sebastientaylor commited on
Commit
dacc58e
Β·
verified Β·
1 Parent(s): de95102

Update model card for yolov8-det

Browse files
Files changed (1) hide show
  1. README.md +19 -8
README.md CHANGED
@@ -25,16 +25,22 @@ model-index:
25
  metrics:
26
  - name: "mAP@0.5 (Nano ONNX FP32)"
27
  type: map_50
28
- value: 50.56
29
  - name: "mAP@0.5-0.95 (Nano ONNX FP32)"
30
  type: map
31
- value: 35.83
32
  - name: "mAP@0.5 (Small ONNX FP32)"
33
  type: map_50
34
- value: 59.37
35
  - name: "mAP@0.5-0.95 (Small ONNX FP32)"
36
  type: map
37
- value: 43.16
 
 
 
 
 
 
38
  ---
39
 
40
  # YOLOv8 Detection β€” EdgeFirst Model Zoo
@@ -57,9 +63,9 @@ Accuracy ceiling for each size, measured against COCO `val2017` (5,000 images) w
57
 
58
  | Size | Params | GFLOPs | mAP@0.5 | mAP@0.5-0.95 | mAP@0.75 | Source |
59
  |------|--------|--------|---------|--------------|----------|--------|
60
- | Nano | 3.2M | 8.9 | 50.56% | 35.83% | 38.97% | [v-51b](https://edgefirst.studio/public/validation/v-51b/details?mode=charts) |
61
- | Small | 11.2M | 28.8 | 59.37% | 43.16% | 46.71% | [v-51d](https://edgefirst.studio/public/validation/v-51d/details?mode=charts) |
62
- | Medium | 25.9M | 79.3 | β€” | β€” | β€” | β€” |
63
  | Large | 43.7M | 165.7 | β€” | β€” | β€” | β€” |
64
  | XLarge | 68.2M | 258.5 | β€” | β€” | β€” | β€” |
65
 
@@ -79,18 +85,23 @@ Row conventions in the table below:
79
 
80
  | Size | Platform | mAP@0.5 | Ξ” vs FP32 (pp) | mAP@0.5-0.95 | Inference (ms) | End-to-end (ms) | Throughput (FPS) | Source |
81
  |------|----------|---------|----------------|--------------|----------------|-----------------|------------------|--------|
 
82
  | Nano | macOS CoreML β€” Neural Engine (FP16) | 50.53% | -0.03 | 35.83% | 1.75 | 5.53 | 749.6 | [v-514](https://edgefirst.studio/public/validation/v-514/details?mode=charts) |
83
  | Nano | macOS CoreML β€” Metal GPU (FP16) | 50.52% | -0.04 | 35.83% | 3.77 | 7.73 | 431.0 | [v-51a](https://edgefirst.studio/public/validation/v-51a/details?mode=charts) |
84
  | Nano | macOS CoreML β€” CPU (FP16) | 50.56% | ref | 35.83% | 17.00 | 21.78 | 116.5 | [v-51b](https://edgefirst.studio/public/validation/v-51b/details?mode=charts) |
85
  | 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) |
86
- | 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) |
 
87
  | 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) |
88
  | 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) |
 
89
  | Small | macOS CoreML β€” 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) |
90
  | Small | macOS CoreML β€” 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) |
91
  | Small | macOS CoreML β€” CPU (FP16) | 59.37% | ref | 43.16% | 32.31 | 37.02 | 59.5 | [v-51d](https://edgefirst.studio/public/validation/v-51d/details?mode=charts) |
 
92
  | 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) |
93
  | 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) |
 
94
 
95
 
96
 
 
25
  metrics:
26
  - name: "mAP@0.5 (Nano ONNX FP32)"
27
  type: map_50
28
+ value: 50.49
29
  - name: "mAP@0.5-0.95 (Nano ONNX FP32)"
30
  type: map
31
+ value: 35.79
32
  - name: "mAP@0.5 (Small ONNX FP32)"
33
  type: map_50
34
+ value: 59.4
35
  - name: "mAP@0.5-0.95 (Small ONNX FP32)"
36
  type: map
37
+ value: 43.22
38
+ - name: "mAP@0.5 (Medium ONNX FP32)"
39
+ type: map_50
40
+ value: 64.68
41
+ - name: "mAP@0.5-0.95 (Medium ONNX FP32)"
42
+ type: map
43
+ value: 48.4
44
  ---
45
 
46
  # YOLOv8 Detection β€” EdgeFirst Model Zoo
 
63
 
64
  | Size | Params | GFLOPs | mAP@0.5 | mAP@0.5-0.95 | mAP@0.75 | Source |
65
  |------|--------|--------|---------|--------------|----------|--------|
66
+ | Nano | 3.2M | 8.9 | 50.49% | 35.79% | 38.86% | [v-6fc](https://edgefirst.studio/public/validation/v-6fc/details?mode=charts) |
67
+ | Small | 11.2M | 28.8 | 59.40% | 43.22% | 46.68% | [v-6fd](https://edgefirst.studio/public/validation/v-6fd/details?mode=charts) |
68
+ | Medium | 25.9M | 79.3 | 64.68% | 48.40% | 52.62% | [v-702](https://edgefirst.studio/public/validation/v-702/details?mode=charts) |
69
  | Large | 43.7M | 165.7 | β€” | β€” | β€” | β€” |
70
  | XLarge | 68.2M | 258.5 | β€” | β€” | β€” | β€” |
71
 
 
85
 
86
  | Size | Platform | mAP@0.5 | Ξ” vs FP32 (pp) | mAP@0.5-0.95 | Inference (ms) | End-to-end (ms) | Throughput (FPS) | Source |
87
  |------|----------|---------|----------------|--------------|----------------|-----------------|------------------|--------|
88
+ | Nano | ONNX FP32 (CUDA) | 50.49% | ref | 35.79% | 6.31 | 11.88 | 448.0 | [v-6fc](https://edgefirst.studio/public/validation/v-6fc/details?mode=charts) |
89
  | Nano | macOS CoreML β€” Neural Engine (FP16) | 50.53% | -0.03 | 35.83% | 1.75 | 5.53 | 749.6 | [v-514](https://edgefirst.studio/public/validation/v-514/details?mode=charts) |
90
  | Nano | macOS CoreML β€” Metal GPU (FP16) | 50.52% | -0.04 | 35.83% | 3.77 | 7.73 | 431.0 | [v-51a](https://edgefirst.studio/public/validation/v-51a/details?mode=charts) |
91
  | Nano | macOS CoreML β€” CPU (FP16) | 50.56% | ref | 35.83% | 17.00 | 21.78 | 116.5 | [v-51b](https://edgefirst.studio/public/validation/v-51b/details?mode=charts) |
92
  | 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) |
93
+ | Nano | NXP i.MX 95 + eIQ Neutron NPU | 48.77% | -1.72 | 34.34% | 46.14 | 73.35 | 77.0 | [v-6b9](https://edgefirst.studio/public/validation/v-6b9/details?mode=charts) |
94
+ | 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) |
95
  | 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) |
96
  | 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) |
97
+ | 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) |
98
  | Small | macOS CoreML β€” 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) |
99
  | Small | macOS CoreML β€” 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) |
100
  | Small | macOS CoreML β€” CPU (FP16) | 59.37% | ref | 43.16% | 32.31 | 37.02 | 59.5 | [v-51d](https://edgefirst.studio/public/validation/v-51d/details?mode=charts) |
101
+ | 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) |
102
  | 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) |
103
  | 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) |
104
+ | Medium | ONNX FP32 (CUDA) | 64.68% | ref | 48.40% | 23.10 | 29.83 | 148.0 | [v-702](https://edgefirst.studio/public/validation/v-702/details?mode=charts) |
105
 
106
 
107