Update model card for yolo11-seg
Browse files
README.md
CHANGED
|
@@ -177,6 +177,12 @@ Row conventions in the table below:
|
|
| 177 |
| Medium | NXP Ara240 (FRDM) — throughput | 62.85% | 37.35% | -2.08 | 39.18 | 63.09 | 29.1 | ~29 | [v-a37](https://edgefirst.studio/public/validation/v-a37/details?mode=charts) |
|
| 178 |
| Medium | Raspberry Pi 5 + Hailo-8L NPU | 64.44% | 37.62% | -1.81 | 79.87 | 99.64 | 11.8 | ~12 | [v-934](https://edgefirst.studio/public/validation/v-934/details?mode=charts) |
|
| 179 |
| Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 67.07% | 39.43% | +0.00 | 72.33 | 97.67 | 54.8 | ~55 | [v-92c](https://edgefirst.studio/public/validation/v-92c/details?mode=charts) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
|
| 181 |
> **⚠ Below expectations — under investigation.** The rows marked ⚠ above measure more than 10 percentage points below the same training session's float reference: the model accuracy on that platform is below our expectations. We publish the measured numbers rather than hiding them, and we are investigating the results to make improvements — the next snapshot of this card will reflect any recovered accuracy.
|
| 182 |
|
|
|
|
| 177 |
| Medium | NXP Ara240 (FRDM) — throughput | 62.85% | 37.35% | -2.08 | 39.18 | 63.09 | 29.1 | ~29 | [v-a37](https://edgefirst.studio/public/validation/v-a37/details?mode=charts) |
|
| 178 |
| Medium | Raspberry Pi 5 + Hailo-8L NPU | 64.44% | 37.62% | -1.81 | 79.87 | 99.64 | 11.8 | ~12 | [v-934](https://edgefirst.studio/public/validation/v-934/details?mode=charts) |
|
| 179 |
| Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 67.07% | 39.43% | +0.00 | 72.33 | 97.67 | 54.8 | ~55 | [v-92c](https://edgefirst.studio/public/validation/v-92c/details?mode=charts) |
|
| 180 |
+
| | Apple iPhone 17 Pro — CoreML Neural Engine (FP16) | 65.98% | 38.80% | -0.63 | 33.57 | 42.62 | 58.0 | ~30 | [v-f77](https://edgefirst.studio/public/validation/v-f77/details?mode=charts) |
|
| 181 |
+
| | Apple iPhone 17 Pro — CoreML Metal GPU (FP16) | 66.00% | 38.72% | -0.71 | 85.00 | 95.86 | 22.6 | ~12 | [v-f78](https://edgefirst.studio/public/validation/v-f78/details?mode=charts) |
|
| 182 |
+
| | Apple iPhone 17 Pro — CoreML CPU (FP16) | 65.98% | 38.66% | -0.77 | 177.14 | 191.83 | 11.2 | ~6 | [v-f7a](https://edgefirst.studio/public/validation/v-f7a/details?mode=charts) |
|
| 183 |
+
| | Apple iPhone 15 Pro — CoreML Neural Engine (FP16) | 65.98% | 38.80% | -0.63 | 39.88 | 53.11 | 48.5 | ~25 | [v-f4c](https://edgefirst.studio/public/validation/v-f4c/details?mode=charts) |
|
| 184 |
+
| | Apple iPhone 15 Pro — CoreML Metal GPU (FP16) | 66.00% | 38.71% | -0.72 | 212.26 | 228.95 | 9.2 | ~5 | [v-f61](https://edgefirst.studio/public/validation/v-f61/details?mode=charts) |
|
| 185 |
+
| | Apple iPhone 15 Pro — CoreML CPU (FP16) | 65.98% | 38.68% | -0.75 | 211.81 | 234.39 | 9.3 | ~5 | [v-f06](https://edgefirst.studio/public/validation/v-f06/details?mode=charts) |
|
| 186 |
|
| 187 |
> **⚠ Below expectations — under investigation.** The rows marked ⚠ above measure more than 10 percentage points below the same training session's float reference: the model accuracy on that platform is below our expectations. We publish the measured numbers rather than hiding them, and we are investigating the results to make improvements — the next snapshot of this card will reflect any recovered accuracy.
|
| 188 |
|