Hugging Face's logo

qualcomm
/
HRNetFace

Object Detection
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
8ac3c5c
·
verified ·
1 Parent(s): 29e0462

v0.58.0

Browse files

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

Files changed (2) hide show
  1. README.md +105 -99
  2. release_assets.json +7 -7
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/v0.57.3/src/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-onnx-float.zip)
32
- | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-qnn_dlc-w8a8.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-tflite-float.zip)
36
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/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/v0.57.3/src/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/v0.57.3/src/qai_hub_models/models/hrnet_face) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,96 +63,102 @@ 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 | 1.543 ms | 212 - 212 MB | NPU
67
- | HRNetFace | ONNX | float | Snapdragon® X Elite | 3.146 ms | 149 - 149 MB | NPU
68
- | HRNetFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.157 ms | 1 - 136 MB | NPU
69
- | HRNetFace | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 4.53 ms | 1 - 121 MB | NPU
70
- | HRNetFace | ONNX | float | Qualcomm® QCS8550 (Proxy) | 3.036 ms | 0 - 4 MB | NPU
71
- | HRNetFace | ONNX | float | Qualcomm® QCS8450 | 4.53 ms | 1 - 121 MB | NPU
72
- | HRNetFace | ONNX | float | Snapdragon® 8 Elite Mobile | 1.652 ms | 0 - 92 MB | NPU
73
- | HRNetFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.331 ms | 1 - 88 MB | NPU
74
- | HRNetFace | ONNX | float | Qualcomm® QCS9075 | 4.766 ms | 2 - 47 MB | NPU
75
- | HRNetFace | ONNX | float | Qualcomm® QCS8750 | 1.652 ms | 0 - 92 MB | NPU
76
- | HRNetFace | ONNX | float | Qualcomm® QCS7181 | 3.146 ms | 149 - 149 MB | NPU
77
- | HRNetFace | ONNX | w8a8 | Snapdragon® X2 Elite | 0.665 ms | 213 - 213 MB | NPU
78
- | HRNetFace | ONNX | w8a8 | Snapdragon® X Elite | 1.329 ms | 149 - 149 MB | NPU
79
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.88 ms | 0 - 147 MB | NPU
80
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.734 ms | 0 - 147 MB | NPU
81
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS6490 | 3.526 ms | 0 - 45 MB | NPU
82
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.299 ms | 0 - 20 MB | NPU
83
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS8450 | 1.734 ms | 0 - 147 MB | NPU
84
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.591 ms | 0 - 106 MB | NPU
85
- | HRNetFace | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.598 ms | 0 - 111 MB | NPU
86
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCM6690 | 10.036 ms | 0 - 230 MB | NPU
87
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS9075 | 1.521 ms | 0 - 45 MB | NPU
88
- | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.7 ms | 0 - 109 MB | NPU
89
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS7790 | 1.598 ms | 0 - 111 MB | NPU
90
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS8750 | 0.7 ms | 0 - 109 MB | NPU
91
- | HRNetFace | ONNX | w8a8 | Qualcomm® QCS7181 | 1.329 ms | 149 - 149 MB | NPU
92
- | HRNetFace | QNN_DLC | float | Snapdragon® X2 Elite | 1.937 ms | 1 - 1 MB | NPU
93
- | HRNetFace | QNN_DLC | float | Snapdragon® X Elite | 3.733 ms | 1 - 1 MB | NPU
94
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.327 ms | 0 - 120 MB | NPU
95
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 5.509 ms | 0 - 103 MB | NPU
96
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8275 | 15.456 ms | 1 - 75 MB | NPU
97
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.279 ms | 1 - 3 MB | NPU
98
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8450 | 5.509 ms | 0 - 103 MB | NPU
99
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.752 ms | 1 - 80 MB | NPU
100
- | HRNetFace | QNN_DLC | float | Qualcomm® SA8295P | 5.66 ms | 1 - 62 MB | NPU
101
- | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.399 ms | 1 - 81 MB | NPU
102
- | HRNetFace | QNN_DLC | float | Qualcomm® SA7255P | 15.456 ms | 1 - 75 MB | NPU
103
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS9075 | 5.026 ms | 1 - 4 MB | NPU
104
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS8750 | 1.752 ms | 1 - 80 MB | NPU
105
- | HRNetFace | QNN_DLC | float | Qualcomm® QCS7181 | 3.733 ms | 1 - 1 MB | NPU
106
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.848 ms | 0 - 0 MB | NPU
107
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.539 ms | 0 - 0 MB | NPU
108
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.902 ms | 0 - 108 MB | NPU
109
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.849 ms | 0 - 108 MB | NPU
110
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 3.829 ms | 0 - 2 MB | NPU
111
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 3.272 ms | 0 - 71 MB | NPU
112
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.331 ms | 0 - 2 MB | NPU
113
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.849 ms | 0 - 108 MB | NPU
114
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.542 ms | 0 - 74 MB | NPU
115
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.613 ms | 0 - 79 MB | NPU
116
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 10.617 ms | 0 - 200 MB | NPU
117
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 1.611 ms | 2 - 4 MB | NPU
118
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.272 ms | 0 - 71 MB | NPU
119
- | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.676 ms | 0 - 69 MB | NPU
120
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.215 ms | 0 - 70 MB | NPU
121
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 1.613 ms | 0 - 79 MB | NPU
122
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 0.676 ms | 0 - 69 MB | NPU
123
- | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 1.539 ms | 0 - 0 MB | NPU
124
- | HRNetFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.339 ms | 0 - 139 MB | NPU
125
- | HRNetFace | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5.486 ms | 0 - 125 MB | NPU
126
- | HRNetFace | TFLITE | float | Qualcomm® QCS8275 | 15.477 ms | 1 - 91 MB | NPU
127
- | HRNetFace | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.351 ms | 0 - 3 MB | NPU
128
- | HRNetFace | TFLITE | float | Qualcomm® SA8775P | 38.193 ms | 1 - 43 MB | GPU
129
- | HRNetFace | TFLITE | float | Qualcomm® SA8650P | 38.193 ms | 1 - 43 MB | GPU
130
- | HRNetFace | TFLITE | float | Qualcomm® SA8255P | 38.193 ms | 1 - 43 MB | GPU
131
- | HRNetFace | TFLITE | float | Qualcomm® QCS8450 | 5.486 ms | 0 - 125 MB | NPU
132
- | HRNetFace | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.758 ms | 0 - 94 MB | NPU
133
- | HRNetFace | TFLITE | float | Qualcomm® SA8295P | 5.652 ms | 1 - 74 MB | NPU
134
- | HRNetFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.391 ms | 0 - 89 MB | NPU
135
- | HRNetFace | TFLITE | float | Qualcomm® SA7255P | 15.477 ms | 1 - 91 MB | NPU
136
- | HRNetFace | TFLITE | float | Qualcomm® QCS9075 | 5.044 ms | 0 - 35 MB | NPU
137
- | HRNetFace | TFLITE | float | Qualcomm® QCS8750 | 1.758 ms | 0 - 94 MB | NPU
138
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.737 ms | 0 - 112 MB | NPU
139
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.489 ms | 0 - 113 MB | NPU
140
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS6490 | 3.221 ms | 0 - 18 MB | NPU
141
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8275 | 2.893 ms | 0 - 71 MB | NPU
142
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.092 ms | 0 - 3 MB | NPU
143
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8775P | 39.03 ms | 2 - 48 MB | GPU
144
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8650P | 39.03 ms | 2 - 48 MB | GPU
145
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8255P | 39.03 ms | 2 - 48 MB | GPU
146
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.489 ms | 0 - 113 MB | NPU
147
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.461 ms | 0 - 72 MB | NPU
148
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.353 ms | 0 - 75 MB | NPU
149
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCM6690 | 9.849 ms | 0 - 193 MB | NPU
150
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS9075 | 1.323 ms | 0 - 18 MB | NPU
151
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA7255P | 2.893 ms | 0 - 71 MB | NPU
152
- | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.577 ms | 0 - 68 MB | NPU
153
- | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8295P | 2.005 ms | 0 - 69 MB | NPU
154
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS7790 | 1.353 ms | 0 - 75 MB | NPU
155
- | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8750 | 0.577 ms | 0 - 68 MB | NPU
 
 
 
 
 
 
156
 
157
  ## License
158
  * 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/blob/v0.58.0/src/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-onnx-float.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-qnn_dlc-w8a8.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/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/v0.58.0/src/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/v0.58.0/src/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® X2 Elite | 1.55 ms | 2 - 2 MB | NPU
67
+ | HRNetFace | ONNX | float | Snapdragon® X Elite | 3.124 ms | 30 - 30 MB | NPU
68
+ | HRNetFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.149 ms | 0 - 147 MB | NPU
69
+ | HRNetFace | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 4.544 ms | 1 - 133 MB | NPU
70
+ | HRNetFace | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.992 ms | 0 - 34 MB | NPU
71
+ | HRNetFace | ONNX | float | Qualcomm® QCS8450 | 4.544 ms | 1 - 133 MB | NPU
72
+ | HRNetFace | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.615 ms | 2 - 4 MB | NPU
73
+ | HRNetFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.352 ms | 0 - 92 MB | NPU
74
+ | HRNetFace | ONNX | float | Snapdragon® 8 Elite Mobile | 1.649 ms | 0 - 92 MB | NPU
75
+ | HRNetFace | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.649 ms | 0 - 92 MB | NPU
76
+ | HRNetFace | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.124 ms | 30 - 30 MB | NPU
77
+ | HRNetFace | ONNX | w8a8 | Snapdragon® X2 Elite | 0.662 ms | 1 - 1 MB | NPU
78
+ | HRNetFace | ONNX | w8a8 | Snapdragon® X Elite | 1.33 ms | 15 - 15 MB | NPU
79
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.869 ms | 0 - 158 MB | NPU
80
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.739 ms | 0 - 158 MB | NPU
81
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.07 ms | 0 - 3 MB | NPU
82
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.29 ms | 0 - 173 MB | NPU
83
+ | HRNetFace | ONNX | w8a8 | Qualcomm® QCS8450 | 1.739 ms | 0 - 158 MB | NPU
84
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.702 ms | 0 - 109 MB | NPU
85
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.595 ms | 0 - 115 MB | NPU
86
+ | HRNetFace | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.595 ms | 0 - 112 MB | NPU
87
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.491 ms | 0 - 3 MB | NPU
88
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.043 ms | 0 - 234 MB | NPU
89
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.595 ms | 0 - 115 MB | NPU
90
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.702 ms | 0 - 109 MB | NPU
91
+ | HRNetFace | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.33 ms | 15 - 15 MB | NPU
92
+ | HRNetFace | QNN_DLC | float | Snapdragon® X2 Elite | 1.915 ms | 1 - 1 MB | NPU
93
+ | HRNetFace | QNN_DLC | float | Snapdragon® X Elite | 3.679 ms | 1 - 1 MB | NPU
94
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.337 ms | 0 - 121 MB | NPU
95
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 5.48 ms | 1 - 106 MB | NPU
96
+ | HRNetFace | QNN_DLC | float | Qualcomm® QCS8275 | 15.442 ms | 1 - 75 MB | NPU
97
+ | HRNetFace | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.279 ms | 1 - 3 MB | NPU
98
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA8775P | 5.077 ms | 1 - 79 MB | NPU
99
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA8650P | 5.077 ms | 1 - 79 MB | NPU
100
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA8255P | 5.077 ms | 1 - 79 MB | NPU
101
+ | HRNetFace | QNN_DLC | float | Qualcomm® QCS8450 | 5.48 ms | 1 - 106 MB | NPU
102
+ | HRNetFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 5.365 ms | 1 - 4 MB | NPU
103
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.414 ms | 1 - 79 MB | NPU
104
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA7255P | 15.442 ms | 1 - 75 MB | NPU
105
+ | HRNetFace | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.761 ms | 0 - 77 MB | NPU
106
+ | HRNetFace | QNN_DLC | float | Qualcomm® SA8295P | 5.642 ms | 1 - 62 MB | NPU
107
+ | HRNetFace | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.761 ms | 0 - 77 MB | NPU
108
+ | HRNetFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 3.679 ms | 1 - 1 MB | NPU
109
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.863 ms | 0 - 0 MB | NPU
110
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® X Elite | 1.546 ms | 0 - 0 MB | NPU
111
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.916 ms | 0 - 112 MB | NPU
112
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.831 ms | 0 - 109 MB | NPU
113
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.943 ms | 0 - 2 MB | NPU
114
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 3.283 ms | 0 - 71 MB | NPU
115
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.329 ms | 0 - 2 MB | NPU
116
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8775P | 1.711 ms | 0 - 72 MB | NPU
117
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8650P | 1.711 ms | 0 - 72 MB | NPU
118
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8255P | 1.711 ms | 0 - 72 MB | NPU
119
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 1.831 ms | 0 - 109 MB | NPU
120
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.681 ms | 0 - 72 MB | NPU
121
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.635 ms | 0 - 79 MB | NPU
122
+ | HRNetFace | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.544 ms | 0 - 73 MB | NPU
123
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.519 ms | 0 - 2 MB | NPU
124
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 10.633 ms | 0 - 200 MB | NPU
125
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA7255P | 3.283 ms | 0 - 71 MB | NPU
126
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.221 ms | 0 - 69 MB | NPU
127
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.635 ms | 0 - 79 MB | NPU
128
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.681 ms | 0 - 72 MB | NPU
129
+ | HRNetFace | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 1.546 ms | 0 - 0 MB | NPU
130
+ | HRNetFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.332 ms | 0 - 140 MB | NPU
131
+ | HRNetFace | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5.462 ms | 0 - 126 MB | NPU
132
+ | HRNetFace | TFLITE | float | Qualcomm® QCS8275 | 15.473 ms | 1 - 91 MB | NPU
133
+ | HRNetFace | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.314 ms | 4 - 7 MB | NPU
134
+ | HRNetFace | TFLITE | float | Qualcomm® SA8775P | 5.14 ms | 1 - 94 MB | NPU
135
+ | HRNetFace | TFLITE | float | Qualcomm® SA8650P | 5.14 ms | 1 - 94 MB | NPU
136
+ | HRNetFace | TFLITE | float | Qualcomm® SA8255P | 5.14 ms | 1 - 94 MB | NPU
137
+ | HRNetFace | TFLITE | float | Qualcomm® QCS8450 | 5.462 ms | 0 - 126 MB | NPU
138
+ | HRNetFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5.001 ms | 0 - 35 MB | NPU
139
+ | HRNetFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.409 ms | 0 - 90 MB | NPU
140
+ | HRNetFace | TFLITE | float | Qualcomm® SA7255P | 15.473 ms | 1 - 91 MB | NPU
141
+ | HRNetFace | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.762 ms | 0 - 87 MB | NPU
142
+ | HRNetFace | TFLITE | float | Qualcomm® SA8295P | 5.681 ms | 1 - 74 MB | NPU
143
+ | HRNetFace | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.762 ms | 0 - 87 MB | NPU
144
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.73 ms | 0 - 115 MB | NPU
145
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 1.554 ms | 0 - 112 MB | NPU
146
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 5.248 ms | 0 - 18 MB | NPU
147
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8275 | 2.894 ms | 0 - 72 MB | NPU
148
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.102 ms | 0 - 2 MB | NPU
149
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8775P | 1.502 ms | 0 - 74 MB | NPU
150
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8650P | 1.502 ms | 0 - 74 MB | NPU
151
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8255P | 1.502 ms | 0 - 74 MB | NPU
152
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® QCS8450 | 1.554 ms | 0 - 112 MB | NPU
153
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.58 ms | 0 - 68 MB | NPU
154
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1.356 ms | 0 - 75 MB | NPU
155
+ | HRNetFace | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.467 ms | 0 - 73 MB | NPU
156
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 1.278 ms | 0 - 18 MB | NPU
157
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 9.85 ms | 0 - 192 MB | NPU
158
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA7255P | 2.894 ms | 0 - 72 MB | NPU
159
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® SA8295P | 1.971 ms | 0 - 69 MB | NPU
160
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 1.356 ms | 0 - 75 MB | NPU
161
+ | HRNetFace | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.58 ms | 0 - 68 MB | NPU
162
 
163
  ## License
164
  * The license for the original implementation of HRNetFace can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "w8a8": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-tflite-w8a8.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-qnn_dlc-w8a8.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-onnx-w8a8.zip"
25
  }
26
  }
27
  },
@@ -32,20 +32,20 @@
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-tflite-float.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-qnn_dlc-float.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.57.3/hrnet_face-onnx-float.zip"
49
  }
50
  }
51
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "w8a8": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-tflite-w8a8.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-qnn_dlc-w8a8.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-onnx-w8a8.zip"
25
  }
26
  }
27
  },
 
32
  "qairt": "2.45.0.260326154327",
33
  "litert": "1.4.4"
34
  },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-tflite-float.zip"
36
  },
37
  "qnn_dlc": {
38
  "tool_versions": {
39
  "qairt": "2.45.0.260326154327"
40
  },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-qnn_dlc-float.zip"
42
  },
43
  "onnx": {
44
  "tool_versions": {
45
  "qairt": "2.45.0.260326154327",
46
  "onnx_runtime": "1.25.0"
47
  },
48
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_face/releases/v0.58.0/hrnet_face-onnx-float.zip"
49
  }
50
  }
51
  }