Hugging Face's logo

qualcomm
/
YOLO26-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
9cf3107
·
verified ·
1 Parent(s): d8c0d34

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (1) hide show
  1. README.md +85 -77
README.md CHANGED
@@ -15,18 +15,18 @@ pipeline_tag: image-segmentation
15
  Ultralytics YOLO26 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.
16
 
17
  This is based on the implementation of YOLO26-Segmentation found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/yolo26_seg) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
22
  ## Getting Started
23
  Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
24
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/yolo26_seg) Python library to compile and export the model with your own:
25
  - Custom weights (e.g., fine-tuned checkpoints)
26
  - Custom input shapes
27
  - Target device and runtime configurations
28
 
29
- See our repository for [YOLO26-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/yolo26_seg) for usage instructions.
30
 
31
 
32
  ## Model Details
@@ -34,87 +34,95 @@ See our repository for [YOLO26-Segmentation on GitHub](https://github.com/qualco
34
  **Model Type:** Model_use_case.semantic_segmentation
35
 
36
  **Model Stats:**
37
- - Model checkpoint: YOLO26N-Seg
38
  - Input resolution: 640x640
39
- - Number of output classes: 80
40
- - Number of parameters: 2.7M
41
  - Model size (float): 9.29 MB
42
  - Model size (w8a16): 5.25 MB
 
 
43
 
44
  ## Performance Summary
45
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
46
  |---|---|---|---|---|---|---
47
- | YOLO26-Segmentation | ONNX | float | Snapdragon® X2 Elite | 4.088 ms | 17 - 17 MB | NPU
48
- | YOLO26-Segmentation | ONNX | float | Snapdragon® X Elite | 8.266 ms | 17 - 17 MB | NPU
49
- | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.757 ms | 17 - 224 MB | NPU
50
- | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 16.263 ms | 17 - 241 MB | NPU
51
- | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.114 ms | 10 - 22 MB | NPU
52
- | YOLO26-Segmentation | ONNX | float | Qualcomm® QCS8450 | 16.263 ms | 17 - 241 MB | NPU
53
- | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 12.73 ms | 15 - 18 MB | NPU
54
- | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.266 ms | 17 - 17 MB | NPU
55
- | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.435 ms | 15 - 192 MB | NPU
56
- | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.435 ms | 15 - 192 MB | NPU
57
- | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.939 ms | 12 - 190 MB | NPU
58
- | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.939 ms | 9 - 9 MB | NPU
59
- | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.436 ms | 7 - 7 MB | NPU
60
- | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.821 ms | 8 - 245 MB | NPU
61
- | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.411 ms | 8 - 246 MB | NPU
62
- | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 20.647 ms | 8 - 10 MB | NPU
63
- | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.158 ms | 8 - 10 MB | NPU
64
- | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® QCS8450 | 8.411 ms | 8 - 246 MB | NPU
65
- | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.663 ms | 8 - 10 MB | NPU
66
- | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.436 ms | 7 - 7 MB | NPU
67
- | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.826 ms | 1 - 93 MB | NPU
68
- | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.826 ms | 1 - 93 MB | NPU
69
- | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.504 ms | 0 - 98 MB | NPU
70
- | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 3.304 ms | 5 - 5 MB | NPU
71
- | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.564 ms | 5 - 5 MB | NPU
72
- | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.855 ms | 5 - 185 MB | NPU
73
- | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.943 ms | 3 - 206 MB | NPU
74
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 16.879 ms | 1 - 158 MB | NPU
75
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.083 ms | 5 - 6 MB | NPU
76
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.827 ms | 0 - 160 MB | NPU
77
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.827 ms | 0 - 160 MB | NPU
78
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.827 ms | 0 - 160 MB | NPU
79
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 10.943 ms | 3 - 206 MB | NPU
80
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.563 ms | 7 - 17 MB | NPU
81
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.564 ms | 5 - 5 MB | NPU
82
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.203 ms | 0 - 160 MB | NPU
83
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.879 ms | 1 - 158 MB | NPU
84
- | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 10.967 ms | 0 - 175 MB | NPU
85
- | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.203 ms | 0 - 160 MB | NPU
86
- | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.463 ms | 5 - 169 MB | NPU
87
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.786 ms | 2 - 2 MB | NPU
88
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.611 ms | 2 - 2 MB | NPU
89
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.481 ms | 2 - 212 MB | NPU
90
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 9.495 ms | 1 - 188 MB | NPU
91
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.138 ms | 2 - 5 MB | NPU
92
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.89 ms | 0 - 187 MB | NPU
93
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8650P | 5.89 ms | 0 - 187 MB | NPU
94
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8255P | 5.89 ms | 0 - 187 MB | NPU
95
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.617 ms | 0 - 6 MB | NPU
96
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.611 ms | 2 - 2 MB | NPU
97
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 25.212 ms | 2 - 186 MB | NPU
98
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 5.455 ms | 2 - 194 MB | NPU
99
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.563 ms | 2 - 192 MB | NPU
100
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 9.495 ms | 1 - 188 MB | NPU
101
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.563 ms | 2 - 192 MB | NPU
102
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.313 ms | 2 - 197 MB | NPU
103
- | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.455 ms | 2 - 194 MB | NPU
104
- | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.108 ms | 3 - 192 MB | NPU
105
- | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 11.336 ms | 4 - 212 MB | NPU
106
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 17.225 ms | 4 - 165 MB | NPU
107
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.492 ms | 4 - 110 MB | NPU
108
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8775P | 7.14 ms | 4 - 170 MB | NPU
109
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8650P | 7.14 ms | 4 - 170 MB | NPU
110
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8255P | 7.14 ms | 4 - 170 MB | NPU
111
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 11.336 ms | 4 - 212 MB | NPU
112
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 8.073 ms | 4 - 23 MB | NPU
113
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.211 ms | 0 - 169 MB | NPU
114
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA7255P | 17.225 ms | 4 - 165 MB | NPU
115
- | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8295P | 11.462 ms | 4 - 182 MB | NPU
116
- | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.211 ms | 0 - 169 MB | NPU
117
- | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.767 ms | 0 - 165 MB | NPU
 
 
 
 
 
 
 
 
118
 
119
  ## License
120
  * The license for the original implementation of YOLO26-Segmentation can be found
 
15
  Ultralytics YOLO26 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.
16
 
17
  This is based on the implementation of YOLO26-Segmentation found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment).
18
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/yolo26_seg) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
21
 
22
  ## Getting Started
23
  Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
24
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/yolo26_seg) Python library to compile and export the model with your own:
25
  - Custom weights (e.g., fine-tuned checkpoints)
26
  - Custom input shapes
27
  - Target device and runtime configurations
28
 
29
+ See our repository for [YOLO26-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/yolo26_seg) for usage instructions.
30
 
31
 
32
  ## Model Details
 
34
  **Model Type:** Model_use_case.semantic_segmentation
35
 
36
  **Model Stats:**
 
37
  - Input resolution: 640x640
38
+ - Model checkpoint: YOLO26N-Seg
 
39
  - Model size (float): 9.29 MB
40
  - Model size (w8a16): 5.25 MB
41
+ - Number of output classes: 80
42
+ - Number of parameters: 2.7M
43
 
44
  ## Performance Summary
45
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
46
  |---|---|---|---|---|---|---
47
+ | YOLO26-Segmentation | ONNX | float | Snapdragon® X2 Elite | 4.101 ms | 17 - 17 MB | NPU
48
+ | YOLO26-Segmentation | ONNX | float | Snapdragon® X Elite | 8.412 ms | 17 - 17 MB | NPU
49
+ | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.724 ms | 17 - 224 MB | NPU
50
+ | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 16.364 ms | 17 - 244 MB | NPU
51
+ | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 9.174 ms | 15 - 19 MB | NPU
52
+ | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.15 ms | 10 - 22 MB | NPU
53
+ | YOLO26-Segmentation | ONNX | float | Qualcomm® QCS8450 | 16.364 ms | 17 - 244 MB | NPU
54
+ | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.68 ms | 15 - 18 MB | NPU
55
+ | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.412 ms | 17 - 17 MB | NPU
56
+ | YOLO26-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.436 ms | 12 - 190 MB | NPU
57
+ | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.436 ms | 12 - 190 MB | NPU
58
+ | YOLO26-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.939 ms | 12 - 193 MB | NPU
59
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® X2 Elite | 2.706 ms | 9 - 9 MB | NPU
60
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® X Elite | 6.477 ms | 7 - 7 MB | NPU
61
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.804 ms | 0 - 234 MB | NPU
62
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.406 ms | 8 - 243 MB | NPU
63
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 20.19 ms | 8 - 11 MB | NPU
64
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.521 ms | 8 - 11 MB | NPU
65
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.141 ms | 8 - 10 MB | NPU
66
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® QCS8450 | 8.406 ms | 8 - 243 MB | NPU
67
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.851 ms | 8 - 10 MB | NPU
68
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.477 ms | 7 - 7 MB | NPU
69
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 31.806 ms | 9 - 221 MB | NPU
70
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 7.504 ms | 8 - 224 MB | NPU
71
+ | YOLO26-Segmentation | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.813 ms | 0 - 92 MB | NPU
72
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.813 ms | 0 - 92 MB | NPU
73
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.512 ms | 0 - 96 MB | NPU
74
+ | YOLO26-Segmentation | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 7.504 ms | 8 - 224 MB | NPU
75
+ | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 3.272 ms | 5 - 5 MB | NPU
76
+ | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.492 ms | 5 - 5 MB | NPU
77
+ | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.844 ms | 5 - 184 MB | NPU
78
+ | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.929 ms | 4 - 207 MB | NPU
79
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 6.611 ms | 5 - 16 MB | NPU
80
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 16.847 ms | 1 - 158 MB | NPU
81
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.086 ms | 5 - 6 MB | NPU
82
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.86 ms | 0 - 162 MB | NPU
83
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.86 ms | 0 - 162 MB | NPU
84
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.86 ms | 0 - 162 MB | NPU
85
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 10.929 ms | 4 - 207 MB | NPU
86
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.57 ms | 7 - 17 MB | NPU
87
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.492 ms | 5 - 5 MB | NPU
88
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.223 ms | 5 - 167 MB | NPU
89
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.847 ms | 1 - 158 MB | NPU
90
+ | YOLO26-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 10.958 ms | 0 - 174 MB | NPU
91
+ | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.223 ms | 5 - 167 MB | NPU
92
+ | YOLO26-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.461 ms | 5 - 170 MB | NPU
93
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.787 ms | 2 - 2 MB | NPU
94
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.597 ms | 2 - 2 MB | NPU
95
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.481 ms | 0 - 211 MB | NPU
96
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.012 ms | 1 - 8 MB | NPU
97
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 9.52 ms | 1 - 188 MB | NPU
98
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.122 ms | 2 - 4 MB | NPU
99
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.873 ms | 2 - 188 MB | NPU
100
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8650P | 5.873 ms | 2 - 188 MB | NPU
101
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8255P | 5.873 ms | 2 - 188 MB | NPU
102
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.635 ms | 1 - 7 MB | NPU
103
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.597 ms | 2 - 2 MB | NPU
104
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 24.794 ms | 2 - 187 MB | NPU
105
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 5.504 ms | 2 - 193 MB | NPU
106
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.564 ms | 0 - 189 MB | NPU
107
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 9.52 ms | 1 - 188 MB | NPU
108
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.564 ms | 0 - 189 MB | NPU
109
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.292 ms | 2 - 196 MB | NPU
110
+ | YOLO26-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.504 ms | 2 - 193 MB | NPU
111
+ | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.094 ms | 4 - 193 MB | NPU
112
+ | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 11.324 ms | 4 - 210 MB | NPU
113
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 7.025 ms | 4 - 24 MB | NPU
114
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 17.281 ms | 4 - 165 MB | NPU
115
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.472 ms | 4 - 7 MB | NPU
116
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8775P | 7.145 ms | 4 - 170 MB | NPU
117
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8650P | 7.145 ms | 4 - 170 MB | NPU
118
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8255P | 7.145 ms | 4 - 170 MB | NPU
119
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 11.324 ms | 4 - 210 MB | NPU
120
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.843 ms | 4 - 23 MB | NPU
121
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.19 ms | 0 - 169 MB | NPU
122
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA7255P | 17.281 ms | 4 - 165 MB | NPU
123
+ | YOLO26-Segmentation | TFLITE | float | Qualcomm® SA8295P | 11.454 ms | 4 - 181 MB | NPU
124
+ | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.19 ms | 0 - 169 MB | NPU
125
+ | YOLO26-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.762 ms | 0 - 167 MB | NPU
126
 
127
  ## License
128
  * The license for the original implementation of YOLO26-Segmentation can be found