Hugging Face's logo

qualcomm
/
LiteHRNet

Keypoint Detection
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
3d55a56
·
verified ·
1 Parent(s): 5ed8b5f

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 +52 -52
  2. release_assets.json +4 -4
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - android
6
  pipeline_tag: keypoint-detection
@@ -14,7 +14,7 @@ pipeline_tag: keypoint-detection
14
  LiteHRNet is a machine learning model that detects human pose and returns a location and confidence for each of 17 joints.
15
 
16
  This is based on the implementation of LiteHRNet found [here](https://github.com/HRNet/Lite-HRNet).
17
- 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/litehrnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
@@ -27,23 +27,23 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | 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/litehrnet/releases/v0.60.0/litehrnet-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.60.0/litehrnet-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.60.0/litehrnet-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[LiteHRNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/litehrnet)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/litehrnet) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
- See our repository for [LiteHRNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/litehrnet) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -57,51 +57,51 @@ See our repository for [LiteHRNet on GitHub](https://github.com/qualcomm/ai-hub-
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
- | LiteHRNet | ONNX | float | Snapdragon® X2 Elite | 2.884 ms | 2 - 2 MB | NPU
61
- | LiteHRNet | ONNX | float | Snapdragon® X Elite | 5.743 ms | 6 - 6 MB | NPU
62
- | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.115 ms | 0 - 124 MB | NPU
63
- | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.302 ms | 1 - 121 MB | NPU
64
- | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.469 ms | 1 - 5 MB | NPU
65
- | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.42 ms | 1 - 22 MB | NPU
66
- | LiteHRNet | ONNX | float | Qualcomm® QCS8450 | 6.302 ms | 1 - 121 MB | NPU
67
- | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.767 ms | 1 - 4 MB | NPU
68
- | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.743 ms | 6 - 6 MB | NPU
69
- | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.875 ms | 0 - 100 MB | NPU
70
- | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Mobile | 2.875 ms | 0 - 100 MB | NPU
71
- | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.782 ms | 0 - 100 MB | NPU
72
- | LiteHRNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.351 ms | 1 - 1 MB | NPU
73
- | LiteHRNet | QNN_DLC | float | Snapdragon® X Elite | 2.417 ms | 1 - 1 MB | NPU
74
- | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.404 ms | 0 - 104 MB | NPU
75
- | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.955 ms | 0 - 102 MB | NPU
76
- | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2.197 ms | 1 - 4 MB | NPU
77
- | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.061 ms | 1 - 78 MB | NPU
78
- | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.12 ms | 1 - 94 MB | NPU
79
- | LiteHRNet | QNN_DLC | float | Qualcomm® SA8775P | 2.707 ms | 1 - 78 MB | NPU
80
- | LiteHRNet | QNN_DLC | float | Qualcomm® SA8650P | 2.707 ms | 1 - 78 MB | NPU
81
- | LiteHRNet | QNN_DLC | float | Qualcomm® SA8255P | 2.707 ms | 1 - 78 MB | NPU
82
- | LiteHRNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.955 ms | 0 - 102 MB | NPU
83
- | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.522 ms | 1 - 3 MB | NPU
84
- | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.417 ms | 1 - 1 MB | NPU
85
- | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.077 ms | 0 - 81 MB | NPU
86
- | LiteHRNet | QNN_DLC | float | Qualcomm® SA7255P | 5.061 ms | 1 - 78 MB | NPU
87
- | LiteHRNet | QNN_DLC | float | Qualcomm® SA8295P | 3.494 ms | 0 - 82 MB | NPU
88
- | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.077 ms | 0 - 81 MB | NPU
89
- | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.916 ms | 1 - 84 MB | NPU
90
- | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.688 ms | 0 - 147 MB | NPU
91
- | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5.361 ms | 1 - 138 MB | NPU
92
- | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.216 ms | 1 - 12 MB | NPU
93
- | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 8.85 ms | 1 - 116 MB | NPU
94
- | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.227 ms | 0 - 2 MB | NPU
95
- | LiteHRNet | TFLITE | float | Qualcomm® SA8775P | 5.364 ms | 1 - 116 MB | NPU
96
- | LiteHRNet | TFLITE | float | Qualcomm® SA8650P | 5.364 ms | 1 - 116 MB | NPU
97
- | LiteHRNet | TFLITE | float | Qualcomm® SA8255P | 5.364 ms | 1 - 116 MB | NPU
98
- | LiteHRNet | TFLITE | float | Qualcomm® QCS8450 | 5.361 ms | 1 - 138 MB | NPU
99
- | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.911 ms | 1 - 11 MB | NPU
100
- | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.245 ms | 0 - 117 MB | NPU
101
- | LiteHRNet | TFLITE | float | Qualcomm® SA7255P | 8.85 ms | 1 - 116 MB | NPU
102
- | LiteHRNet | TFLITE | float | Qualcomm® SA8295P | 6.333 ms | 1 - 113 MB | NPU
103
- | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.245 ms | 0 - 117 MB | NPU
104
- | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.043 ms | 0 - 111 MB | NPU
105
 
106
  ## License
107
  * The license for the original implementation of LiteHRNet can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: apache-2.0
4
  tags:
5
  - android
6
  pipeline_tag: keypoint-detection
 
14
  LiteHRNet is a machine learning model that detects human pose and returns a location and confidence for each of 17 joints.
15
 
16
  This is based on the implementation of LiteHRNet found [here](https://github.com/HRNet/Lite-HRNet).
17
+ 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/litehrnet) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
 
19
  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.
20
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | 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/litehrnet/releases/v0.61.0/litehrnet-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.61.0/litehrnet-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.61.0/litehrnet-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[LiteHRNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/litehrnet)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/litehrnet) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
+ See our repository for [LiteHRNet on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/litehrnet) for usage instructions.
47
 
48
  ## Model Details
49
 
 
57
  ## Performance Summary
58
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
59
  |---|---|---|---|---|---|---
60
+ | LiteHRNet | ONNX | float | Snapdragon® X2 Elite | 2.878 ms | 2 - 2 MB | NPU
61
+ | LiteHRNet | ONNX | float | Snapdragon® X Elite | 5.735 ms | 5 - 5 MB | NPU
62
+ | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.108 ms | 0 - 123 MB | NPU
63
+ | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.316 ms | 1 - 122 MB | NPU
64
+ | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.465 ms | 1 - 5 MB | NPU
65
+ | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.419 ms | 1 - 114 MB | NPU
66
+ | LiteHRNet | ONNX | float | Qualcomm® QCS8450 | 6.316 ms | 1 - 122 MB | NPU
67
+ | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.773 ms | 1 - 4 MB | NPU
68
+ | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.735 ms | 5 - 5 MB | NPU
69
+ | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.881 ms | 0 - 98 MB | NPU
70
+ | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Mobile | 2.881 ms | 0 - 98 MB | NPU
71
+ | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.772 ms | 0 - 100 MB | NPU
72
+ | LiteHRNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.292 ms | 1 - 1 MB | NPU
73
+ | LiteHRNet | QNN_DLC | float | Snapdragon® X Elite | 2.442 ms | 1 - 1 MB | NPU
74
+ | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.393 ms | 0 - 104 MB | NPU
75
+ | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.951 ms | 0 - 101 MB | NPU
76
+ | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2.192 ms | 1 - 4 MB | NPU
77
+ | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.034 ms | 1 - 78 MB | NPU
78
+ | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.117 ms | 1 - 91 MB | NPU
79
+ | LiteHRNet | QNN_DLC | float | Qualcomm® SA8775P | 2.719 ms | 1 - 80 MB | NPU
80
+ | LiteHRNet | QNN_DLC | float | Qualcomm® SA8650P | 2.719 ms | 1 - 80 MB | NPU
81
+ | LiteHRNet | QNN_DLC | float | Qualcomm® SA8255P | 2.719 ms | 1 - 80 MB | NPU
82
+ | LiteHRNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.951 ms | 0 - 101 MB | NPU
83
+ | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.908 ms | 1 - 3 MB | NPU
84
+ | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.442 ms | 1 - 1 MB | NPU
85
+ | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.075 ms | 0 - 80 MB | NPU
86
+ | LiteHRNet | QNN_DLC | float | Qualcomm® SA7255P | 5.034 ms | 1 - 78 MB | NPU
87
+ | LiteHRNet | QNN_DLC | float | Qualcomm® SA8295P | 3.482 ms | 0 - 77 MB | NPU
88
+ | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.075 ms | 0 - 80 MB | NPU
89
+ | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.913 ms | 1 - 83 MB | NPU
90
+ | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.686 ms | 0 - 149 MB | NPU
91
+ | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5.368 ms | 1 - 138 MB | NPU
92
+ | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.23 ms | 1 - 12 MB | NPU
93
+ | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 8.834 ms | 1 - 116 MB | NPU
94
+ | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.262 ms | 0 - 3 MB | NPU
95
+ | LiteHRNet | TFLITE | float | Qualcomm® SA8775P | 5.35 ms | 1 - 116 MB | NPU
96
+ | LiteHRNet | TFLITE | float | Qualcomm® SA8650P | 5.35 ms | 1 - 116 MB | NPU
97
+ | LiteHRNet | TFLITE | float | Qualcomm® SA8255P | 5.35 ms | 1 - 116 MB | NPU
98
+ | LiteHRNet | TFLITE | float | Qualcomm® QCS8450 | 5.368 ms | 1 - 138 MB | NPU
99
+ | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.924 ms | 1 - 11 MB | NPU
100
+ | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.251 ms | 0 - 119 MB | NPU
101
+ | LiteHRNet | TFLITE | float | Qualcomm® SA7255P | 8.834 ms | 1 - 116 MB | NPU
102
+ | LiteHRNet | TFLITE | float | Qualcomm® SA8295P | 6.4 ms | 1 - 113 MB | NPU
103
+ | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.251 ms | 0 - 119 MB | NPU
104
+ | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.051 ms | 0 - 110 MB | NPU
105
 
106
  ## License
107
  * The license for the original implementation of LiteHRNet 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/litehrnet/releases/v0.60.0/litehrnet-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/litehrnet/releases/v0.60.0/litehrnet-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/litehrnet/releases/v0.60.0/litehrnet-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/litehrnet/releases/v0.61.0/litehrnet-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/litehrnet/releases/v0.61.0/litehrnet-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/litehrnet/releases/v0.61.0/litehrnet-tflite-float.zip"
24
  }
25
  }
26
  }