Hugging Face's logo

qualcomm
/
SixDRepNet

Keypoint Detection
PyTorch
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
76a5598
·
verified ·
1 Parent(s): 3b3e811

v0.61.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (2) hide show
  1. README.md +93 -91
  2. release_assets.json +4 -4
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - real_time
6
  - android
@@ -15,7 +15,7 @@ pipeline_tag: keypoint-detection
15
  6DRepNet predicts head pose (pitch, yaw, roll) from a face image using a RepVGG-B1g2 backbone and a continuous 6D rotation representation, achieving robust and accurate head pose estimation.
16
 
17
  This is based on the implementation of SixDRepNet found [here](https://github.com/thohemp/6DRepNet).
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/sixd_repnet) 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
 
@@ -28,23 +28,23 @@ 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.60.0/sixd_repnet-onnx-float.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.60.0/sixd_repnet-qnn_dlc-float.zip)
33
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.60.0/sixd_repnet-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[SixDRepNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sixd_repnet)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/sixd_repnet) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
- See our repository for [SixDRepNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/sixd_repnet) for usage instructions.
48
 
49
  ## Model Details
50
 
@@ -58,94 +58,96 @@ See our repository for [SixDRepNet on GitHub](https://github.com/qualcomm/ai-hub
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
- | face_detector | ONNX | float | Snapdragon® X2 Elite | 2.196 ms | 5 - 5 MB | NPU
62
- | face_detector | ONNX | float | Snapdragon® X Elite | 4.158 ms | 5 - 5 MB | NPU
63
- | face_detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.496 ms | 0 - 164 MB | NPU
64
- | face_detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.801 ms | 7 - 178 MB | NPU
65
- | face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.376 ms | 4 - 13 MB | NPU
66
- | face_detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.99 ms | 0 - 4 MB | NPU
67
- | face_detector | ONNX | float | Qualcomm® QCS8450 | 6.801 ms | 7 - 178 MB | NPU
68
- | face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.806 ms | 5 - 12 MB | NPU
69
- | face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.158 ms | 5 - 5 MB | NPU
70
- | face_detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.259 ms | 0 - 155 MB | NPU
71
- | face_detector | ONNX | float | Snapdragon® 8 Elite Mobile | 2.259 ms | 0 - 155 MB | NPU
72
- | face_detector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.081 ms | 3 - 158 MB | NPU
73
- | face_detector | QNN_DLC | float | Snapdragon® X2 Elite | 2.832 ms | 5 - 5 MB | NPU
74
- | face_detector | QNN_DLC | float | Snapdragon® X Elite | 5.809 ms | 5 - 5 MB | NPU
75
- | face_detector | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.505 ms | 5 - 170 MB | NPU
76
- | face_detector | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 8.348 ms | 5 - 61 MB | NPU
77
- | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.395 ms | 5 - 13 MB | NPU
78
- | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 11.566 ms | 1 - 149 MB | NPU
79
- | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.236 ms | 2 - 4 MB | NPU
80
- | face_detector | QNN_DLC | float | Qualcomm® SA8775P | 6.338 ms | 0 - 152 MB | NPU
81
- | face_detector | QNN_DLC | float | Qualcomm® SA8650P | 6.338 ms | 0 - 152 MB | NPU
82
- | face_detector | QNN_DLC | float | Qualcomm® SA8255P | 6.338 ms | 0 - 152 MB | NPU
83
- | face_detector | QNN_DLC | float | Qualcomm® QCS8450 | 8.348 ms | 5 - 61 MB | NPU
84
- | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.084 ms | 5 - 12 MB | NPU
85
- | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.809 ms | 5 - 5 MB | NPU
86
- | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.809 ms | 0 - 154 MB | NPU
87
- | face_detector | QNN_DLC | float | Qualcomm® SA7255P | 11.566 ms | 1 - 149 MB | NPU
88
- | face_detector | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.809 ms | 0 - 154 MB | NPU
89
- | face_detector | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.369 ms | 4 - 157 MB | NPU
90
- | face_detector | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.481 ms | 0 - 168 MB | NPU
91
- | face_detector | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.324 ms | 1 - 55 MB | NPU
92
- | face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 5.447 ms | 1 - 11 MB | NPU
93
- | face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 11.6 ms | 1 - 149 MB | NPU
94
- | face_detector | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.285 ms | 1 - 3 MB | NPU
95
- | face_detector | TFLITE | float | Qualcomm® SA8775P | 6.362 ms | 1 - 154 MB | NPU
96
- | face_detector | TFLITE | float | Qualcomm® SA8650P | 6.362 ms | 1 - 154 MB | NPU
97
- | face_detector | TFLITE | float | Qualcomm® SA8255P | 6.362 ms | 1 - 154 MB | NPU
98
- | face_detector | TFLITE | float | Qualcomm® QCS8450 | 8.324 ms | 1 - 55 MB | NPU
99
- | face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.089 ms | 1 - 10 MB | NPU
100
- | face_detector | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.787 ms | 0 - 154 MB | NPU
101
- | face_detector | TFLITE | float | Qualcomm® SA7255P | 11.6 ms | 1 - 149 MB | NPU
102
- | face_detector | TFLITE | float | Qualcomm® SA8295P | 7.722 ms | 1 - 35 MB | NPU
103
- | face_detector | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.787 ms | 0 - 154 MB | NPU
104
- | face_detector | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.4 ms | 0 - 152 MB | NPU
105
- | pose_estimator | ONNX | float | Snapdragon® X2 Elite | 1.289 ms | 1 - 1 MB | NPU
106
- | pose_estimator | ONNX | float | Snapdragon® X Elite | 2.617 ms | 76 - 76 MB | NPU
107
- | pose_estimator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.077 ms | 0 - 37 MB | NPU
108
- | pose_estimator | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 5.55 ms | 0 - 39 MB | NPU
109
- | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 5.131 ms | 0 - 4 MB | NPU
110
- | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.711 ms | 0 - 81 MB | NPU
111
- | pose_estimator | ONNX | float | Qualcomm® QCS8450 | 5.55 ms | 0 - 39 MB | NPU
112
- | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.494 ms | 0 - 4 MB | NPU
113
- | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.617 ms | 76 - 76 MB | NPU
114
- | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.637 ms | 0 - 25 MB | NPU
115
- | pose_estimator | ONNX | float | Snapdragon® 8 Elite Mobile | 1.637 ms | 0 - 25 MB | NPU
 
116
  | pose_estimator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.335 ms | 0 - 25 MB | NPU
117
- | pose_estimator | QNN_DLC | float | Snapdragon® X2 Elite | 1.472 ms | 1 - 1 MB | NPU
118
- | pose_estimator | QNN_DLC | float | Snapdragon® X Elite | 2.88 ms | 1 - 1 MB | NPU
119
- | pose_estimator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.235 ms | 0 - 38 MB | NPU
120
  | pose_estimator | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 6.532 ms | 0 - 40 MB | NPU
121
- | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.156 ms | 1 - 4 MB | NPU
122
- | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 17.823 ms | 1 - 25 MB | NPU
123
- | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.773 ms | 1 - 2 MB | NPU
124
- | pose_estimator | QNN_DLC | float | Qualcomm® SA8775P | 4.84 ms | 1 - 26 MB | NPU
125
- | pose_estimator | QNN_DLC | float | Qualcomm® SA8650P | 4.84 ms | 1 - 26 MB | NPU
126
- | pose_estimator | QNN_DLC | float | Qualcomm® SA8255P | 4.84 ms | 1 - 26 MB | NPU
127
  | pose_estimator | QNN_DLC | float | Qualcomm® QCS8450 | 6.532 ms | 0 - 40 MB | NPU
128
- | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.645 ms | 3 - 5 MB | NPU
129
- | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.88 ms | 1 - 1 MB | NPU
130
- | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.723 ms | 0 - 28 MB | NPU
131
- | pose_estimator | QNN_DLC | float | Qualcomm® SA7255P | 17.823 ms | 1 - 25 MB | NPU
132
- | pose_estimator | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.723 ms | 0 - 28 MB | NPU
 
133
  | pose_estimator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.434 ms | 1 - 28 MB | NPU
134
- | pose_estimator | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.253 ms | 0 - 43 MB | NPU
135
- | pose_estimator | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.499 ms | 0 - 46 MB | NPU
136
- | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 5.125 ms | 0 - 78 MB | NPU
137
- | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 17.413 ms | 0 - 26 MB | NPU
138
- | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.847 ms | 0 - 3 MB | NPU
139
- | pose_estimator | TFLITE | float | Qualcomm® SA8775P | 4.807 ms | 0 - 27 MB | NPU
140
- | pose_estimator | TFLITE | float | Qualcomm® SA8650P | 4.807 ms | 0 - 27 MB | NPU
141
- | pose_estimator | TFLITE | float | Qualcomm® SA8255P | 4.807 ms | 0 - 27 MB | NPU
142
- | pose_estimator | TFLITE | float | Qualcomm® QCS8450 | 6.499 ms | 0 - 46 MB | NPU
143
- | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.641 ms | 0 - 78 MB | NPU
144
- | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.71 ms | 0 - 31 MB | NPU
145
- | pose_estimator | TFLITE | float | Qualcomm® SA7255P | 17.413 ms | 0 - 26 MB | NPU
146
- | pose_estimator | TFLITE | float | Qualcomm® SA8295P | 5.337 ms | 0 - 27 MB | NPU
147
- | pose_estimator | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.71 ms | 0 - 31 MB | NPU
148
- | pose_estimator | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.381 ms | 0 - 26 MB | NPU
149
 
150
  ## License
151
  * The license for the original implementation of SixDRepNet can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: mit
4
  tags:
5
  - real_time
6
  - android
 
15
  6DRepNet predicts head pose (pitch, yaw, roll) from a face image using a RepVGG-B1g2 backbone and a continuous 6D rotation representation, achieving robust and accurate head pose estimation.
16
 
17
  This is based on the implementation of SixDRepNet found [here](https://github.com/thohemp/6DRepNet).
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/v0.61.0/src/qai_hub_models/models/sixd_repnet) 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.61.0/sixd_repnet-onnx-float.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.61.0/sixd_repnet-qnn_dlc-float.zip)
33
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.61.0/sixd_repnet-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[SixDRepNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sixd_repnet)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/sixd_repnet) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
+ See our repository for [SixDRepNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/sixd_repnet) for usage instructions.
48
 
49
  ## Model Details
50
 
 
58
  ## Performance Summary
59
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
  |---|---|---|---|---|---|---
61
+ | face_detector | ONNX | float | Snapdragon® X2 Elite | 2.25 ms | 5 - 5 MB | NPU
62
+ | face_detector | ONNX | float | Snapdragon® X Elite | 4.128 ms | 5 - 5 MB | NPU
63
+ | face_detector | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.518 ms | 2 - 170 MB | NPU
64
+ | face_detector | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.783 ms | 7 - 176 MB | NPU
65
+ | face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.4 ms | 4 - 13 MB | NPU
66
+ | face_detector | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 3.996 ms | 2 - 5 MB | NPU
67
+ | face_detector | ONNX | float | Qualcomm® QCS8450 | 6.783 ms | 7 - 176 MB | NPU
68
+ | face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.824 ms | 5 - 12 MB | NPU
69
+ | face_detector | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.128 ms | 5 - 5 MB | NPU
70
+ | face_detector | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.263 ms | 0 - 154 MB | NPU
71
+ | face_detector | ONNX | float | Snapdragon® 8 Elite Mobile | 2.263 ms | 0 - 154 MB | NPU
72
+ | face_detector | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.079 ms | 1 - 155 MB | NPU
73
+ | face_detector | QNN_DLC | float | Snapdragon® X2 Elite | 2.827 ms | 5 - 5 MB | NPU
74
+ | face_detector | QNN_DLC | float | Snapdragon® X Elite | 5.85 ms | 5 - 5 MB | NPU
75
+ | face_detector | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.488 ms | 5 - 174 MB | NPU
76
+ | face_detector | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 8.327 ms | 5 - 59 MB | NPU
77
+ | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.398 ms | 5 - 13 MB | NPU
78
+ | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 11.582 ms | 2 - 150 MB | NPU
79
+ | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.246 ms | 5 - 6 MB | NPU
80
+ | face_detector | QNN_DLC | float | Qualcomm® SA8775P | 6.36 ms | 0 - 152 MB | NPU
81
+ | face_detector | QNN_DLC | float | Qualcomm® SA8650P | 6.36 ms | 0 - 152 MB | NPU
82
+ | face_detector | QNN_DLC | float | Qualcomm® SA8255P | 6.36 ms | 0 - 152 MB | NPU
83
+ | face_detector | QNN_DLC | float | Qualcomm® QCS8450 | 8.327 ms | 5 - 59 MB | NPU
84
+ | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 7.55 ms | 5 - 12 MB | NPU
85
+ | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.85 ms | 5 - 5 MB | NPU
86
+ | face_detector | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.818 ms | 0 - 153 MB | NPU
87
+ | face_detector | QNN_DLC | float | Qualcomm® SA7255P | 11.582 ms | 2 - 150 MB | NPU
88
+ | face_detector | QNN_DLC | float | Qualcomm® SA8295P | 7.684 ms | 0 - 34 MB | NPU
89
+ | face_detector | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.818 ms | 0 - 153 MB | NPU
90
+ | face_detector | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.369 ms | 4 - 158 MB | NPU
91
+ | face_detector | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.478 ms | 0 - 164 MB | NPU
92
+ | face_detector | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.307 ms | 1 - 53 MB | NPU
93
+ | face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 5.418 ms | 1 - 11 MB | NPU
94
+ | face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 11.597 ms | 1 - 149 MB | NPU
95
+ | face_detector | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.306 ms | 1 - 3 MB | NPU
96
+ | face_detector | TFLITE | float | Qualcomm® SA8775P | 6.323 ms | 1 - 155 MB | NPU
97
+ | face_detector | TFLITE | float | Qualcomm® SA8650P | 6.323 ms | 1 - 155 MB | NPU
98
+ | face_detector | TFLITE | float | Qualcomm® SA8255P | 6.323 ms | 1 - 155 MB | NPU
99
+ | face_detector | TFLITE | float | Qualcomm® QCS8450 | 8.307 ms | 1 - 53 MB | NPU
100
+ | face_detector | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.09 ms | 1 - 10 MB | NPU
101
+ | face_detector | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.799 ms | 0 - 151 MB | NPU
102
+ | face_detector | TFLITE | float | Qualcomm® SA7255P | 11.597 ms | 1 - 149 MB | NPU
103
+ | face_detector | TFLITE | float | Qualcomm® SA8295P | 7.715 ms | 1 - 35 MB | NPU
104
+ | face_detector | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.799 ms | 0 - 151 MB | NPU
105
+ | face_detector | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.417 ms | 0 - 152 MB | NPU
106
+ | pose_estimator | ONNX | float | Snapdragon® X2 Elite | 1.298 ms | 2 - 2 MB | NPU
107
+ | pose_estimator | ONNX | float | Snapdragon® X Elite | 2.614 ms | 75 - 75 MB | NPU
108
+ | pose_estimator | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.079 ms | 0 - 39 MB | NPU
109
+ | pose_estimator | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 5.552 ms | 0 - 40 MB | NPU
110
+ | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 5.122 ms | 0 - 4 MB | NPU
111
+ | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.712 ms | 0 - 82 MB | NPU
112
+ | pose_estimator | ONNX | float | Qualcomm® QCS8450 | 5.552 ms | 0 - 40 MB | NPU
113
+ | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 4.498 ms | 0 - 4 MB | NPU
114
+ | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.614 ms | 75 - 75 MB | NPU
115
+ | pose_estimator | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 1.637 ms | 0 - 24 MB | NPU
116
+ | pose_estimator | ONNX | float | Snapdragon® 8 Elite Mobile | 1.637 ms | 0 - 24 MB | NPU
117
  | pose_estimator | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.335 ms | 0 - 25 MB | NPU
118
+ | pose_estimator | QNN_DLC | float | Snapdragon® X2 Elite | 1.517 ms | 1 - 1 MB | NPU
119
+ | pose_estimator | QNN_DLC | float | Snapdragon® X Elite | 2.875 ms | 1 - 1 MB | NPU
120
+ | pose_estimator | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.233 ms | 0 - 37 MB | NPU
121
  | pose_estimator | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 6.532 ms | 0 - 40 MB | NPU
122
+ | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.164 ms | 1 - 4 MB | NPU
123
+ | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 17.805 ms | 1 - 25 MB | NPU
124
+ | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.785 ms | 1 - 2 MB | NPU
125
+ | pose_estimator | QNN_DLC | float | Qualcomm® SA8775P | 4.82 ms | 1 - 26 MB | NPU
126
+ | pose_estimator | QNN_DLC | float | Qualcomm® SA8650P | 4.82 ms | 1 - 26 MB | NPU
127
+ | pose_estimator | QNN_DLC | float | Qualcomm® SA8255P | 4.82 ms | 1 - 26 MB | NPU
128
  | pose_estimator | QNN_DLC | float | Qualcomm® QCS8450 | 6.532 ms | 0 - 40 MB | NPU
129
+ | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 4.652 ms | 3 - 5 MB | NPU
130
+ | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.875 ms | 1 - 1 MB | NPU
131
+ | pose_estimator | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.695 ms | 0 - 28 MB | NPU
132
+ | pose_estimator | QNN_DLC | float | Qualcomm® SA7255P | 17.805 ms | 1 - 25 MB | NPU
133
+ | pose_estimator | QNN_DLC | float | Qualcomm® SA8295P | 5.409 ms | 1 - 28 MB | NPU
134
+ | pose_estimator | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.695 ms | 0 - 28 MB | NPU
135
  | pose_estimator | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.434 ms | 1 - 28 MB | NPU
136
+ | pose_estimator | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.257 ms | 0 - 44 MB | NPU
137
+ | pose_estimator | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 6.502 ms | 0 - 46 MB | NPU
138
+ | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 5.134 ms | 0 - 78 MB | NPU
139
+ | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 17.389 ms | 0 - 26 MB | NPU
140
+ | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.85 ms | 0 - 2 MB | NPU
141
+ | pose_estimator | TFLITE | float | Qualcomm® SA8775P | 4.843 ms | 0 - 27 MB | NPU
142
+ | pose_estimator | TFLITE | float | Qualcomm® SA8650P | 4.843 ms | 0 - 27 MB | NPU
143
+ | pose_estimator | TFLITE | float | Qualcomm® SA8255P | 4.843 ms | 0 - 27 MB | NPU
144
+ | pose_estimator | TFLITE | float | Qualcomm® QCS8450 | 6.502 ms | 0 - 46 MB | NPU
145
+ | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.776 ms | 0 - 78 MB | NPU
146
+ | pose_estimator | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 1.705 ms | 0 - 29 MB | NPU
147
+ | pose_estimator | TFLITE | float | Qualcomm® SA7255P | 17.389 ms | 0 - 26 MB | NPU
148
+ | pose_estimator | TFLITE | float | Qualcomm® SA8295P | 5.352 ms | 0 - 28 MB | NPU
149
+ | pose_estimator | TFLITE | float | Snapdragon® 8 Elite Mobile | 1.705 ms | 0 - 29 MB | NPU
150
+ | pose_estimator | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.38 ms | 0 - 29 MB | NPU
151
 
152
  ## License
153
  * The license for the original implementation of SixDRepNet can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.60.0/sixd_repnet-onnx-float.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/sixd_repnet/releases/v0.60.0/sixd_repnet-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.60.0/sixd_repnet-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.61.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.61.0/sixd_repnet-onnx-float.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/sixd_repnet/releases/v0.61.0/sixd_repnet-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sixd_repnet/releases/v0.61.0/sixd_repnet-tflite-float.zip"
24
  }
25
  }
26
  }