Hugging Face's logo

qualcomm
/
RTMPose-Body2d

Keypoint Detection
PyTorch
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
fcacb09
·
verified ·
1 Parent(s): 5bfba6e

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +56 -56
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: keypoint-detection
14
  RTMPose is a machine learning model that detects human pose and returns a location and confidence for each of 133 joints.
15
 
16
  This is based on the implementation of RTMPose-Body2d found [here](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose).
17
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/rtmpose_body2d) 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
 
@@ -27,25 +27,25 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | 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/rtmpose_body2d/releases/v0.47.0/rtmpose_body2d-onnx-float.zip)
31
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.47.0/rtmpose_body2d-onnx-w8a16.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.47.0/rtmpose_body2d-qnn_dlc-float.zip)
33
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.47.0/rtmpose_body2d-qnn_dlc-w8a16.zip)
34
- | 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/rtmpose_body2d/releases/v0.47.0/rtmpose_body2d-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[RTMPose-Body2d on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/rtmpose_body2d)**.
37
 
38
 
39
  ### Option 2: Export with Custom Configurations
40
 
41
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/rtmpose_body2d) 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 [RTMPose-Body2d on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/rtmpose_body2d) for usage instructions.
49
 
50
  ## Model Details
51
 
@@ -60,55 +60,55 @@ See our repository for [RTMPose-Body2d on GitHub](https://github.com/quic/ai-hub
60
  ## Performance Summary
61
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
62
  |---|---|---|---|---|---|---
63
- | RTMPose-Body2d | ONNX | float | Snapdragon® X Elite | 1.873 ms | 37 - 37 MB | NPU
64
- | RTMPose-Body2d | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.338 ms | 0 - 55 MB | NPU
65
- | RTMPose-Body2d | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.765 ms | 0 - 41 MB | NPU
66
- | RTMPose-Body2d | ONNX | float | Qualcomm® QCS9075 | 2.437 ms | 0 - 4 MB | NPU
67
- | RTMPose-Body2d | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.091 ms | 0 - 35 MB | NPU
68
- | RTMPose-Body2d | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.921 ms | 0 - 38 MB | NPU
69
- | RTMPose-Body2d | ONNX | float | Snapdragon® X2 Elite | 0.933 ms | 37 - 37 MB | NPU
70
- | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® X Elite | 1.91 ms | 19 - 19 MB | NPU
71
- | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.169 ms | 0 - 87 MB | NPU
72
- | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCS6490 | 175.399 ms | 53 - 56 MB | CPU
73
- | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.71 ms | 0 - 36 MB | NPU
74
- | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCS9075 | 1.904 ms | 0 - 3 MB | NPU
75
- | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCM6690 | 86.92 ms | 48 - 57 MB | CPU
76
- | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.868 ms | 0 - 61 MB | NPU
77
- | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 82.722 ms | 47 - 55 MB | CPU
78
- | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.736 ms | 0 - 61 MB | NPU
79
- | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® X2 Elite | 0.77 ms | 19 - 19 MB | NPU
80
- | RTMPose-Body2d | QNN_DLC | float | Snapdragon® X Elite | 1.84 ms | 1 - 1 MB | NPU
81
- | RTMPose-Body2d | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.331 ms | 0 - 57 MB | NPU
82
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.51 ms | 1 - 33 MB | NPU
83
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.738 ms | 1 - 2 MB | NPU
84
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® SA8775P | 2.429 ms | 1 - 36 MB | NPU
85
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS9075 | 2.433 ms | 1 - 3 MB | NPU
86
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.514 ms | 0 - 62 MB | NPU
87
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® SA7255P | 7.51 ms | 1 - 33 MB | NPU
88
- | RTMPose-Body2d | QNN_DLC | float | Qualcomm® SA8295P | 3.533 ms | 0 - 35 MB | NPU
89
- | RTMPose-Body2d | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.074 ms | 1 - 34 MB | NPU
90
- | RTMPose-Body2d | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.905 ms | 1 - 36 MB | NPU
91
- | RTMPose-Body2d | QNN_DLC | float | Snapdragon® X2 Elite | 1.087 ms | 1 - 1 MB | NPU
92
- | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.951 ms | 0 - 0 MB | NPU
93
- | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.18 ms | 0 - 75 MB | NPU
94
- | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 3.835 ms | 0 - 50 MB | NPU
95
- | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.732 ms | 0 - 2 MB | NPU
96
- | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® SA8775P | 2.04 ms | 0 - 52 MB | NPU
97
- | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.904 ms | 0 - 2 MB | NPU
98
- | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® SA7255P | 3.835 ms | 0 - 50 MB | NPU
99
- | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.89 ms | 0 - 53 MB | NPU
100
- | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.753 ms | 0 - 51 MB | NPU
101
- | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.974 ms | 0 - 0 MB | NPU
102
- | RTMPose-Body2d | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.327 ms | 0 - 91 MB | NPU
103
- | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.468 ms | 0 - 49 MB | NPU
104
  | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.755 ms | 0 - 2 MB | NPU
105
- | RTMPose-Body2d | TFLITE | float | Qualcomm® SA8775P | 2.455 ms | 0 - 51 MB | NPU
106
- | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS9075 | 2.425 ms | 0 - 40 MB | NPU
107
- | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.556 ms | 0 - 93 MB | NPU
108
- | RTMPose-Body2d | TFLITE | float | Qualcomm® SA7255P | 7.468 ms | 0 - 49 MB | NPU
109
- | RTMPose-Body2d | TFLITE | float | Qualcomm® SA8295P | 3.553 ms | 0 - 51 MB | NPU
110
- | RTMPose-Body2d | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.078 ms | 0 - 52 MB | NPU
111
- | RTMPose-Body2d | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.901 ms | 0 - 49 MB | NPU
112
 
113
  ## License
114
  * The license for the original implementation of RTMPose-Body2d can be found
 
14
  RTMPose is a machine learning model that detects human pose and returns a location and confidence for each of 133 joints.
15
 
16
  This is based on the implementation of RTMPose-Body2d found [here](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose).
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/main/qai_hub_models/models/rtmpose_body2d) 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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.48.0/rtmpose_body2d-onnx-float.zip)
31
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.48.0/rtmpose_body2d-onnx-w8a16.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.48.0/rtmpose_body2d-qnn_dlc-float.zip)
33
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/releases/v0.48.0/rtmpose_body2d-qnn_dlc-w8a16.zip)
34
+ | 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/rtmpose_body2d/releases/v0.48.0/rtmpose_body2d-tflite-float.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[RTMPose-Body2d on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/rtmpose_body2d)**.
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/main/qai_hub_models/models/rtmpose_body2d) 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 [RTMPose-Body2d on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/rtmpose_body2d) 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
+ | RTMPose-Body2d | ONNX | float | Snapdragon® X2 Elite | 0.923 ms | 37 - 37 MB | NPU
64
+ | RTMPose-Body2d | ONNX | float | Snapdragon® X Elite | 1.889 ms | 37 - 37 MB | NPU
65
+ | RTMPose-Body2d | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.334 ms | 0 - 62 MB | NPU
66
+ | RTMPose-Body2d | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.767 ms | 0 - 42 MB | NPU
67
+ | RTMPose-Body2d | ONNX | float | Qualcomm® QCS9075 | 2.457 ms | 1 - 4 MB | NPU
68
+ | RTMPose-Body2d | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.094 ms | 0 - 36 MB | NPU
69
+ | RTMPose-Body2d | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.924 ms | 0 - 39 MB | NPU
70
+ | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® X2 Elite | 0.769 ms | 19 - 19 MB | NPU
71
+ | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® X Elite | 1.934 ms | 19 - 19 MB | NPU
72
+ | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.168 ms | 0 - 91 MB | NPU
73
+ | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCS6490 | 178.11 ms | 49 - 53 MB | CPU
74
+ | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.705 ms | 0 - 22 MB | NPU
75
+ | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCS9075 | 1.91 ms | 0 - 3 MB | NPU
76
+ | RTMPose-Body2d | ONNX | w8a16 | Qualcomm® QCM6690 | 86.948 ms | 37 - 46 MB | CPU
77
+ | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.861 ms | 0 - 59 MB | NPU
78
+ | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 82.847 ms | 48 - 57 MB | CPU
79
+ | RTMPose-Body2d | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.737 ms | 0 - 60 MB | NPU
80
+ | RTMPose-Body2d | QNN_DLC | float | Snapdragon® X2 Elite | 1.103 ms | 1 - 1 MB | NPU
81
+ | RTMPose-Body2d | QNN_DLC | float | Snapdragon® X Elite | 1.857 ms | 1 - 1 MB | NPU
82
+ | RTMPose-Body2d | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.328 ms | 0 - 58 MB | NPU
83
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.532 ms | 1 - 33 MB | NPU
84
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.737 ms | 1 - 2 MB | NPU
85
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® SA8775P | 2.432 ms | 1 - 35 MB | NPU
86
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS9075 | 2.412 ms | 1 - 3 MB | NPU
87
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 3.539 ms | 0 - 63 MB | NPU
88
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® SA7255P | 7.532 ms | 1 - 33 MB | NPU
89
+ | RTMPose-Body2d | QNN_DLC | float | Qualcomm® SA8295P | 3.526 ms | 0 - 35 MB | NPU
90
+ | RTMPose-Body2d | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.075 ms | 0 - 35 MB | NPU
91
+ | RTMPose-Body2d | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.907 ms | 1 - 35 MB | NPU
92
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.998 ms | 0 - 0 MB | NPU
93
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.941 ms | 0 - 0 MB | NPU
94
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.185 ms | 0 - 80 MB | NPU
95
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 3.882 ms | 0 - 49 MB | NPU
96
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.734 ms | 0 - 2 MB | NPU
97
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® SA8775P | 2.052 ms | 0 - 52 MB | NPU
98
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.899 ms | 0 - 2 MB | NPU
99
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Qualcomm® SA7255P | 3.882 ms | 0 - 49 MB | NPU
100
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.892 ms | 0 - 50 MB | NPU
101
+ | RTMPose-Body2d | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.757 ms | 0 - 51 MB | NPU
102
+ | RTMPose-Body2d | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.326 ms | 0 - 90 MB | NPU
103
+ | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.492 ms | 0 - 49 MB | NPU
104
  | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.755 ms | 0 - 2 MB | NPU
105
+ | RTMPose-Body2d | TFLITE | float | Qualcomm® SA8775P | 2.419 ms | 0 - 51 MB | NPU
106
+ | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS9075 | 2.415 ms | 0 - 40 MB | NPU
107
+ | RTMPose-Body2d | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 3.52 ms | 0 - 97 MB | NPU
108
+ | RTMPose-Body2d | TFLITE | float | Qualcomm® SA7255P | 7.492 ms | 0 - 49 MB | NPU
109
+ | RTMPose-Body2d | TFLITE | float | Qualcomm® SA8295P | 3.563 ms | 0 - 51 MB | NPU
110
+ | RTMPose-Body2d | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.076 ms | 0 - 48 MB | NPU
111
+ | RTMPose-Body2d | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.9 ms | 0 - 50 MB | NPU
112
 
113
  ## License
114
  * The license for the original implementation of RTMPose-Body2d can be found