Hugging Face's logo

qualcomm
/
YOLOE-Segmentation

Image Segmentation
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
51544bc
·
verified ·
1 Parent(s): 7b6b7d7

v0.58.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (1) hide show
  1. README.md +104 -59
README.md CHANGED
@@ -15,18 +15,18 @@ pipeline_tag: image-segmentation
15
  Ultralytics YOLOE 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 YOLOE-Segmentation found [here](https://github.com/THU-MIG/yoloe).
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/v0.57.3/src/qai_hub_models/models/yoloe_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/v0.57.3/src/qai_hub_models/models/yoloe_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 [YOLOE-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/yoloe_seg) for usage instructions.
30
 
31
 
32
  ## Model Details
@@ -42,63 +42,108 @@ See our repository for [YOLOE-Segmentation on GitHub](https://github.com/qualcom
42
  ## Performance Summary
43
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
44
  |---|---|---|---|---|---|---
45
- | YOLOE-Segmentation | ONNX | float | Snapdragon® X2 Elite | 15.676 ms | 176 - 176 MB | NPU
46
- | YOLOE-Segmentation | ONNX | float | Snapdragon® X Elite | 31.024 ms | 145 - 145 MB | NPU
47
- | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 24.169 ms | 17 - 289 MB | NPU
48
- | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 68.04 ms | 17 - 335 MB | NPU
49
- | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 30.679 ms | 0 - 95 MB | NPU
50
- | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8450 | 68.04 ms | 17 - 335 MB | NPU
51
- | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 18.194 ms | 12 - 232 MB | NPU
52
- | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.031 ms | 13 - 242 MB | NPU
53
- | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS9075 | 48.175 ms | 17 - 62 MB | NPU
54
- | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8750 | 18.194 ms | 12 - 232 MB | NPU
55
- | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS7181 | 31.024 ms | 145 - 145 MB | NPU
56
- | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 15.499 ms | 5 - 5 MB | NPU
57
- | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 29.182 ms | 5 - 5 MB | NPU
58
- | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 21.749 ms | 5 - 269 MB | NPU
59
- | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 62.519 ms | 5 - 315 MB | NPU
60
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 | 178.782 ms | 1 - 209 MB | NPU
61
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 28.102 ms | 5 - 7 MB | NPU
62
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 62.519 ms | 5 - 315 MB | NPU
63
- | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 17.151 ms | 5 - 219 MB | NPU
64
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 178.782 ms | 1 - 209 MB | NPU
65
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 49.982 ms | 0 - 248 MB | NPU
66
- | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.406 ms | 4 - 216 MB | NPU
67
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 46.076 ms | 5 - 15 MB | NPU
68
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8750 | 17.151 ms | 5 - 219 MB | NPU
69
- | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS7181 | 29.182 ms | 5 - 5 MB | NPU
70
- | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 21.128 ms | 34 - 379 MB | NPU
71
- | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 62.578 ms | 0 - 391 MB | NPU
72
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8275 | 177.45 ms | 5 - 237 MB | NPU
73
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 27.334 ms | 0 - 140 MB | NPU
74
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8775P | 1634.277 ms | 50 - 61 MB | CPU
75
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8650P | 1634.277 ms | 50 - 61 MB | CPU
76
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8255P | 1634.277 ms | 50 - 61 MB | CPU
77
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 62.578 ms | 0 - 391 MB | NPU
78
- | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 16.323 ms | 4 - 246 MB | NPU
79
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA7255P | 177.45 ms | 5 - 237 MB | NPU
80
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8295P | 48.524 ms | 5 - 277 MB | NPU
81
- | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.924 ms | 3 - 245 MB | NPU
82
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 44.982 ms | 4 - 106 MB | NPU
83
- | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8750 | 16.323 ms | 4 - 246 MB | NPU
84
- | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.277 ms | 1 - 306 MB | NPU
85
- | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 12.967 ms | 1 - 305 MB | NPU
86
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS6490 | 34.017 ms | 1 - 51 MB | NPU
87
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8275 | 27.001 ms | 1 - 229 MB | NPU
88
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 8.098 ms | 1 - 31 MB | NPU
89
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 482.445 ms | 13 - 25 MB | CPU
90
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 482.445 ms | 13 - 25 MB | CPU
91
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 482.445 ms | 13 - 25 MB | CPU
92
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 12.967 ms | 1 - 305 MB | NPU
93
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 27.001 ms | 1 - 229 MB | NPU
94
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCM6690 | 163.707 ms | 1 - 249 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 14.517 ms | 1 - 233 MB | NPU
96
- | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.443 ms | 1 - 244 MB | NPU
97
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS9075 | 9.095 ms | 0 - 49 MB | NPU
98
- | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 13.691 ms | 0 - 228 MB | NPU
99
- | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 5.001 ms | 1 - 232 MB | NPU
100
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS7790 | 13.691 ms | 0 - 228 MB | NPU
101
- | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8750 | 5.001 ms | 1 - 232 MB | NPU
102
 
103
  ## License
104
  * The license for the original implementation of YOLOE-Segmentation can be found
 
15
  Ultralytics YOLOE 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 YOLOE-Segmentation found [here](https://github.com/THU-MIG/yoloe).
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/v0.58.0/src/qai_hub_models/models/yoloe_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/v0.58.0/src/qai_hub_models/models/yoloe_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 [YOLOE-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/yoloe_seg) for usage instructions.
30
 
31
 
32
  ## Model Details
 
42
  ## Performance Summary
43
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
44
  |---|---|---|---|---|---|---
45
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® X2 Elite | 15.638 ms | 17 - 17 MB | NPU
46
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® X Elite | 31.106 ms | 89 - 89 MB | NPU
47
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 24.024 ms | 1 - 282 MB | NPU
48
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 66.903 ms | 17 - 347 MB | NPU
49
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.457 ms | 0 - 95 MB | NPU
50
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® QCS8450 | 66.903 ms | 17 - 347 MB | NPU
51
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 12.329 ms | 12 - 246 MB | NPU
52
+ | YOLOE-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 18.25 ms | 12 - 232 MB | NPU
53
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 47.273 ms | 13 - 20 MB | NPU
54
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 18.25 ms | 12 - 232 MB | NPU
55
+ | YOLOE-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 31.106 ms | 89 - 89 MB | NPU
56
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 15.537 ms | 5 - 5 MB | NPU
57
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 29.366 ms | 5 - 5 MB | NPU
58
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 21.668 ms | 2 - 263 MB | NPU
59
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 63.071 ms | 5 - 316 MB | NPU
60
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 | 178.804 ms | 1 - 209 MB | NPU
61
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 28.3 ms | 5 - 6 MB | NPU
62
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 44.216 ms | 1 - 209 MB | NPU
63
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 44.216 ms | 1 - 209 MB | NPU
64
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 44.216 ms | 1 - 209 MB | NPU
65
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 63.071 ms | 5 - 316 MB | NPU
66
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.679 ms | 5 - 217 MB | NPU
67
+ | YOLOE-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 17.079 ms | 0 - 215 MB | NPU
68
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 44.466 ms | 7 - 17 MB | NPU
69
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 178.804 ms | 1 - 209 MB | NPU
70
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 49.981 ms | 0 - 248 MB | NPU
71
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 17.079 ms | 0 - 215 MB | NPU
72
+ | YOLOE-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 29.366 ms | 5 - 5 MB | NPU
73
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 9.532 ms | 2 - 2 MB | NPU
74
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® X Elite | 20.163 ms | 2 - 2 MB | NPU
75
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 13.441 ms | 2 - 393 MB | NPU
76
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 33.315 ms | 2 - 391 MB | NPU
77
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 116.745 ms | 1 - 8 MB | NPU
78
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 54.043 ms | 1 - 301 MB | NPU
79
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.162 ms | 2 - 329 MB | NPU
80
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8775P | 18.561 ms | 1 - 303 MB | NPU
81
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8650P | 18.561 ms | 1 - 303 MB | NPU
82
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8255P | 18.561 ms | 1 - 303 MB | NPU
83
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 33.315 ms | 2 - 391 MB | NPU
84
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 10.587 ms | 2 - 309 MB | NPU
85
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 18.709 ms | 1 - 7 MB | NPU
86
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA7255P | 54.043 ms | 1 - 301 MB | NPU
87
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® SA8295P | 29.262 ms | 0 - 303 MB | NPU
88
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 31.537 ms | 2 - 320 MB | NPU
89
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 7.448 ms | 2 - 316 MB | NPU
90
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 353.374 ms | 3 - 366 MB | NPU
91
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 31.537 ms | 2 - 320 MB | NPU
92
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 10.587 ms | 2 - 309 MB | NPU
93
+ | YOLOE-Segmentation | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.163 ms | 2 - 2 MB | NPU
94
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 4.3 ms | 1 - 1 MB | NPU
95
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® X Elite | 9.521 ms | 1 - 1 MB | NPU
96
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.104 ms | 1 - 299 MB | NPU
97
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.722 ms | 1 - 298 MB | NPU
98
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 45.382 ms | 1 - 5 MB | NPU
99
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 26.973 ms | 1 - 226 MB | NPU
100
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.886 ms | 1 - 4 MB | NPU
101
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8775P | 8.341 ms | 1 - 228 MB | NPU
102
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8650P | 8.341 ms | 1 - 228 MB | NPU
103
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8255P | 8.341 ms | 1 - 228 MB | NPU
104
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 13.722 ms | 1 - 298 MB | NPU
105
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.332 ms | 1 - 233 MB | NPU
106
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 8.057 ms | 3 - 7 MB | NPU
107
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA7255P | 26.973 ms | 1 - 226 MB | NPU
108
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® SA8295P | 14.564 ms | 0 - 228 MB | NPU
109
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.411 ms | 1 - 228 MB | NPU
110
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 151.534 ms | 1 - 244 MB | NPU
111
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 4.94 ms | 1 - 222 MB | NPU
112
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 14.332 ms | 1 - 233 MB | NPU
113
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 4.94 ms | 1 - 222 MB | NPU
114
+ | YOLOE-Segmentation | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 9.521 ms | 1 - 1 MB | NPU
115
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 21.242 ms | 0 - 346 MB | NPU
116
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 61.851 ms | 5 - 395 MB | NPU
117
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8275 | 177.474 ms | 5 - 237 MB | NPU
118
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 27.608 ms | 4 - 8 MB | NPU
119
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8775P | 43.427 ms | 4 - 236 MB | NPU
120
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8650P | 43.427 ms | 4 - 236 MB | NPU
121
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8255P | 43.427 ms | 4 - 236 MB | NPU
122
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 61.851 ms | 5 - 395 MB | NPU
123
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.244 ms | 4 - 245 MB | NPU
124
+ | YOLOE-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 16.38 ms | 3 - 244 MB | NPU
125
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 43.441 ms | 4 - 106 MB | NPU
126
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA7255P | 177.474 ms | 5 - 237 MB | NPU
127
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® SA8295P | 48.552 ms | 5 - 277 MB | NPU
128
+ | YOLOE-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 16.38 ms | 3 - 244 MB | NPU
129
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.276 ms | 0 - 305 MB | NPU
130
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 12.532 ms | 1 - 305 MB | NPU
131
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 45.607 ms | 1 - 51 MB | NPU
132
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8275 | 615.581 ms | 13 - 24 MB | CPU
133
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 8.073 ms | 0 - 3 MB | NPU
134
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8775P | 8.24 ms | 1 - 230 MB | NPU
135
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8650P | 8.24 ms | 1 - 230 MB | NPU
136
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8255P | 8.24 ms | 1 - 230 MB | NPU
137
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® QCS8450 | 12.532 ms | 1 - 305 MB | NPU
138
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 13.678 ms | 1 - 229 MB | NPU
139
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 7.93 ms | 0 - 50 MB | NPU
140
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA7255P | 615.581 ms | 13 - 24 MB | CPU
141
  | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® SA8295P | 14.517 ms | 1 - 233 MB | NPU
142
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.477 ms | 0 - 239 MB | NPU
143
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 155.791 ms | 1 - 248 MB | NPU
144
+ | YOLOE-Segmentation | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 4.983 ms | 1 - 230 MB | NPU
145
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 13.678 ms | 1 - 229 MB | NPU
146
+ | YOLOE-Segmentation | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 4.983 ms | 1 - 230 MB | NPU
 
147
 
148
  ## License
149
  * The license for the original implementation of YOLOE-Segmentation can be found