Hugging Face's logo

qualcomm
/
HRNetFace

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
f80dc96
·
verified ·
1 Parent(s): b8b6554

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +74 -74
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: object-detection
15
  Detects attributes (liveness, eye closeness, mask presence, glasses presence, sunglasses presence) that apply to a given face.
16
 
17
  This is based on the implementation of HRNetFace found [here](https://github.com/HRNet/HRNet-Facial-Landmark-Detection).
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/hrnet_face) 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
 
@@ -28,26 +28,26 @@ 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/hrnet_face/releases/v0.48.0/hrnet_face-onnx-float.zip)
32
- | 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/hrnet_face/releases/v0.48.0/hrnet_face-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.48.0/hrnet_face-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.48.0/hrnet_face-qnn_dlc-w8a8.zip)
35
- | 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/hrnet_face/releases/v0.48.0/hrnet_face-tflite-float.zip)
36
- | 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/hrnet_face/releases/v0.48.0/hrnet_face-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[HRNetFace on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_face)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/hrnet_face) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
- See our repository for [HRNetFace on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/hrnet_face) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,73 +63,73 @@ See our repository for [HRNetFace on GitHub](https://github.com/qualcomm/ai-hub-
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | HRNetFace | ONNX | float | Snapdragon® X2 Elite | 1.54 ms | 31 - 31 MB | NPU
67
- | HRNetFace | ONNX | float | Snapdragon® X Elite | 3.34 ms | 30 - 30 MB | NPU
68
- | HRNetFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.156 ms | 0 - 156 MB | NPU
69
- | HRNetFace | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.97 ms | 0 - 34 MB | NPU
70
- | HRNetFace | ONNX | float | Qualcomm® QCS9075 | 4.741 ms | 2 - 4 MB | NPU
71
- | HRNetFace | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.653 ms | 0 - 98 MB | NPU
72
- | HRNetFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.328 ms | 1 - 98 MB | NPU
73
- | HRNetFace | ONNX | w8a8 | Snapdragon® X2 Elite | 0.654 ms | 15 - 15 MB | NPU
74
- | HRNetFace | ONNX | w8a8 | Snapdragon® X Elite | 1.542 ms | 15 - 15 MB | NPU
75
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.899 ms | 0 - 153 MB | NPU
76
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS6490 | 97.024 ms | 18 - 36 MB | CPU
77
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.298 ms | 0 - 21 MB | NPU
78
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS9075 | 1.523 ms | 0 - 3 MB | NPU
79
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCM6690 | 49.948 ms | 21 - 40 MB | CPU
80
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.702 ms | 0 - 103 MB | NPU
81
- | HRNetFace | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 46.986 ms | 18 - 37 MB | CPU
82
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.587 ms | 0 - 104 MB | NPU
83
- | HRNetFace | QNN_DLC | float | Snapdragon® X2 Elite | 1.932 ms | 1 - 1 MB | NPU
84
- | HRNetFace | QNN_DLC | float | Snapdragon® X Elite | 3.721 ms | 1 - 1 MB | NPU
85
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.339 ms | 0 - 123 MB | NPU
86
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 15.449 ms | 1 - 77 MB | NPU
87
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.319 ms | 1 - 2 MB | NPU
88
- | HRNetFace | QNN_DLC | float | Qualcomm® SA8775P | 5.1 ms | 1 - 80 MB | NPU
89
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS9075 | 5.029 ms | 1 - 4 MB | NPU
90
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.434 ms | 0 - 107 MB | NPU
91
- | HRNetFace | QNN_DLC | float | Qualcomm® SA7255P | 15.449 ms | 1 - 77 MB | NPU
92
- | HRNetFace | QNN_DLC | float | Qualcomm® SA8295P | 5.593 ms | 1 - 62 MB | NPU
93
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.758 ms | 0 - 80 MB | NPU
94
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.369 ms | 1 - 83 MB | NPU
95
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.849 ms | 0 - 0 MB | NPU
96
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.563 ms | 0 - 0 MB | NPU
97
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.906 ms | 0 - 110 MB | NPU
98
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.77 ms | 0 - 2 MB | NPU
99
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 3.252 ms | 0 - 70 MB | NPU
100
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.35 ms | 0 - 115 MB | NPU
 
101
  | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.702 ms | 0 - 72 MB | NPU
102
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.616 ms | 0 - 2 MB | NPU
103
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 10.476 ms | 0 - 197 MB | NPU
104
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.78 ms | 0 - 106 MB | NPU
105
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.252 ms | 0 - 70 MB | NPU
106
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.21 ms | 0 - 68 MB | NPU
107
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.659 ms | 0 - 72 MB | NPU
108
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.619 ms | 0 - 78 MB | NPU
109
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.541 ms | 0 - 72 MB | NPU
110
- | HRNetFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.321 ms | 0 - 144 MB | NPU
111
- | HRNetFace | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 15.414 ms | 0 - 93 MB | NPU
112
- | HRNetFace | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.333 ms | 0 - 2 MB | NPU
113
- | HRNetFace | TFLITE | float | Qualcomm® SA8775P | 5.168 ms | 0 - 94 MB | NPU
114
- | HRNetFace | TFLITE | float | Qualcomm® QCS9075 | 5.041 ms | 0 - 35 MB | NPU
115
- | HRNetFace | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.433 ms | 1 - 129 MB | NPU
116
- | HRNetFace | TFLITE | float | Qualcomm® SA7255P | 15.414 ms | 0 - 93 MB | NPU
117
- | HRNetFace | TFLITE | float | Qualcomm® SA8295P | 5.659 ms | 1 - 75 MB | NPU
118
  | HRNetFace | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.757 ms | 0 - 89 MB | NPU
119
- | HRNetFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.381 ms | 0 - 99 MB | NPU
120
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.736 ms | 0 - 113 MB | NPU
121
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS6490 | 3.343 ms | 0 - 18 MB | NPU
122
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.895 ms | 0 - 71 MB | NPU
123
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.109 ms | 0 - 3 MB | NPU
124
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8775P | 5.606 ms | 0 - 70 MB | NPU
125
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.326 ms | 0 - 18 MB | NPU
126
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCM6690 | 9.802 ms | 0 - 198 MB | NPU
127
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.596 ms | 0 - 111 MB | NPU
128
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA7255P | 2.895 ms | 0 - 71 MB | NPU
129
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8295P | 1.949 ms | 0 - 68 MB | NPU
130
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.583 ms | 0 - 72 MB | NPU
131
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.354 ms | 0 - 75 MB | NPU
132
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.465 ms | 0 - 74 MB | NPU
133
 
134
  ## License
135
  * The license for the original implementation of HRNetFace can be found
 
15
  Detects attributes (liveness, eye closeness, mask presence, glasses presence, sunglasses presence) that apply to a given face.
16
 
17
  This is based on the implementation of HRNetFace found [here](https://github.com/HRNet/HRNet-Facial-Landmark-Detection).
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/tree/v0.49.1/qai_hub_models/models/hrnet_face) 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/hrnet_face/releases/v0.49.1/hrnet_face-onnx-float.zip)
32
+ | 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/hrnet_face/releases/v0.49.1/hrnet_face-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.49.1/hrnet_face-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.49.1/hrnet_face-qnn_dlc-w8a8.zip)
35
+ | 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/hrnet_face/releases/v0.49.1/hrnet_face-tflite-float.zip)
36
+ | 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/hrnet_face/releases/v0.49.1/hrnet_face-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[HRNetFace on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/hrnet_face)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/hrnet_face) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
+ See our repository for [HRNetFace on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/hrnet_face) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | HRNetFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.327 ms | 1 - 98 MB | NPU
67
+ | HRNetFace | ONNX | float | Snapdragon® X2 Elite | 1.532 ms | 31 - 31 MB | NPU
68
+ | HRNetFace | ONNX | float | Snapdragon® X Elite | 3.313 ms | 30 - 30 MB | NPU
69
+ | HRNetFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.157 ms | 0 - 155 MB | NPU
70
+ | HRNetFace | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.978 ms | 0 - 33 MB | NPU
71
+ | HRNetFace | ONNX | float | Qualcomm® QCS9075 | 4.752 ms | 2 - 4 MB | NPU
72
+ | HRNetFace | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.65 ms | 0 - 95 MB | NPU
73
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.585 ms | 0 - 105 MB | NPU
74
+ | HRNetFace | ONNX | w8a8 | Snapdragon® X2 Elite | 1.427 ms | 15 - 15 MB | NPU
75
+ | HRNetFace | ONNX | w8a8 | Snapdragon® X Elite | 1.547 ms | 15 - 15 MB | NPU
76
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.887 ms | 0 - 154 MB | NPU
77
+ | HRNetFace | ONNX | w8a8 | Qualcomm® QCS6490 | 91.751 ms | 18 - 37 MB | CPU
78
+ | HRNetFace | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.3 ms | 0 - 21 MB | NPU
79
+ | HRNetFace | ONNX | w8a8 | Qualcomm® QCS9075 | 1.544 ms | 0 - 3 MB | NPU
80
+ | HRNetFace | ONNX | w8a8 | Qualcomm® QCM6690 | 49.856 ms | 18 - 37 MB | CPU
81
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.696 ms | 0 - 95 MB | NPU
82
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 46.773 ms | 18 - 36 MB | CPU
83
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.37 ms | 1 - 83 MB | NPU
84
+ | HRNetFace | QNN_DLC | float | Snapdragon® X2 Elite | 1.955 ms | 1 - 1 MB | NPU
85
+ | HRNetFace | QNN_DLC | float | Snapdragon® X Elite | 3.71 ms | 1 - 1 MB | NPU
86
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.318 ms | 0 - 125 MB | NPU
87
+ | HRNetFace | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 15.446 ms | 1 - 77 MB | NPU
88
+ | HRNetFace | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.326 ms | 1 - 147 MB | NPU
89
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA8775P | 5.117 ms | 1 - 80 MB | NPU
90
+ | HRNetFace | QNN_DLC | float | Qualcomm® QCS9075 | 5.028 ms | 1 - 4 MB | NPU
91
+ | HRNetFace | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.415 ms | 0 - 109 MB | NPU
92
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA7255P | 15.446 ms | 1 - 77 MB | NPU
93
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA8295P | 5.619 ms | 1 - 62 MB | NPU
94
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.748 ms | 0 - 79 MB | NPU
95
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.528 ms | 0 - 72 MB | NPU
96
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.856 ms | 0 - 0 MB | NPU
97
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.556 ms | 0 - 0 MB | NPU
98
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.918 ms | 0 - 108 MB | NPU
99
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.643 ms | 0 - 2 MB | NPU
100
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 3.238 ms | 0 - 70 MB | NPU
101
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.329 ms | 0 - 2 MB | NPU
102
  | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.702 ms | 0 - 72 MB | NPU
103
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.615 ms | 0 - 2 MB | NPU
104
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 10.463 ms | 0 - 197 MB | NPU
105
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.782 ms | 0 - 107 MB | NPU
106
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.238 ms | 0 - 70 MB | NPU
107
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.208 ms | 0 - 68 MB | NPU
108
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.673 ms | 0 - 71 MB | NPU
109
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.643 ms | 0 - 78 MB | NPU
110
+ | HRNetFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.383 ms | 0 - 100 MB | NPU
111
+ | HRNetFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.345 ms | 0 - 143 MB | NPU
112
+ | HRNetFace | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 15.416 ms | 0 - 93 MB | NPU
113
+ | HRNetFace | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.375 ms | 0 - 2 MB | NPU
114
+ | HRNetFace | TFLITE | float | Qualcomm® SA8775P | 5.162 ms | 0 - 96 MB | NPU
115
+ | HRNetFace | TFLITE | float | Qualcomm® QCS9075 | 5.038 ms | 0 - 35 MB | NPU
116
+ | HRNetFace | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.44 ms | 0 - 129 MB | NPU
117
+ | HRNetFace | TFLITE | float | Qualcomm® SA7255P | 15.416 ms | 0 - 93 MB | NPU
118
+ | HRNetFace | TFLITE | float | Qualcomm® SA8295P | 5.652 ms | 0 - 76 MB | NPU
119
  | HRNetFace | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.757 ms | 0 - 89 MB | NPU
120
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.466 ms | 0 - 73 MB | NPU
121
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.75 ms | 0 - 117 MB | NPU
122
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS6490 | 3.319 ms | 0 - 18 MB | NPU
123
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 2.906 ms | 0 - 70 MB | NPU
124
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.097 ms | 0 - 3 MB | NPU
125
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8775P | 1.488 ms | 0 - 73 MB | NPU
126
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.325 ms | 0 - 18 MB | NPU
127
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCM6690 | 9.776 ms | 0 - 197 MB | NPU
128
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 1.49 ms | 0 - 110 MB | NPU
129
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA7255P | 2.906 ms | 0 - 70 MB | NPU
130
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8295P | 1.961 ms | 0 - 68 MB | NPU
131
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.581 ms | 0 - 71 MB | NPU
132
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.362 ms | 0 - 75 MB | NPU
 
133
 
134
  ## License
135
  * The license for the original implementation of HRNetFace can be found