files
README.md
CHANGED
|
@@ -75,16 +75,21 @@ Accuracy ceiling for each size, measured against COCO `val2017` (5,000 images) w
|
|
| 75 |
|
| 76 |
Each row is one EdgeFirst Studio validation session. Click the **Source** link to inspect the full session — model artifact, dataset version, parameters, per-stage Perfetto trace, and the host hardware description (hostname, kernel version, SoC, NPU, profiler version).
|
| 77 |
|
| 78 |
-
|
|
|
|
|
|
|
|
|
|
| 79 |
|
| 80 |
| Size | Platform | Box mAP@0.5 | Mask mAP@0.5-0.95 | Δ mask vs FP32 (pp) | Inference (ms) | FPS (median) | Source |
|
| 81 |
|------|----------|-------------|-------------------|---------------------|----------------|--------------|--------|
|
| 82 |
| Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 48.22% | 26.08% | -2.67 | 105.78 | 7.6 | [v-1d5f](https://test.edgefirst.studio/public/validation/v-1d5f/details) |
|
| 83 |
-
| Nano | NXP i.MX 95 + eIQ Neutron NPU |
|
| 84 |
| Nano | Raspberry Pi 5 + Hailo-8L NPU | 50.35% | 27.64% | -1.11 | 28.52 | 33.6 | [v-1d5c](https://test.edgefirst.studio/public/validation/v-1d5c/details) |
|
| 85 |
| Small | Raspberry Pi 5 + Hailo-8L NPU | 58.66% | 32.39% | -0.94 | 40.49 | 24.0 | [v-1d5d](https://test.edgefirst.studio/public/validation/v-1d5d/details) |
|
| 86 |
| Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.95% | 35.52% | -1.09 | 83.81 | 11.8 | [v-1d60](https://test.edgefirst.studio/public/validation/v-1d60/details) |
|
| 87 |
|
|
|
|
|
|
|
| 88 |
|
| 89 |
---
|
| 90 |
|
|
|
|
| 75 |
|
| 76 |
Each row is one EdgeFirst Studio validation session. Click the **Source** link to inspect the full session — model artifact, dataset version, parameters, per-stage Perfetto trace, and the host hardware description (hostname, kernel version, SoC, NPU, profiler version).
|
| 77 |
|
| 78 |
+
Two row conventions in the table below:
|
| 79 |
+
|
| 80 |
+
- **Rows without a number** under the metric columns are validation sessions that are currently work in progress — typically a larger size that has not yet been profiled on a given NPU, or a session that has not yet been linked to an ONNX FP32 reference. The Studio Source link tracks the current status.
|
| 81 |
+
- **Rows whose `Δ vs FP32` cell carries a ⚠** are published with a caveat: the quantization or runtime regression on that platform exceeds the 10 percentage-point publication threshold we grade every measurement against. The numbers are still measured on real hardware and reproducible from the linked Studio session — they are shown for transparency rather than suppressed. We are actively investigating these regressions in collaboration with the toolchain vendor and working to close the gap; the note immediately under the table summarises the current state.
|
| 82 |
|
| 83 |
| Size | Platform | Box mAP@0.5 | Mask mAP@0.5-0.95 | Δ mask vs FP32 (pp) | Inference (ms) | FPS (median) | Source |
|
| 84 |
|------|----------|-------------|-------------------|---------------------|----------------|--------------|--------|
|
| 85 |
| Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 48.22% | 26.08% | -2.67 | 105.78 | 7.6 | [v-1d5f](https://test.edgefirst.studio/public/validation/v-1d5f/details) |
|
| 86 |
+
| Nano | NXP i.MX 95 + eIQ Neutron NPU | 10.82% | 4.03% | -24.72 âš | 43.21 | 19.0 | [v-1d5e](https://test.edgefirst.studio/public/validation/v-1d5e/details) |
|
| 87 |
| Nano | Raspberry Pi 5 + Hailo-8L NPU | 50.35% | 27.64% | -1.11 | 28.52 | 33.6 | [v-1d5c](https://test.edgefirst.studio/public/validation/v-1d5c/details) |
|
| 88 |
| Small | Raspberry Pi 5 + Hailo-8L NPU | 58.66% | 32.39% | -0.94 | 40.49 | 24.0 | [v-1d5d](https://test.edgefirst.studio/public/validation/v-1d5d/details) |
|
| 89 |
| Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.95% | 35.52% | -1.09 | 83.81 | 11.8 | [v-1d60](https://test.edgefirst.studio/public/validation/v-1d60/details) |
|
| 90 |
|
| 91 |
+
> **âš Investigations in progress.** The rows marked âš above show a drop of more than 10 percentage points against the same training session's ONNX FP32 reference. We publish them as-is so the current state of every (model, platform) pair is visible; we are working with the toolchain vendor to close each regression, and the numbers will improve as fixes land. The next snapshot of this card will reflect any recovered accuracy.
|
| 92 |
+
|
| 93 |
|
| 94 |
---
|
| 95 |
|