Hugging Face's logo

qualcomm
/
HRNetPose

Keypoint Detection
PyTorch
TF Lite
ONNX
android
Model card Files Community
qaihm-bot commited on
Commit
afbc5b4
·
verified ·
1 Parent(s): 1c86c4b

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -30
README.md CHANGED
@@ -34,45 +34,44 @@ More details on model performance across various devices, can be found
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.81 ms | 0 - 59 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
38
- | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.91 ms | 1 - 26 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) |
39
- | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.068 ms | 0 - 167 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
40
- | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.04 ms | 0 - 38 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
41
- | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.132 ms | 1 - 41 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) |
42
- | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.196 ms | 0 - 72 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
43
- | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.965 ms | 0 - 38 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
44
- | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.036 ms | 1 - 36 MB | FP16 | NPU | Use Export Script |
45
- | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.162 ms | 0 - 47 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
46
- | HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.801 ms | 0 - 29 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
47
- | HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.728 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
48
- | HRNetPose | SA7255P ADP | SA7255P | TFLITE | 103.083 ms | 0 - 33 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
49
- | HRNetPose | SA7255P ADP | SA7255P | QNN | 103.103 ms | 1 - 9 MB | FP16 | NPU | Use Export Script |
50
- | HRNetPose | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.814 ms | 0 - 49 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
51
- | HRNetPose | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.77 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
52
- | HRNetPose | SA8295P ADP | SA8295P | TFLITE | 4.618 ms | 0 - 31 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
53
- | HRNetPose | SA8295P ADP | SA8295P | QNN | 5.06 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
54
- | HRNetPose | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.799 ms | 0 - 69 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
55
- | HRNetPose | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.742 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
56
- | HRNetPose | SA8775P ADP | SA8775P | TFLITE | 5.44 ms | 0 - 33 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
57
- | HRNetPose | SA8775P ADP | SA8775P | QNN | 5.447 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
58
- | HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 3.71 ms | 0 - 31 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
59
- | HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 3.902 ms | 1 - 32 MB | FP16 | NPU | Use Export Script |
60
- | HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.933 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
61
- | HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.931 ms | 56 - 56 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
62
 
63
 
64
 
65
 
66
  ## Installation
67
 
68
- This model can be installed as a Python package via pip.
69
 
 
70
  ```bash
71
- pip install "qai-hub-models[hrnet_pose]"
72
  ```
73
 
74
 
75
-
76
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
77
 
78
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
@@ -151,7 +150,7 @@ from qai_hub_models.models.hrnet_pose import Model
151
  torch_model = Model.from_pretrained()
152
 
153
  # Device
154
- device = hub.Device("Samsung Galaxy S23")
155
 
156
  # Trace model
157
  input_shape = torch_model.get_input_spec()
@@ -243,7 +242,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
243
 
244
 
245
  ## License
246
- * The license for the original implementation of HRNetPose can be found [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
 
247
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
248
 
249
 
 
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.808 ms | 0 - 59 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
38
+ | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.902 ms | 0 - 32 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) |
39
+ | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.906 ms | 0 - 137 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
40
+ | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.048 ms | 0 - 41 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
41
+ | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.129 ms | 0 - 35 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so) |
42
+ | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.211 ms | 0 - 70 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
43
+ | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.968 ms | 0 - 38 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
44
+ | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.036 ms | 1 - 37 MB | FP16 | NPU | Use Export Script |
45
+ | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.155 ms | 0 - 49 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
46
+ | HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.801 ms | 0 - 39 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
47
+ | HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.733 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
48
+ | HRNetPose | SA7255P ADP | SA7255P | TFLITE | 103.032 ms | 0 - 34 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
49
+ | HRNetPose | SA7255P ADP | SA7255P | QNN | 103.017 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
50
+ | HRNetPose | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.805 ms | 0 - 39 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
51
+ | HRNetPose | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.733 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
52
+ | HRNetPose | SA8295P ADP | SA8295P | TFLITE | 4.632 ms | 0 - 31 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
53
+ | HRNetPose | SA8295P ADP | SA8295P | QNN | 4.716 ms | 1 - 15 MB | FP16 | NPU | Use Export Script |
54
+ | HRNetPose | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.853 ms | 0 - 59 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
55
+ | HRNetPose | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.739 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
56
+ | HRNetPose | SA8775P ADP | SA8775P | TFLITE | 5.47 ms | 0 - 34 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
57
+ | HRNetPose | SA8775P ADP | SA8775P | QNN | 5.442 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
58
+ | HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 3.772 ms | 0 - 33 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite) |
59
+ | HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 3.786 ms | 1 - 29 MB | FP16 | NPU | Use Export Script |
60
+ | HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.957 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
61
+ | HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.937 ms | 57 - 57 MB | FP16 | NPU | [HRNetPose.onnx](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.onnx) |
62
 
63
 
64
 
65
 
66
  ## Installation
67
 
 
68
 
69
+ Install the package via pip:
70
  ```bash
71
+ pip install "qai-hub-models[hrnet-pose]"
72
  ```
73
 
74
 
 
75
  ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
76
 
77
  Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
 
150
  torch_model = Model.from_pretrained()
151
 
152
  # Device
153
+ device = hub.Device("Samsung Galaxy S24")
154
 
155
  # Trace model
156
  input_shape = torch_model.get_input_spec()
 
242
 
243
 
244
  ## License
245
+ * The license for the original implementation of HRNetPose can be found
246
+ [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
247
  * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
248
 
249