Update model card for yolov5-det

README.md

@@ -37,10 +37,10 @@ model-index:
             value: 41.26
           - name: "mAP@0.5 (Medium ONNX FP32)"
             type: map_50
-            value: 63.3
+            value: 63.29
           - name: "mAP@0.5-0.95 (Medium ONNX FP32)"
             type: map
-            value: 47.0
+            value: 46.99
 ---
 
 # YOLOv5 Detection — EdgeFirst Model Zoo
@@ -66,7 +66,7 @@ Accuracy ceiling for each size, measured against COCO `val2017` (5,000 images) w
 |------|--------|--------|---------|--------------|----------|--------|
 | Nano | 1.9M | 4.5 | 47.75% | 32.95% | 35.61% | [v-6f0](https://edgefirst.studio/public/validation/v-6f0/details?mode=charts) |
 | Small | 7.2M | 16.5 | 57.33% | 41.26% | 44.93% | [v-6f4](https://edgefirst.studio/public/validation/v-6f4/details?mode=charts) |
-| Medium | 21.2M | 49.0 | 63.30% | 47.00% | 51.35% | [v-717](https://edgefirst.studio/public/validation/v-717/details?mode=charts) |
+| Medium | 21.2M | 49.0 | 63.29% | 46.99% | 51.32% | [v-6f6](https://edgefirst.studio/public/validation/v-6f6/details?mode=charts) |
 | Large | 46.5M | 109.1 | — | — | — | — |
 | XLarge | 86.7M | 205.7 | — | — | — | — |
 
@@ -110,10 +110,10 @@ Row conventions in the table below:
 | Small | NXP ARA240 (Kinara DVM) | 54.54% | -2.79 | 37.67% | 13.51 | 26.74 | 97.0 | [v-6be](https://edgefirst.studio/public/validation/v-6be/details?mode=charts) |
 | Small | Raspberry Pi 5 + Hailo-8L NPU | 55.58% | -1.76 | 39.75% | 29.34 | 39.87 | 32.1 | [v-4d7](https://edgefirst.studio/public/validation/v-4d7/details?mode=charts) |
 | Small | NVIDIA Jetson Orin Nano (TensorRT FP16) | 57.34% | +0.00 | 41.25% | 13.33 | 22.72 | 124.6 | [v-4d6](https://edgefirst.studio/public/validation/v-4d6/details?mode=charts) |
-| Medium | ONNX FP32 (AWS Graviton · 48-core) | 63.30% | ref | 47.00% | 154.67 | 163.39 | 24.0 | [v-717](https://edgefirst.studio/public/validation/v-717/details?mode=charts) |
-| Medium | ONNX FP32 (CUDA) | 63.29% | -0.01 | 46.99% | 33.90 | 40.43 | 96.0 | [v-6f6](https://edgefirst.studio/public/validation/v-6f6/details?mode=charts) |
-| Medium | ONNX FP16 (CUDA) | 63.27% | -0.03 | 46.93% | 20.12 | 26.31 | 167.0 | [v-6f7](https://edgefirst.studio/public/validation/v-6f7/details?mode=charts) |
-| Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 63.31% | +0.01 | 46.96% | 44.25 | 56.88 | 88.5 | [v-6de](https://edgefirst.studio/public/validation/v-6de/details?mode=charts) |
+| Medium | ONNX FP32 (AWS Graviton · 48-core) | 63.30% | +0.01 | 47.00% | 154.67 | 163.39 | 24.0 | [v-717](https://edgefirst.studio/public/validation/v-717/details?mode=charts) |
+| Medium | ONNX FP32 (CUDA) | 63.29% | ref | 46.99% | 33.90 | 40.43 | 96.0 | [v-6f6](https://edgefirst.studio/public/validation/v-6f6/details?mode=charts) |
+| Medium | ONNX FP16 (CUDA) | 63.27% | -0.02 | 46.93% | 20.12 | 26.31 | 167.0 | [v-6f7](https://edgefirst.studio/public/validation/v-6f7/details?mode=charts) |
+| Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 63.31% | +0.02 | 46.96% | 44.25 | 56.88 | 88.5 | [v-6de](https://edgefirst.studio/public/validation/v-6de/details?mode=charts) |