Update model card for yolov5-det

README.md

@@ -63,9 +63,9 @@ Accuracy ceiling for each size, measured against COCO `val2017` (5,000 images) w
 
 | Size | Params | GFLOPs | mAP@0.5 | mAP@0.5-0.95 | mAP@0.75 | Source |
 |------|--------|--------|---------|--------------|----------|--------|
-| Nano | 1.9M | 4.5 | 47.77% | 32.93% | 35.68% | [v-1d56](https://test.edgefirst.studio/public/validation/v-1d56/details?mode=metrics) |
-| Small | 7.2M | 16.5 | 57.32% | 41.27% | 44.90% | [v-1d2e](https://test.edgefirst.studio/public/validation/v-1d2e/details?mode=metrics) |
-| Medium | 21.2M | 49.0 | 63.29% | 47.00% | 51.39% | [v-1d2f](https://test.edgefirst.studio/public/validation/v-1d2f/details?mode=metrics) |
+| Nano | 1.9M | 4.5 | 47.77% | 32.93% | 35.68% | [v-1d56](https://test.edgefirst.studio/public/validation/v-1d56/details?mode=info) |
+| Small | 7.2M | 16.5 | 57.32% | 41.27% | 44.90% | [v-1d2e](https://test.edgefirst.studio/public/validation/v-1d2e/details?mode=info) |
+| Medium | 21.2M | 49.0 | 63.29% | 47.00% | 51.39% | [v-1d2f](https://test.edgefirst.studio/public/validation/v-1d2f/details?mode=info) |
 | Large | 46.5M | 109.1 | — | — | — | — |
 | XLarge | 86.7M | 205.7 | — | — | — | — |
 
@@ -79,15 +79,15 @@ Rows without a number under the metric columns are validation sessions that are
 
 | Size | Platform | mAP@0.5 | Δ vs FP32 (pp) | mAP@0.5-0.95 | Inference (ms) | FPS (median) | Source |
 |------|----------|---------|----------------|--------------|----------------|--------------|--------|
-| Nano | ONNX FP32 (CPU) | 47.77% | +0.00 | 32.93% | 5.45 | 161.6 | [v-1d2d](https://test.edgefirst.studio/public/validation/v-1d2d/details?mode=metrics) |
-| Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 46.56% | -1.21 | 31.92% | 58.38 | 12.6 | [v-1d2b](https://test.edgefirst.studio/public/validation/v-1d2b/details?mode=metrics) |
-| Nano | NXP i.MX 95 + eIQ Neutron NPU | 46.02% | -1.75 | 31.19% | 11.95 | 58.7 | [v-1d2c](https://test.edgefirst.studio/public/validation/v-1d2c/details?mode=metrics) |
-| Nano | Raspberry Pi 5 + Hailo-8L NPU | 45.49% | -2.28 | 31.17% | 15.68 | 61.3 | [v-1d26](https://test.edgefirst.studio/public/validation/v-1d26/details?mode=metrics) |
-| Small | NXP i.MX 8M Plus + VeriSilicon NPU | 56.34% | -0.98 | 40.20% | 110.36 | 7.6 | [v-1d38](https://test.edgefirst.studio/public/validation/v-1d38/details?mode=metrics) |
-| Small | NXP i.MX 95 + eIQ Neutron NPU | 56.19% | -1.13 | 40.07% | 31.91 | 27.1 | [v-1d32](https://test.edgefirst.studio/public/validation/v-1d32/details?mode=metrics) |
-| Small | Raspberry Pi 5 + Hailo-8L NPU | 55.95% | -1.37 | 40.06% | 30.51 | 32.0 | [v-1d27](https://test.edgefirst.studio/public/validation/v-1d27/details?mode=metrics) |
-| Medium | NXP i.MX 95 + eIQ Neutron NPU | 62.74% | -0.55 | 46.52% | 77.14 | 11.9 | [v-1d39](https://test.edgefirst.studio/public/validation/v-1d39/details?mode=metrics) |
-| Medium | Raspberry Pi 5 + Hailo-8L NPU | 62.50% | -0.79 | 46.24% | 61.08 | 16.2 | [v-1d28](https://test.edgefirst.studio/public/validation/v-1d28/details?mode=metrics) |
+| Nano | ONNX FP32 (CPU) | 47.77% | +0.00 | 32.93% | 5.45 | 161.6 | [v-1d2d](https://test.edgefirst.studio/public/validation/v-1d2d/details?mode=info) |
+| Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 46.56% | -1.21 | 31.92% | 58.38 | 12.6 | [v-1d2b](https://test.edgefirst.studio/public/validation/v-1d2b/details?mode=info) |
+| Nano | NXP i.MX 95 + eIQ Neutron NPU | 46.02% | -1.75 | 31.19% | 11.95 | 58.7 | [v-1d2c](https://test.edgefirst.studio/public/validation/v-1d2c/details?mode=info) |
+| Nano | Raspberry Pi 5 + Hailo-8L NPU | 45.49% | -2.28 | 31.17% | 15.68 | 61.3 | [v-1d26](https://test.edgefirst.studio/public/validation/v-1d26/details?mode=info) |
+| Small | NXP i.MX 8M Plus + VeriSilicon NPU | 56.34% | -0.98 | 40.20% | 110.36 | 7.6 | [v-1d38](https://test.edgefirst.studio/public/validation/v-1d38/details?mode=info) |
+| Small | NXP i.MX 95 + eIQ Neutron NPU | 56.19% | -1.13 | 40.07% | 31.91 | 27.1 | [v-1d32](https://test.edgefirst.studio/public/validation/v-1d32/details?mode=info) |
+| Small | Raspberry Pi 5 + Hailo-8L NPU | 55.95% | -1.37 | 40.06% | 30.51 | 32.0 | [v-1d27](https://test.edgefirst.studio/public/validation/v-1d27/details?mode=info) |
+| Medium | NXP i.MX 95 + eIQ Neutron NPU | 62.74% | -0.55 | 46.52% | 77.14 | 11.9 | [v-1d39](https://test.edgefirst.studio/public/validation/v-1d39/details?mode=info) |
+| Medium | Raspberry Pi 5 + Hailo-8L NPU | 62.50% | -0.79 | 46.24% | 61.08 | 16.2 | [v-1d28](https://test.edgefirst.studio/public/validation/v-1d28/details?mode=info) |
 
 
 ---
@@ -140,7 +140,7 @@ for det in results.detections:
 Every measurement in the tables above is reachable through the EdgeFirst Studio validation framework. The `v-XXXX` Source link on each row resolves to a public Studio URL of the form:
 
 ```
-https://test.edgefirst.studio/public/validation/v-XXXX/details?mode=metrics
+https://test.edgefirst.studio/public/validation/v-XXXX/details?mode=info
 ```
 
 From there, the full provenance chain is one click deeper: training session ID, dataset version, calibration artifact, converter chain (e.g. TFLite quantizer + Neutron compile), validation parameters, and the host hardware description (hostname, kernel version, SoC, NPU, profiler version). The same model file you download from this repository embeds the same chain in its `edgefirst.json` metadata.