sebastientaylor commited on
Commit
9dc4194
·
verified ·
1 Parent(s): 50b74db

Update model card for yolo11-seg

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -87,6 +87,7 @@ Row conventions in the table below:
87
  | Nano | ONNX FP32 (AWS Graviton · 48-core) | 52.25% | 30.16% | +0.00 | 37.23 | 49.88 | 100.0 | [v-725](https://edgefirst.studio/public/validation/v-725/details?mode=charts) |
88
  | Nano | ONNX FP32 (CUDA) | 52.22% | 30.16% | ref | 10.97 | 21.23 | 239.0 | [v-6e3](https://edgefirst.studio/public/validation/v-6e3/details?mode=charts) |
89
  | Nano | ONNX FP16 (CUDA) | 52.22% | 30.15% | -0.01 | 8.43 | 18.55 | 320.0 | [v-6e5](https://edgefirst.studio/public/validation/v-6e5/details?mode=charts) |
 
90
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 37.52% | 21.48% | -8.68 | 108.47 | 149.81 | 8.0 | [v-700](https://edgefirst.studio/public/validation/v-700/details?mode=charts) |
91
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 47.33% | 26.61% | -3.55 | 103.53 | 177.39 | 9.0 | [v-6ea](https://edgefirst.studio/public/validation/v-6ea/details?mode=charts) |
92
  | Nano | NXP i.MX 95 + eIQ Neutron NPU | Not supported | — | — | — | — | — | [v-6ed](https://edgefirst.studio/public/validation/v-6ed/details?mode=charts) |
@@ -96,6 +97,7 @@ Row conventions in the table below:
96
  | Small | ONNX FP32 (AWS Graviton · 48-core) | 60.89% | 35.25% | -0.02 | 91.68 | 105.25 | 42.5 | [v-726](https://edgefirst.studio/public/validation/v-726/details?mode=charts) |
97
  | Small | ONNX FP32 (CUDA) | 60.88% | 35.27% | ref | 19.62 | 30.41 | 154.0 | [v-6e6](https://edgefirst.studio/public/validation/v-6e6/details?mode=charts) |
98
  | Small | ONNX FP16 (CUDA) | 60.84% | 35.28% | +0.01 | 13.20 | 25.02 | 225.0 | [v-6e7](https://edgefirst.studio/public/validation/v-6e7/details?mode=charts) |
 
99
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 58.53% | 33.89% | -1.38 | 38.46 | 56.73 | 24.0 | [v-6f1](https://edgefirst.studio/public/validation/v-6f1/details?mode=charts) |
100
  | Small | NVIDIA Jetson Orin Nano (TensorRT FP16) | 60.85% | 35.28% | +0.01 | 14.67 | 44.29 | 99.0 | [v-6cd](https://edgefirst.studio/public/validation/v-6cd/details?mode=charts) |
101
  | Medium | ONNX FP32 (AWS Graviton · 48-core) | 66.25% | — | ref | 168.86 | 177.75 | 24.0 | [v-72b](https://edgefirst.studio/public/validation/v-72b/details?mode=charts) |
 
87
  | Nano | ONNX FP32 (AWS Graviton · 48-core) | 52.25% | 30.16% | +0.00 | 37.23 | 49.88 | 100.0 | [v-725](https://edgefirst.studio/public/validation/v-725/details?mode=charts) |
88
  | Nano | ONNX FP32 (CUDA) | 52.22% | 30.16% | ref | 10.97 | 21.23 | 239.0 | [v-6e3](https://edgefirst.studio/public/validation/v-6e3/details?mode=charts) |
89
  | Nano | ONNX FP16 (CUDA) | 52.22% | 30.15% | -0.01 | 8.43 | 18.55 | 320.0 | [v-6e5](https://edgefirst.studio/public/validation/v-6e5/details?mode=charts) |
90
+ | Nano | macOS CoreML — Metal GPU (FP16) | 51.85% | 29.94% | -0.22 | 6.86 | 18.07 | 266.0 | [v-739](https://edgefirst.studio/public/validation/v-739/details?mode=charts) |
91
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 37.52% | 21.48% | -8.68 | 108.47 | 149.81 | 8.0 | [v-700](https://edgefirst.studio/public/validation/v-700/details?mode=charts) |
92
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 47.33% | 26.61% | -3.55 | 103.53 | 177.39 | 9.0 | [v-6ea](https://edgefirst.studio/public/validation/v-6ea/details?mode=charts) |
93
  | Nano | NXP i.MX 95 + eIQ Neutron NPU | Not supported | — | — | — | — | — | [v-6ed](https://edgefirst.studio/public/validation/v-6ed/details?mode=charts) |
 
97
  | Small | ONNX FP32 (AWS Graviton · 48-core) | 60.89% | 35.25% | -0.02 | 91.68 | 105.25 | 42.5 | [v-726](https://edgefirst.studio/public/validation/v-726/details?mode=charts) |
98
  | Small | ONNX FP32 (CUDA) | 60.88% | 35.27% | ref | 19.62 | 30.41 | 154.0 | [v-6e6](https://edgefirst.studio/public/validation/v-6e6/details?mode=charts) |
99
  | Small | ONNX FP16 (CUDA) | 60.84% | 35.28% | +0.01 | 13.20 | 25.02 | 225.0 | [v-6e7](https://edgefirst.studio/public/validation/v-6e7/details?mode=charts) |
100
+ | Small | macOS CoreML — Neural Engine (FP16) | 60.16% | 34.89% | -0.38 | 6.81 | 13.26 | 254.0 | [v-730](https://edgefirst.studio/public/validation/v-730/details?mode=charts) |
101
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 58.53% | 33.89% | -1.38 | 38.46 | 56.73 | 24.0 | [v-6f1](https://edgefirst.studio/public/validation/v-6f1/details?mode=charts) |
102
  | Small | NVIDIA Jetson Orin Nano (TensorRT FP16) | 60.85% | 35.28% | +0.01 | 14.67 | 44.29 | 99.0 | [v-6cd](https://edgefirst.studio/public/validation/v-6cd/details?mode=charts) |
103
  | Medium | ONNX FP32 (AWS Graviton · 48-core) | 66.25% | — | ref | 168.86 | 177.75 | 24.0 | [v-72b](https://edgefirst.studio/public/validation/v-72b/details?mode=charts) |