Hugging Face's logo

qualcomm
/
Yolo-X

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
697e65f
·
verified ·
1 Parent(s): 1cdedbc

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +87 -86
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: object-detection
15
  YoloX is a machine learning model that predicts bounding boxes and classes of objects in an image.
16
 
17
  This is based on the implementation of Yolo-X found [here](https://github.com/Megvii-BaseDetection/YOLOX/).
18
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/yolox) 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
 
@@ -28,30 +28,30 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-onnx-w8a16.zip)
33
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-onnx-w8a8.zip)
34
- | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-onnx-w8a8_mixed_int16.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-qnn_dlc-w8a16.zip)
37
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-qnn_dlc-w8a8.zip)
38
- | QNN_DLC | w8a8_mixed_int16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-qnn_dlc-w8a8_mixed_int16.zip)
39
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-tflite-float.zip)
40
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.47.0/yolox-tflite-w8a8.zip)
41
 
42
  For more device-specific assets and performance metrics, visit **[Yolo-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/yolox)**.
43
 
44
 
45
  ### Option 2: Export with Custom Configurations
46
 
47
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/yolox) Python library to compile and export the model with your own:
48
  - Custom weights (e.g., fine-tuned checkpoints)
49
  - Custom input shapes
50
  - Target device and runtime configurations
51
 
52
  This option is ideal if you need to customize the model beyond the default configuration provided here.
53
 
54
- See our repository for [Yolo-X on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/yolox) for usage instructions.
55
 
56
  ## Model Details
57
 
@@ -68,79 +68,80 @@ See our repository for [Yolo-X on GitHub](https://github.com/quic/ai-hub-models/
68
  ## Performance Summary
69
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
70
  |---|---|---|---|---|---|---
71
- | Yolo-X | ONNX | float | Snapdragon® X Elite | 13.178 ms | 14 - 14 MB | NPU
72
- | Yolo-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.841 ms | 0 - 187 MB | NPU
73
- | Yolo-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 13.149 ms | 0 - 17 MB | NPU
74
- | Yolo-X | ONNX | float | Qualcomm® QCS9075 | 16.154 ms | 5 - 7 MB | NPU
75
- | Yolo-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.37 ms | 3 - 164 MB | NPU
76
- | Yolo-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.87 ms | 5 - 166 MB | NPU
77
- | Yolo-X | ONNX | float | Snapdragon® X2 Elite | 8.62 ms | 14 - 14 MB | NPU
78
- | Yolo-X | ONNX | w8a16 | Snapdragon® X Elite | 14.5 ms | 7 - 7 MB | NPU
79
- | Yolo-X | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 9.752 ms | 3 - 241 MB | NPU
80
- | Yolo-X | ONNX | w8a16 | Qualcomm® QCS6490 | 811.041 ms | 113 - 116 MB | CPU
81
- | Yolo-X | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 13.537 ms | 0 - 12 MB | NPU
82
- | Yolo-X | ONNX | w8a16 | Qualcomm® QCS9075 | 14.368 ms | 2 - 5 MB | NPU
83
- | Yolo-X | ONNX | w8a16 | Qualcomm® QCM6690 | 423.273 ms | 99 - 109 MB | CPU
84
- | Yolo-X | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 8.728 ms | 0 - 205 MB | NPU
85
- | Yolo-X | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 396.04 ms | 112 - 122 MB | CPU
86
- | Yolo-X | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 10.751 ms | 3 - 210 MB | NPU
87
- | Yolo-X | ONNX | w8a16 | Snapdragon® X2 Elite | 11.183 ms | 8 - 8 MB | NPU
88
- | Yolo-X | ONNX | w8a8 | Snapdragon® X Elite | 9.065 ms | 8 - 8 MB | NPU
89
- | Yolo-X | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.108 ms | 1 - 90 MB | NPU
90
- | Yolo-X | ONNX | w8a8 | Qualcomm® QCS6490 | 107.7 ms | 48 - 57 MB | CPU
91
- | Yolo-X | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 8.228 ms | 0 - 114 MB | NPU
92
- | Yolo-X | ONNX | w8a8 | Qualcomm® QCS9075 | 8.775 ms | 1 - 4 MB | NPU
93
- | Yolo-X | ONNX | w8a8 | Qualcomm® QCM6690 | 97.744 ms | 38 - 49 MB | CPU
94
- | Yolo-X | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.753 ms | 1 - 60 MB | NPU
95
- | Yolo-X | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 93.66 ms | 49 - 60 MB | CPU
96
- | Yolo-X | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 8.013 ms | 1 - 59 MB | NPU
97
- | Yolo-X | ONNX | w8a8 | Snapdragon® X2 Elite | 8.163 ms | 8 - 8 MB | NPU
98
- | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® X Elite | 50.347 ms | 34 - 34 MB | NPU
99
- | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 36.391 ms | 25 - 1233 MB | NPU
100
- | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCS6490 | 324.708 ms | 105 - 112 MB | CPU
101
- | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 50.982 ms | 22 - 26 MB | NPU
102
- | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCM6690 | 206.948 ms | 96 - 107 MB | CPU
103
- | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 31.855 ms | 27 - 865 MB | NPU
104
- | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 193.83 ms | 105 - 116 MB | CPU
105
- | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 32.263 ms | 24 - 1155 MB | NPU
106
- | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® X2 Elite | 37.979 ms | 34 - 34 MB | NPU
107
- | Yolo-X | QNN_DLC | float | Snapdragon® X Elite | 6.068 ms | 5 - 5 MB | NPU
108
- | Yolo-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.261 ms | 5 - 181 MB | NPU
109
- | Yolo-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 27.629 ms | 0 - 154 MB | NPU
110
- | Yolo-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 5.638 ms | 5 - 99 MB | NPU
111
- | Yolo-X | QNN_DLC | float | Qualcomm® SA8775P | 8.432 ms | 0 - 158 MB | NPU
112
- | Yolo-X | QNN_DLC | float | Qualcomm® QCS9075 | 8.755 ms | 7 - 13 MB | NPU
113
- | Yolo-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 14.877 ms | 3 - 209 MB | NPU
114
- | Yolo-X | QNN_DLC | float | Qualcomm® SA7255P | 27.629 ms | 0 - 154 MB | NPU
115
- | Yolo-X | QNN_DLC | float | Qualcomm® SA8295P | 11.454 ms | 0 - 175 MB | NPU
116
- | Yolo-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.157 ms | 0 - 159 MB | NPU
117
- | Yolo-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.382 ms | 5 - 164 MB | NPU
118
- | Yolo-X | QNN_DLC | float | Snapdragon® X2 Elite | 3.421 ms | 5 - 5 MB | NPU
119
- | Yolo-X | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.498 ms | 2 - 2 MB | NPU
120
- | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.282 ms | 2 - 104 MB | NPU
121
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 14.529 ms | 3 - 7 MB | NPU
122
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 10.828 ms | 1 - 72 MB | NPU
123
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.007 ms | 2 - 15 MB | NPU
124
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.559 ms | 1 - 73 MB | NPU
125
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 5.428 ms | 1 - 5 MB | NPU
126
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 45.8 ms | 3 - 198 MB | NPU
127
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 6.493 ms | 2 - 111 MB | NPU
128
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® SA7255P | 10.828 ms | 1 - 72 MB | NPU
129
- | Yolo-X | QNN_DLC | w8a16 | Qualcomm® SA8295P | 6.993 ms | 0 - 70 MB | NPU
130
- | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.345 ms | 2 - 82 MB | NPU
131
- | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.046 ms | 2 - 189 MB | NPU
132
- | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.805 ms | 2 - 82 MB | NPU
133
- | Yolo-X | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.955 ms | 2 - 2 MB | NPU
134
- | Yolo-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.264 ms | 0 - 201 MB | NPU
135
- | Yolo-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 27.644 ms | 0 - 166 MB | NPU
136
- | Yolo-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5.632 ms | 0 - 3 MB | NPU
137
- | Yolo-X | TFLITE | float | Qualcomm® SA8775P | 8.467 ms | 0 - 171 MB | NPU
138
- | Yolo-X | TFLITE | float | Qualcomm® QCS9075 | 8.733 ms | 0 - 26 MB | NPU
139
- | Yolo-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 14.881 ms | 0 - 220 MB | NPU
140
- | Yolo-X | TFLITE | float | Qualcomm® SA7255P | 27.644 ms | 0 - 166 MB | NPU
141
- | Yolo-X | TFLITE | float | Qualcomm® SA8295P | 11.496 ms | 0 - 188 MB | NPU
142
- | Yolo-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.21 ms | 0 - 168 MB | NPU
143
- | Yolo-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.379 ms | 0 - 174 MB | NPU
 
144
 
145
  ## License
146
  * The license for the original implementation of Yolo-X can be found
 
15
  YoloX is a machine learning model that predicts bounding boxes and classes of objects in an image.
16
 
17
  This is based on the implementation of Yolo-X found [here](https://github.com/Megvii-BaseDetection/YOLOX/).
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/main/qai_hub_models/models/yolox) 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
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-onnx-w8a16.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-onnx-w8a8.zip)
34
+ | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-onnx-w8a8_mixed_int16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-qnn_dlc-w8a16.zip)
37
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-qnn_dlc-w8a8.zip)
38
+ | QNN_DLC | w8a8_mixed_int16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-qnn_dlc-w8a8_mixed_int16.zip)
39
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-tflite-float.zip)
40
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolox/releases/v0.48.0/yolox-tflite-w8a8.zip)
41
 
42
  For more device-specific assets and performance metrics, visit **[Yolo-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/yolox)**.
43
 
44
 
45
  ### Option 2: Export with Custom Configurations
46
 
47
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/yolox) Python library to compile and export the model with your own:
48
  - Custom weights (e.g., fine-tuned checkpoints)
49
  - Custom input shapes
50
  - Target device and runtime configurations
51
 
52
  This option is ideal if you need to customize the model beyond the default configuration provided here.
53
 
54
+ See our repository for [Yolo-X on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/yolox) for usage instructions.
55
 
56
  ## Model Details
57
 
 
68
  ## Performance Summary
69
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
70
  |---|---|---|---|---|---|---
71
+ | Yolo-X | ONNX | float | Snapdragon® X2 Elite | 7.287 ms | 14 - 14 MB | NPU
72
+ | Yolo-X | ONNX | float | Snapdragon® X Elite | 13.258 ms | 14 - 14 MB | NPU
73
+ | Yolo-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 8.853 ms | 3 - 184 MB | NPU
74
+ | Yolo-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 13.016 ms | 0 - 163 MB | NPU
75
+ | Yolo-X | ONNX | float | Qualcomm® QCS9075 | 16.339 ms | 5 - 7 MB | NPU
76
+ | Yolo-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.364 ms | 1 - 159 MB | NPU
77
+ | Yolo-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.855 ms | 5 - 167 MB | NPU
78
+ | Yolo-X | ONNX | w8a16 | Snapdragon® X2 Elite | 11.103 ms | 8 - 8 MB | NPU
79
+ | Yolo-X | ONNX | w8a16 | Snapdragon® X Elite | 14.481 ms | 7 - 7 MB | NPU
80
+ | Yolo-X | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 9.641 ms | 3 - 241 MB | NPU
81
+ | Yolo-X | ONNX | w8a16 | Qualcomm® QCS6490 | 806.18 ms | 113 - 116 MB | CPU
82
+ | Yolo-X | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 13.59 ms | 0 - 11 MB | NPU
83
+ | Yolo-X | ONNX | w8a16 | Qualcomm® QCS9075 | 14.485 ms | 2 - 5 MB | NPU
84
+ | Yolo-X | ONNX | w8a16 | Qualcomm® QCM6690 | 420.958 ms | 102 - 112 MB | CPU
85
+ | Yolo-X | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 8.626 ms | 0 - 199 MB | NPU
86
+ | Yolo-X | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 395.379 ms | 113 - 122 MB | CPU
87
+ | Yolo-X | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 10.743 ms | 3 - 205 MB | NPU
88
+ | Yolo-X | ONNX | w8a8 | Snapdragon® X2 Elite | 8.15 ms | 8 - 8 MB | NPU
89
+ | Yolo-X | ONNX | w8a8 | Snapdragon® X Elite | 9.074 ms | 8 - 8 MB | NPU
90
+ | Yolo-X | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.155 ms | 1 - 93 MB | NPU
91
+ | Yolo-X | ONNX | w8a8 | Qualcomm® QCS6490 | 108.293 ms | 47 - 57 MB | CPU
92
+ | Yolo-X | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 8.226 ms | 1 - 39 MB | NPU
93
+ | Yolo-X | ONNX | w8a8 | Qualcomm® QCS9075 | 8.781 ms | 1 - 4 MB | NPU
94
+ | Yolo-X | ONNX | w8a8 | Qualcomm® QCM6690 | 97.766 ms | 40 - 50 MB | CPU
95
+ | Yolo-X | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.746 ms | 1 - 61 MB | NPU
96
+ | Yolo-X | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 94.911 ms | 49 - 59 MB | CPU
97
+ | Yolo-X | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 8.098 ms | 1 - 59 MB | NPU
98
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® X2 Elite | 25.949 ms | 19 - 19 MB | NPU
99
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® X Elite | 34.067 ms | 16 - 16 MB | NPU
100
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 25.444 ms | 11 - 855 MB | NPU
101
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCS6490 | 338.044 ms | 103 - 112 MB | CPU
102
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 35.676 ms | 4 - 29 MB | NPU
103
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCS9075 | 35.572 ms | 11 - 14 MB | NPU
104
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Qualcomm® QCM6690 | 206.229 ms | 104 - 114 MB | CPU
105
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 21.917 ms | 12 - 721 MB | NPU
106
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 192.904 ms | 106 - 117 MB | CPU
107
+ | Yolo-X | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 24.449 ms | 10 - 685 MB | NPU
108
+ | Yolo-X | QNN_DLC | float | Snapdragon® X2 Elite | 3.495 ms | 5 - 5 MB | NPU
109
+ | Yolo-X | QNN_DLC | float | Snapdragon® X Elite | 6.05 ms | 5 - 5 MB | NPU
110
+ | Yolo-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.26 ms | 5 - 183 MB | NPU
111
+ | Yolo-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 27.639 ms | 1 - 154 MB | NPU
112
+ | Yolo-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 5.571 ms | 5 - 112 MB | NPU
113
+ | Yolo-X | QNN_DLC | float | Qualcomm® SA8775P | 8.462 ms | 2 - 160 MB | NPU
114
+ | Yolo-X | QNN_DLC | float | Qualcomm® QCS9075 | 8.751 ms | 5 - 11 MB | NPU
115
+ | Yolo-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 14.86 ms | 5 - 211 MB | NPU
116
+ | Yolo-X | QNN_DLC | float | Qualcomm® SA7255P | 27.639 ms | 1 - 154 MB | NPU
117
+ | Yolo-X | QNN_DLC | float | Qualcomm® SA8295P | 11.498 ms | 0 - 175 MB | NPU
118
+ | Yolo-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.163 ms | 0 - 154 MB | NPU
119
+ | Yolo-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.381 ms | 5 - 164 MB | NPU
120
+ | Yolo-X | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.42 ms | 2 - 2 MB | NPU
121
+ | Yolo-X | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.533 ms | 2 - 2 MB | NPU
122
+ | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.281 ms | 2 - 109 MB | NPU
123
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 14.928 ms | 1 - 5 MB | NPU
124
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 10.865 ms | 0 - 69 MB | NPU
125
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 5.023 ms | 2 - 4 MB | NPU
126
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.555 ms | 1 - 72 MB | NPU
127
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 5.423 ms | 2 - 6 MB | NPU
128
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 45.995 ms | 2 - 197 MB | NPU
129
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 6.638 ms | 2 - 110 MB | NPU
130
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® SA7255P | 10.865 ms | 0 - 69 MB | NPU
131
+ | Yolo-X | QNN_DLC | w8a16 | Qualcomm® SA8295P | 7.073 ms | 0 - 70 MB | NPU
132
+ | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.37 ms | 2 - 82 MB | NPU
133
+ | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.951 ms | 2 - 188 MB | NPU
134
+ | Yolo-X | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.801 ms | 2 - 84 MB | NPU
135
+ | Yolo-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.25 ms | 0 - 200 MB | NPU
136
+ | Yolo-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 27.613 ms | 0 - 166 MB | NPU
137
+ | Yolo-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5.611 ms | 0 - 2 MB | NPU
138
+ | Yolo-X | TFLITE | float | Qualcomm® SA8775P | 8.476 ms | 0 - 170 MB | NPU
139
+ | Yolo-X | TFLITE | float | Qualcomm® QCS9075 | 8.732 ms | 0 - 26 MB | NPU
140
+ | Yolo-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 14.791 ms | 0 - 221 MB | NPU
141
+ | Yolo-X | TFLITE | float | Qualcomm® SA7255P | 27.613 ms | 0 - 166 MB | NPU
142
+ | Yolo-X | TFLITE | float | Qualcomm® SA8295P | 11.492 ms | 0 - 189 MB | NPU
143
+ | Yolo-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.207 ms | 0 - 171 MB | NPU
144
+ | Yolo-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.38 ms | 0 - 174 MB | NPU
145
 
146
  ## License
147
  * The license for the original implementation of Yolo-X can be found