sebastientaylor commited on
Commit
cf2c95a
·
verified ·
1 Parent(s): 0ac0da6

Update model card for yolov8-det

Browse files
Files changed (1) hide show
  1. README.md +26 -14
README.md CHANGED
@@ -1,5 +1,5 @@
1
  ---
2
- license: apache-2.0
3
  library_name: edgefirst
4
  pipeline_tag: object-detection
5
  tags:
@@ -55,7 +55,7 @@ Part of the [EdgeFirst Model Zoo](https://huggingface.co/spaces/EdgeFirst/Models
55
  > [!NOTE]
56
  > Anchor-free DFL detection head. Detection and instance-segmentation variants.
57
 
58
- [![x86_64 | Linux](https://img.shields.io/badge/x86__64-Linux-6C757D?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![aarch64 | Linux](https://img.shields.io/badge/aarch64-Linux-718096?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![Apple | macOS](https://img.shields.io/badge/Apple-macOS-4B0082?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP i.MX 8M Plus](https://img.shields.io/badge/NXP-i.MX_8M_Plus-E8B820?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP i.MX 93](https://img.shields.io/badge/NXP-i.MX_93-8B7DC4?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP i.MX 95](https://img.shields.io/badge/NXP-i.MX_95-1FA0A8?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP ARA240](https://img.shields.io/badge/NXP-ARA240-5BB8F5?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![RPi5 + Hailo-8/8L](https://img.shields.io/badge/RPi5-Hailo--8%2F8L-D9534F?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NVIDIA Jetson](https://img.shields.io/badge/NVIDIA-Jetson-2E8B57?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models)
59
  ---
60
 
61
  ## Reference accuracy — ONNX FP32
@@ -98,13 +98,14 @@ Row conventions in the table below:
98
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 48.34% | -2.22 | 33.98% | 60.76 | 105.27 | 14.0 | [v-529](https://edgefirst.studio/public/validation/v-529/details?mode=charts) |
99
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 49.36% | -1.13 | 34.78% | 61.10 | 113.47 | 14.0 | [v-8c7](https://edgefirst.studio/public/validation/v-8c7/details?mode=charts) |
100
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 47.24% | -3.25 | 32.01% | 66.97 | 100.70 | 13.0 | [v-8c1](https://edgefirst.studio/public/validation/v-8c1/details?mode=charts) |
101
- | Nano | NXP i.MX 95 + eIQ Neutron NPU | 48.77% | -1.72 | 34.34% | 45.47 | 73.31 | 77.0 | [v-79e](https://edgefirst.studio/public/validation/v-79e/details?mode=charts) |
 
102
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 47.38% | -3.11 | 32.08% | 44.44 | 59.30 | 22.0 | [v-8b1](https://edgefirst.studio/public/validation/v-8b1/details?mode=charts) |
103
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 47.38% | -3.11 | 32.08% | 44.09 | 58.84 | 22.0 | [v-8af](https://edgefirst.studio/public/validation/v-8af/details?mode=charts) |
104
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 47.38% | -3.11 | 32.08% | 62.08 | 81.32 | 61.0 | [v-8b3](https://edgefirst.studio/public/validation/v-8b3/details?mode=charts) |
105
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 47.38% | -3.11 | 32.08% | 61.78 | 80.89 | 62.0 | [v-8b0](https://edgefirst.studio/public/validation/v-8b0/details?mode=charts) |
106
- | Nano | NXP ARA240 (Kinara DVM) | 45.71% | -4.78 | 31.48% | 7.42 | 47.14 | 225.5 | [v-6bb](https://edgefirst.studio/public/validation/v-6bb/details?mode=charts) |
107
- | Nano | NXP ARA240 (Kinara DVM) (FRDM) | 46.63% | -3.86 | 32.13% | 6.85 | 43.75 | 215.0 | [v-898](https://edgefirst.studio/public/validation/v-898/details?mode=charts) |
108
  | Nano | Raspberry Pi 5 + Hailo-8L NPU | 48.55% | -2.01 | 34.36% | 13.20 | 23.79 | 65.0 | [v-4d9](https://edgefirst.studio/public/validation/v-4d9/details?mode=charts) |
109
  | Nano | Raspberry Pi 5 + Hailo-8L NPU | 49.80% | -0.69 | 35.22% | 13.20 | 24.86 | 65.0 | [v-8df](https://edgefirst.studio/public/validation/v-8df/details?mode=charts) |
110
  | Nano | NVIDIA Jetson Orin Nano (TensorRT FP16) | 50.50% | -0.06 | 35.80% | 7.68 | 18.41 | 179.2 | [v-4d8](https://edgefirst.studio/public/validation/v-4d8/details?mode=charts) |
@@ -113,8 +114,11 @@ Row conventions in the table below:
113
  | Small | ONNX FP32 (CUDA) | 59.40% | ref | 43.22% | 15.47 | 21.25 | 203.0 | [v-6fd](https://edgefirst.studio/public/validation/v-6fd/details?mode=charts) |
114
  | Small | ONNX FP16 (CUDA) | 59.37% | -0.03 | 43.19% | 10.65 | 16.41 | 296.0 | [v-6fe](https://edgefirst.studio/public/validation/v-6fe/details?mode=charts) |
115
  | Small | macOS CoreML — Neural Engine (FP16) | 59.36% | -0.01 | 43.22% | 4.99 | 8.78 | 327.3 | [v-515](https://edgefirst.studio/public/validation/v-515/details?mode=charts) |
 
116
  | Small | macOS CoreML — Metal GPU (FP16) | 59.37% | +0.00 | 43.17% | 10.13 | 13.73 | 184.0 | [v-51c](https://edgefirst.studio/public/validation/v-51c/details?mode=charts) |
 
117
  | Small | macOS CoreML — CPU (FP16) | 59.37% | +0.00 | 43.16% | 32.31 | 37.02 | 59.5 | [v-51d](https://edgefirst.studio/public/validation/v-51d/details?mode=charts) |
 
118
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU | 55.89% | -3.51 | 38.36% | 122.49 | 155.93 | 8.0 | [v-7ae](https://edgefirst.studio/public/validation/v-7ae/details?mode=charts) |
119
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU | 57.96% | -1.44 | 41.90% | 116.54 | 165.48 | 8.0 | [v-7a3](https://edgefirst.studio/public/validation/v-7a3/details?mode=charts) |
120
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 58.80% | -0.60 | 42.45% | 116.71 | 168.28 | 8.0 | [v-93f](https://edgefirst.studio/public/validation/v-93f/details?mode=charts) |
@@ -124,8 +128,8 @@ Row conventions in the table below:
124
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 58.62% | -0.78 | 42.29% | 146.86 | 182.46 | 26.0 | [v-903](https://edgefirst.studio/public/validation/v-903/details?mode=charts) |
125
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 55.76% | -3.64 | 38.21% | 145.91 | 161.37 | 27.0 | [v-8fe](https://edgefirst.studio/public/validation/v-8fe/details?mode=charts) |
126
  | Small | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 58.62% | -0.78 | 42.29% | 141.60 | 174.37 | 27.0 | [v-8f3](https://edgefirst.studio/public/validation/v-8f3/details?mode=charts) |
127
- | Small | NXP ARA240 (Kinara DVM) | 54.79% | -4.61 | 38.18% | 11.59 | 25.06 | 119.0 | [v-6bc](https://edgefirst.studio/public/validation/v-6bc/details?mode=charts) |
128
- | Small | NXP ARA240 (Kinara DVM) (FRDM) | 56.70% | -2.70 | 39.81% | 10.28 | 24.15 | 143.0 | [v-8e4](https://edgefirst.studio/public/validation/v-8e4/details?mode=charts) |
129
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 57.80% | -1.57 | 41.77% | 30.37 | 40.86 | 28.8 | [v-4da](https://edgefirst.studio/public/validation/v-4da/details?mode=charts) |
130
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 58.52% | -0.88 | 42.34% | 30.36 | 45.07 | 29.0 | [v-8ec](https://edgefirst.studio/public/validation/v-8ec/details?mode=charts) |
131
  | Small | NVIDIA Jetson Orin Nano (TensorRT FP16) | 59.40% | +0.03 | 43.16% | 14.96 | 24.20 | 113.2 | [v-4db](https://edgefirst.studio/public/validation/v-4db/details?mode=charts) |
@@ -140,16 +144,15 @@ Row conventions in the table below:
140
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU | 62.65% | -2.03 | 46.64% | 222.08 | 271.35 | 4.0 | [v-779](https://edgefirst.studio/public/validation/v-779/details?mode=charts) |
141
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 63.49% | -1.19 | 47.22% | 222.33 | 274.39 | 4.0 | [v-983](https://edgefirst.studio/public/validation/v-983/details?mode=charts) |
142
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 60.40% | -4.28 | 42.66% | 228.25 | 261.97 | 4.0 | [v-97d](https://edgefirst.studio/public/validation/v-97d/details?mode=charts) |
143
- | Medium | NXP i.MX 95 + eIQ Neutron NPU | 60.37% | -4.31 | 42.68% | 395.18 | 407.52 | 10.0 | [v-778](https://edgefirst.studio/public/validation/v-778/details?mode=charts) |
144
- | Medium | NXP i.MX 95 + eIQ Neutron NPU | 62.67% | -2.01 | 46.52% | 396.24 | 420.77 | 10.0 | [v-774](https://edgefirst.studio/public/validation/v-774/details?mode=charts) |
145
- | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) | 63.51% | -1.17 | 47.11% | 396.05 | 422.54 | 10.0 | [v-863](https://edgefirst.studio/public/validation/v-863/details?mode=charts) |
146
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 63.51% | -1.17 | 47.11% | 101.26 | 135.73 | 10.0 | [v-974](https://edgefirst.studio/public/validation/v-974/details?mode=charts) |
147
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 60.37% | -4.31 | 42.68% | 135.40 | 149.92 | 7.0 | [v-96e](https://edgefirst.studio/public/validation/v-96e/details?mode=charts) |
148
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 63.51% | -1.17 | 47.11% | 393.79 | 429.57 | 10.0 | [v-976](https://edgefirst.studio/public/validation/v-976/details?mode=charts) |
149
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 60.37% | -4.31 | 42.68% | 392.42 | 408.62 | 10.0 | [v-96f](https://edgefirst.studio/public/validation/v-96f/details?mode=charts) |
150
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 63.51% | -1.17 | 47.11% | 387.27 | 419.61 | 10.0 | [v-94f](https://edgefirst.studio/public/validation/v-94f/details?mode=charts) |
151
- | Medium | NXP ARA240 (Kinara DVM) | 59.51% | -5.17 | 42.24% | 24.56 | 40.78 | 47.0 | [v-797](https://edgefirst.studio/public/validation/v-797/details?mode=charts) |
152
- | Medium | NXP ARA240 (Kinara DVM) (FRDM) | 59.99% | -4.69 | 42.66% | 21.49 | 34.36 | 54.0 | [v-908](https://edgefirst.studio/public/validation/v-908/details?mode=charts) |
153
  | Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.03% | -1.65 | 47.04% | 56.25 | 67.26 | 17.0 | [v-767](https://edgefirst.studio/public/validation/v-767/details?mode=charts) |
154
  | Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.88% | -0.80 | 47.67% | 56.26 | 71.51 | 17.0 | [v-90a](https://edgefirst.studio/public/validation/v-90a/details?mode=charts) |
155
  | Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 64.68% | +0.00 | 48.40% | 51.87 | 65.93 | 76.0 | [v-75c](https://edgefirst.studio/public/validation/v-75c/details?mode=charts) |
@@ -281,6 +284,14 @@ No sidecar files required; the model artifact is self-contained.
281
 
282
  ---
283
 
 
 
 
 
 
 
 
 
284
  ## Citation
285
 
286
  ```bibtex
@@ -289,7 +300,7 @@ No sidecar files required; the model artifact is self-contained.
289
  author = {Au-Zone Technologies},
290
  url = {https://huggingface.co/EdgeFirst/yolov8-det},
291
  year = {2026},
292
- license = {Apache-2.0},
293
  }
294
  ```
295
 
@@ -298,6 +309,7 @@ No sidecar files required; the model artifact is self-contained.
298
  <p align="center">
299
  <sub>
300
  <a href="https://edgefirst.studio">EdgeFirst Studio</a> · <a href="https://github.com/EdgeFirstAI">GitHub</a> · <a href="https://doc.edgefirst.ai">Docs</a> · <a href="https://www.au-zone.com">Au-Zone Technologies</a><br>
301
- Apache 2.0 · © Au-Zone Technologies Inc.
 
302
  </sub>
303
  </p>
 
1
  ---
2
+ license: agpl-3.0
3
  library_name: edgefirst
4
  pipeline_tag: object-detection
5
  tags:
 
55
  > [!NOTE]
56
  > Anchor-free DFL detection head. Detection and instance-segmentation variants.
57
 
58
+ [![x86_64 | Linux](https://img.shields.io/badge/x86__64-Linux-6C757D?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![aarch64 | Linux](https://img.shields.io/badge/aarch64-Linux-718096?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![Apple | macOS](https://img.shields.io/badge/Apple-macOS-4B0082?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP i.MX 8M Plus](https://img.shields.io/badge/NXP-i.MX_8M_Plus-E8B820?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP i.MX 93](https://img.shields.io/badge/NXP-i.MX_93-8B7DC4?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP i.MX 95](https://img.shields.io/badge/NXP-i.MX_95-1FA0A8?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NXP Ara240](https://img.shields.io/badge/NXP-Ara240-5BB8F5?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![RPi5 + Hailo-8/8L](https://img.shields.io/badge/RPi5-Hailo--8%2F8L-D9534F?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models) [![NVIDIA Jetson](https://img.shields.io/badge/NVIDIA-Jetson-2E8B57?style=flat-square)](https://huggingface.co/spaces/EdgeFirst/Models)
59
  ---
60
 
61
  ## Reference accuracy — ONNX FP32
 
98
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU | 48.34% | -2.22 | 33.98% | 60.76 | 105.27 | 14.0 | [v-529](https://edgefirst.studio/public/validation/v-529/details?mode=charts) |
99
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 49.36% | -1.13 | 34.78% | 61.10 | 113.47 | 14.0 | [v-8c7](https://edgefirst.studio/public/validation/v-8c7/details?mode=charts) |
100
  | Nano | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 47.24% | -3.25 | 32.01% | 66.97 | 100.70 | 13.0 | [v-8c1](https://edgefirst.studio/public/validation/v-8c1/details?mode=charts) |
101
+ | Nano | NXP i.MX 95 + eIQ Neutron NPU | 48.33% | -2.23 | 33.92% | 13.87 | 58.10 | 49.7 | [v-528](https://edgefirst.studio/public/validation/v-528/details?mode=charts) |
102
+ | Nano | NXP i.MX 95 + eIQ Neutron NPU — throughput | 48.77% | -1.72 | 34.34% | 45.47 | 73.31 | 77.0 | [v-79e](https://edgefirst.studio/public/validation/v-79e/details?mode=charts) |
103
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 47.38% | -3.11 | 32.08% | 44.44 | 59.30 | 22.0 | [v-8b1](https://edgefirst.studio/public/validation/v-8b1/details?mode=charts) |
104
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 47.38% | -3.11 | 32.08% | 44.09 | 58.84 | 22.0 | [v-8af](https://edgefirst.studio/public/validation/v-8af/details?mode=charts) |
105
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 47.38% | -3.11 | 32.08% | 62.08 | 81.32 | 61.0 | [v-8b3](https://edgefirst.studio/public/validation/v-8b3/details?mode=charts) |
106
  | Nano | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 47.38% | -3.11 | 32.08% | 61.78 | 80.89 | 62.0 | [v-8b0](https://edgefirst.studio/public/validation/v-8b0/details?mode=charts) |
107
+ | Nano | NXP Ara240 | 45.71% | -4.78 | 31.48% | 7.42 | 47.14 | 225.5 | [v-6bb](https://edgefirst.studio/public/validation/v-6bb/details?mode=charts) |
108
+ | Nano | NXP Ara240 (FRDM) | 46.63% | -3.86 | 32.13% | 6.85 | 43.75 | 215.0 | [v-898](https://edgefirst.studio/public/validation/v-898/details?mode=charts) |
109
  | Nano | Raspberry Pi 5 + Hailo-8L NPU | 48.55% | -2.01 | 34.36% | 13.20 | 23.79 | 65.0 | [v-4d9](https://edgefirst.studio/public/validation/v-4d9/details?mode=charts) |
110
  | Nano | Raspberry Pi 5 + Hailo-8L NPU | 49.80% | -0.69 | 35.22% | 13.20 | 24.86 | 65.0 | [v-8df](https://edgefirst.studio/public/validation/v-8df/details?mode=charts) |
111
  | Nano | NVIDIA Jetson Orin Nano (TensorRT FP16) | 50.50% | -0.06 | 35.80% | 7.68 | 18.41 | 179.2 | [v-4d8](https://edgefirst.studio/public/validation/v-4d8/details?mode=charts) |
 
114
  | Small | ONNX FP32 (CUDA) | 59.40% | ref | 43.22% | 15.47 | 21.25 | 203.0 | [v-6fd](https://edgefirst.studio/public/validation/v-6fd/details?mode=charts) |
115
  | Small | ONNX FP16 (CUDA) | 59.37% | -0.03 | 43.19% | 10.65 | 16.41 | 296.0 | [v-6fe](https://edgefirst.studio/public/validation/v-6fe/details?mode=charts) |
116
  | Small | macOS CoreML — Neural Engine (FP16) | 59.36% | -0.01 | 43.22% | 4.99 | 8.78 | 327.3 | [v-515](https://edgefirst.studio/public/validation/v-515/details?mode=charts) |
117
+ | Small | macOS CoreML — Neural Engine (FP16) | 58.80% | -0.60 | 42.78% | 5.01 | 8.46 | 343.0 | [v-9ed](https://edgefirst.studio/public/validation/v-9ed/details?mode=charts) |
118
  | Small | macOS CoreML — Metal GPU (FP16) | 59.37% | +0.00 | 43.17% | 10.13 | 13.73 | 184.0 | [v-51c](https://edgefirst.studio/public/validation/v-51c/details?mode=charts) |
119
+ | Small | macOS CoreML — Metal GPU (FP16) | 58.82% | -0.58 | 42.73% | 15.93 | 19.52 | 172.5 | [v-9ee](https://edgefirst.studio/public/validation/v-9ee/details?mode=charts) |
120
  | Small | macOS CoreML — CPU (FP16) | 59.37% | +0.00 | 43.16% | 32.31 | 37.02 | 59.5 | [v-51d](https://edgefirst.studio/public/validation/v-51d/details?mode=charts) |
121
+ | Small | macOS CoreML — CPU (FP16) | 58.83% | -0.57 | 42.70% | 32.00 | 36.09 | 60.0 | [v-9ef](https://edgefirst.studio/public/validation/v-9ef/details?mode=charts) |
122
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU | 55.89% | -3.51 | 38.36% | 122.49 | 155.93 | 8.0 | [v-7ae](https://edgefirst.studio/public/validation/v-7ae/details?mode=charts) |
123
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU | 57.96% | -1.44 | 41.90% | 116.54 | 165.48 | 8.0 | [v-7a3](https://edgefirst.studio/public/validation/v-7a3/details?mode=charts) |
124
  | Small | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 58.80% | -0.60 | 42.45% | 116.71 | 168.28 | 8.0 | [v-93f](https://edgefirst.studio/public/validation/v-93f/details?mode=charts) |
 
128
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 58.62% | -0.78 | 42.29% | 146.86 | 182.46 | 26.0 | [v-903](https://edgefirst.studio/public/validation/v-903/details?mode=charts) |
129
  | Small | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 55.76% | -3.64 | 38.21% | 145.91 | 161.37 | 27.0 | [v-8fe](https://edgefirst.studio/public/validation/v-8fe/details?mode=charts) |
130
  | Small | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 58.62% | -0.78 | 42.29% | 141.60 | 174.37 | 27.0 | [v-8f3](https://edgefirst.studio/public/validation/v-8f3/details?mode=charts) |
131
+ | Small | NXP Ara240 | 54.79% | -4.61 | 38.18% | 11.59 | 25.06 | 119.0 | [v-6bc](https://edgefirst.studio/public/validation/v-6bc/details?mode=charts) |
132
+ | Small | NXP Ara240 (FRDM) | 56.70% | -2.70 | 39.81% | 10.28 | 24.15 | 143.0 | [v-8e4](https://edgefirst.studio/public/validation/v-8e4/details?mode=charts) |
133
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 57.80% | -1.57 | 41.77% | 30.37 | 40.86 | 28.8 | [v-4da](https://edgefirst.studio/public/validation/v-4da/details?mode=charts) |
134
  | Small | Raspberry Pi 5 + Hailo-8L NPU | 58.52% | -0.88 | 42.34% | 30.36 | 45.07 | 29.0 | [v-8ec](https://edgefirst.studio/public/validation/v-8ec/details?mode=charts) |
135
  | Small | NVIDIA Jetson Orin Nano (TensorRT FP16) | 59.40% | +0.03 | 43.16% | 14.96 | 24.20 | 113.2 | [v-4db](https://edgefirst.studio/public/validation/v-4db/details?mode=charts) |
 
144
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU | 62.65% | -2.03 | 46.64% | 222.08 | 271.35 | 4.0 | [v-779](https://edgefirst.studio/public/validation/v-779/details?mode=charts) |
145
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 63.49% | -1.19 | 47.22% | 222.33 | 274.39 | 4.0 | [v-983](https://edgefirst.studio/public/validation/v-983/details?mode=charts) |
146
  | Medium | NXP i.MX 8M Plus + VeriSilicon NPU (FRDM) | 60.40% | -4.28 | 42.66% | 228.25 | 261.97 | 4.0 | [v-97d](https://edgefirst.studio/public/validation/v-97d/details?mode=charts) |
147
+ | Medium | NXP i.MX 95 + eIQ Neutron NPU — throughput | 60.37% | -4.31 | 42.68% | 395.18 | 407.52 | 10.0 | [v-778](https://edgefirst.studio/public/validation/v-778/details?mode=charts) |
148
+ | Medium | NXP i.MX 95 + eIQ Neutron NPU — throughput | 62.67% | -2.01 | 46.52% | 396.24 | 420.77 | 10.0 | [v-774](https://edgefirst.studio/public/validation/v-774/details?mode=charts) |
 
149
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 63.51% | -1.17 | 47.11% | 101.26 | 135.73 | 10.0 | [v-974](https://edgefirst.studio/public/validation/v-974/details?mode=charts) |
150
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — latency | 60.37% | -4.31 | 42.68% | 135.40 | 149.92 | 7.0 | [v-96e](https://edgefirst.studio/public/validation/v-96e/details?mode=charts) |
151
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 63.51% | -1.17 | 47.11% | 393.79 | 429.57 | 10.0 | [v-976](https://edgefirst.studio/public/validation/v-976/details?mode=charts) |
152
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (FRDM) — throughput | 60.37% | -4.31 | 42.68% | 392.42 | 408.62 | 10.0 | [v-96f](https://edgefirst.studio/public/validation/v-96f/details?mode=charts) |
153
  | Medium | NXP i.MX 95 + eIQ Neutron NPU (Phytec) — throughput | 63.51% | -1.17 | 47.11% | 387.27 | 419.61 | 10.0 | [v-94f](https://edgefirst.studio/public/validation/v-94f/details?mode=charts) |
154
+ | Medium | NXP Ara240 | 59.51% | -5.17 | 42.24% | 24.56 | 40.78 | 47.0 | [v-797](https://edgefirst.studio/public/validation/v-797/details?mode=charts) |
155
+ | Medium | NXP Ara240 (FRDM) | 59.99% | -4.69 | 42.66% | 21.49 | 34.36 | 54.0 | [v-908](https://edgefirst.studio/public/validation/v-908/details?mode=charts) |
156
  | Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.03% | -1.65 | 47.04% | 56.25 | 67.26 | 17.0 | [v-767](https://edgefirst.studio/public/validation/v-767/details?mode=charts) |
157
  | Medium | Raspberry Pi 5 + Hailo-8L NPU | 63.88% | -0.80 | 47.67% | 56.26 | 71.51 | 17.0 | [v-90a](https://edgefirst.studio/public/validation/v-90a/details?mode=charts) |
158
  | Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 64.68% | +0.00 | 48.40% | 51.87 | 65.93 | 76.0 | [v-75c](https://edgefirst.studio/public/validation/v-75c/details?mode=charts) |
 
284
 
285
  ---
286
 
287
+ ## License
288
+
289
+ Model **weights** in this repository are derived from [Ultralytics](https://github.com/ultralytics/ultralytics) YOLO and remain © Ultralytics Inc., licensed **AGPL-3.0** — use requires AGPL-3.0 compliance or an Ultralytics Enterprise License.
290
+
291
+ The **validation results, this model card, and its metadata** are Au-Zone Technologies' own contribution, licensed **[CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/)** (Attribution — NonCommercial) — see the repository `LICENSE` for the full text and citation requirements.
292
+
293
+ ---
294
+
295
  ## Citation
296
 
297
  ```bibtex
 
300
  author = {Au-Zone Technologies},
301
  url = {https://huggingface.co/EdgeFirst/yolov8-det},
302
  year = {2026},
303
+ license = {CC-BY-NC-4.0},
304
  }
305
  ```
306
 
 
309
  <p align="center">
310
  <sub>
311
  <a href="https://edgefirst.studio">EdgeFirst Studio</a> · <a href="https://github.com/EdgeFirstAI">GitHub</a> · <a href="https://doc.edgefirst.ai">Docs</a> · <a href="https://www.au-zone.com">Au-Zone Technologies</a><br>
312
+ Model weights © Ultralytics Inc. (AGPL-3.0) · Validation results &amp; card © 2026 Au-Zone Technologies (CC BY-NC 4.0)<br>
313
+ NXP<sup>®</sup>, i.MX, eIQ<sup>®</sup>, Neutron, and Ara240 are trademarks or products of NXP Semiconductors. Hailo is a trademark of Hailo Technologies Ltd. Jetson is a trademark of NVIDIA Corporation. All other trademarks are the property of their respective owners.
314
  </sub>
315
  </p>