Hugging Face's logo

qualcomm
/
CavaFace

Object Detection
PyTorch
real_time
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
7f1fedd
·
verified ·
1 Parent(s): f962574

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 +51 -51
  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
  - bu_auto
@@ -16,7 +16,7 @@ pipeline_tag: object-detection
16
  A PyTorch-based framework for training face recognition models that generates facial embeddings for verification and identification tasks
17
 
18
  This is based on the implementation of CavaFace found [here](https://github.com/cavalleria/cavaface).
19
- 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/cavaface) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
@@ -29,23 +29,23 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/cavaface/releases/v0.60.0/cavaface-onnx-float.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cavaface/releases/v0.60.0/cavaface-qnn_dlc-float.zip)
34
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cavaface/releases/v0.60.0/cavaface-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[CavaFace on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cavaface)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/cavaface) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
- See our repository for [CavaFace on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/cavaface) for usage instructions.
49
 
50
  ## Model Details
51
 
@@ -60,50 +60,50 @@ See our repository for [CavaFace on GitHub](https://github.com/qualcomm/ai-hub-m
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | CavaFace | ONNX | float | Snapdragon® X2 Elite | 2.328 ms | 1 - 1 MB | NPU
64
- | CavaFace | ONNX | float | Snapdragon® X Elite | 4.301 ms | 126 - 126 MB | NPU
65
- | CavaFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.188 ms | 0 - 136 MB | NPU
66
- | CavaFace | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 9.554 ms | 0 - 229 MB | NPU
67
- | CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 7.641 ms | 0 - 4 MB | NPU
68
- | CavaFace | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.323 ms | 0 - 164 MB | NPU
69
- | CavaFace | ONNX | float | Qualcomm® QCS8450 | 9.554 ms | 0 - 229 MB | NPU
70
- | CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 6.706 ms | 0 - 3 MB | NPU
71
- | CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.301 ms | 126 - 126 MB | NPU
72
- | CavaFace | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.625 ms | 0 - 91 MB | NPU
73
- | CavaFace | ONNX | float | Snapdragon® 8 Elite Mobile | 2.625 ms | 0 - 91 MB | NPU
74
- | CavaFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.268 ms | 0 - 88 MB | NPU
75
- | CavaFace | QNN_DLC | float | Snapdragon® X2 Elite | 2.586 ms | 0 - 0 MB | NPU
76
- | CavaFace | QNN_DLC | float | Snapdragon® X Elite | 4.469 ms | 0 - 0 MB | NPU
77
- | CavaFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.188 ms | 0 - 131 MB | NPU
78
- | CavaFace | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.57 ms | 0 - 221 MB | NPU
79
- | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 7.608 ms | 0 - 3 MB | NPU
80
- | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 24.705 ms | 0 - 81 MB | NPU
81
- | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.298 ms | 0 - 2 MB | NPU
82
- | CavaFace | QNN_DLC | float | Qualcomm® SA8775P | 6.935 ms | 0 - 82 MB | NPU
83
- | CavaFace | QNN_DLC | float | Qualcomm® SA8650P | 6.935 ms | 0 - 82 MB | NPU
84
- | CavaFace | QNN_DLC | float | Qualcomm® SA8255P | 6.935 ms | 0 - 82 MB | NPU
85
- | CavaFace | QNN_DLC | float | Qualcomm® QCS8450 | 9.57 ms | 0 - 221 MB | NPU
86
- | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 7.129 ms | 0 - 2 MB | NPU
87
- | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.469 ms | 0 - 0 MB | NPU
88
- | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.647 ms | 0 - 83 MB | NPU
89
- | CavaFace | QNN_DLC | float | Qualcomm® SA7255P | 24.705 ms | 0 - 81 MB | NPU
90
- | CavaFace | QNN_DLC | float | Qualcomm® SA8295P | 8.018 ms | 0 - 200 MB | NPU
91
- | CavaFace | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.647 ms | 0 - 83 MB | NPU
92
- | CavaFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.256 ms | 0 - 85 MB | NPU
93
- | CavaFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.147 ms | 0 - 244 MB | NPU
94
- | CavaFace | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 9.431 ms | 0 - 333 MB | NPU
95
- | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 24.515 ms | 0 - 95 MB | NPU
96
- | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.17 ms | 0 - 2 MB | NPU
97
- | CavaFace | TFLITE | float | Qualcomm® SA8775P | 6.881 ms | 0 - 96 MB | NPU
98
- | CavaFace | TFLITE | float | Qualcomm® SA8650P | 6.881 ms | 0 - 96 MB | NPU
99
- | CavaFace | TFLITE | float | Qualcomm® SA8255P | 6.881 ms | 0 - 96 MB | NPU
100
- | CavaFace | TFLITE | float | Qualcomm® QCS8450 | 9.431 ms | 0 - 333 MB | NPU
101
- | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.609 ms | 0 - 128 MB | NPU
102
- | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.609 ms | 0 - 98 MB | NPU
103
- | CavaFace | TFLITE | float | Qualcomm® SA7255P | 24.515 ms | 0 - 95 MB | NPU
104
- | CavaFace | TFLITE | float | Qualcomm® SA8295P | 7.976 ms | 0 - 209 MB | NPU
105
- | CavaFace | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.609 ms | 0 - 98 MB | NPU
106
- | CavaFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.242 ms | 0 - 97 MB | NPU
107
 
108
  ## License
109
  * The license for the original implementation of CavaFace can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: mit
4
  tags:
5
  - real_time
6
  - bu_auto
 
16
  A PyTorch-based framework for training face recognition models that generates facial embeddings for verification and identification tasks
17
 
18
  This is based on the implementation of CavaFace found [here](https://github.com/cavalleria/cavaface).
19
+ 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/cavaface) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | 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/cavaface/releases/v0.61.0/cavaface-onnx-float.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cavaface/releases/v0.61.0/cavaface-qnn_dlc-float.zip)
34
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/cavaface/releases/v0.61.0/cavaface-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[CavaFace on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/cavaface)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/cavaface) Python library to compile and export the model with your own:
42
  - Custom weights (e.g., fine-tuned checkpoints)
43
  - Custom input shapes
44
  - Target device and runtime configurations
45
 
46
  This option is ideal if you need to customize the model beyond the default configuration provided here.
47
 
48
+ See our repository for [CavaFace on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/cavaface) for usage instructions.
49
 
50
  ## Model Details
51
 
 
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
+ | CavaFace | ONNX | float | Snapdragon® X2 Elite | 2.335 ms | 1 - 1 MB | NPU
64
+ | CavaFace | ONNX | float | Snapdragon® X Elite | 4.303 ms | 127 - 127 MB | NPU
65
+ | CavaFace | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.19 ms | 0 - 138 MB | NPU
66
+ | CavaFace | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 9.533 ms | 0 - 229 MB | NPU
67
+ | CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 7.648 ms | 0 - 4 MB | NPU
68
+ | CavaFace | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.315 ms | 0 - 164 MB | NPU
69
+ | CavaFace | ONNX | float | Qualcomm® QCS8450 | 9.533 ms | 0 - 229 MB | NPU
70
+ | CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 6.99 ms | 0 - 3 MB | NPU
71
+ | CavaFace | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.303 ms | 127 - 127 MB | NPU
72
+ | CavaFace | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.615 ms | 0 - 89 MB | NPU
73
+ | CavaFace | ONNX | float | Snapdragon® 8 Elite Mobile | 2.615 ms | 0 - 89 MB | NPU
74
+ | CavaFace | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.28 ms | 0 - 90 MB | NPU
75
+ | CavaFace | QNN_DLC | float | Snapdragon® X2 Elite | 2.6 ms | 0 - 0 MB | NPU
76
+ | CavaFace | QNN_DLC | float | Snapdragon® X Elite | 4.505 ms | 1 - 1 MB | NPU
77
+ | CavaFace | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.189 ms | 0 - 133 MB | NPU
78
+ | CavaFace | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.576 ms | 0 - 221 MB | NPU
79
+ | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 7.594 ms | 0 - 3 MB | NPU
80
+ | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 24.709 ms | 0 - 81 MB | NPU
81
+ | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.303 ms | 0 - 2 MB | NPU
82
+ | CavaFace | QNN_DLC | float | Qualcomm® SA8775P | 6.92 ms | 0 - 82 MB | NPU
83
+ | CavaFace | QNN_DLC | float | Qualcomm® SA8650P | 6.92 ms | 0 - 82 MB | NPU
84
+ | CavaFace | QNN_DLC | float | Qualcomm® SA8255P | 6.92 ms | 0 - 82 MB | NPU
85
+ | CavaFace | QNN_DLC | float | Qualcomm® QCS8450 | 9.576 ms | 0 - 221 MB | NPU
86
+ | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.678 ms | 0 - 2 MB | NPU
87
+ | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.505 ms | 1 - 1 MB | NPU
88
+ | CavaFace | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.589 ms | 0 - 85 MB | NPU
89
+ | CavaFace | QNN_DLC | float | Qualcomm® SA7255P | 24.709 ms | 0 - 81 MB | NPU
90
+ | CavaFace | QNN_DLC | float | Qualcomm® SA8295P | 8.011 ms | 0 - 198 MB | NPU
91
+ | CavaFace | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.589 ms | 0 - 85 MB | NPU
92
+ | CavaFace | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.25 ms | 0 - 84 MB | NPU
93
+ | CavaFace | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.136 ms | 0 - 242 MB | NPU
94
+ | CavaFace | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 9.459 ms | 0 - 331 MB | NPU
95
+ | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 24.515 ms | 0 - 96 MB | NPU
96
+ | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.158 ms | 0 - 3 MB | NPU
97
+ | CavaFace | TFLITE | float | Qualcomm® SA8775P | 6.898 ms | 0 - 96 MB | NPU
98
+ | CavaFace | TFLITE | float | Qualcomm® SA8650P | 6.898 ms | 0 - 96 MB | NPU
99
+ | CavaFace | TFLITE | float | Qualcomm® SA8255P | 6.898 ms | 0 - 96 MB | NPU
100
+ | CavaFace | TFLITE | float | Qualcomm® QCS8450 | 9.459 ms | 0 - 331 MB | NPU
101
+ | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.608 ms | 0 - 128 MB | NPU
102
+ | CavaFace | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.582 ms | 0 - 97 MB | NPU
103
+ | CavaFace | TFLITE | float | Qualcomm® SA7255P | 24.515 ms | 0 - 96 MB | NPU
104
+ | CavaFace | TFLITE | float | Qualcomm® SA8295P | 7.95 ms | 0 - 210 MB | NPU
105
+ | CavaFace | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.582 ms | 0 - 97 MB | NPU
106
+ | CavaFace | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.23 ms | 0 - 99 MB | NPU
107
 
108
  ## License
109
  * The license for the original implementation of CavaFace 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/cavaface/releases/v0.60.0/cavaface-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/cavaface/releases/v0.60.0/cavaface-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/cavaface/releases/v0.60.0/cavaface-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/cavaface/releases/v0.61.0/cavaface-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/cavaface/releases/v0.61.0/cavaface-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/cavaface/releases/v0.61.0/cavaface-tflite-float.zip"
24
  }
25
  }
26
  }