Hugging Face's logo

qualcomm
/
HRNetPoseQuantized

Keypoint Detection
PyTorch
LiteRT
ONNX
quantized
android
Model card Files Community
qaihm-bot commited on
Commit
bb7abaa
·
verified ·
1 Parent(s): b6b47cd

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +35 -49
README.md CHANGED
@@ -35,38 +35,38 @@ More details on model performance across various devices, can be found
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
- | HRNetPoseQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.973 ms | 0 - 126 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
39
- | HRNetPoseQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.162 ms | 0 - 2 MB | INT8 | NPU | [HRNetPoseQuantized.so](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.so) |
40
- | HRNetPoseQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 3.353 ms | 0 - 74 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.onnx) |
41
- | HRNetPoseQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.724 ms | 0 - 90 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
42
- | HRNetPoseQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.841 ms | 0 - 18 MB | INT8 | NPU | [HRNetPoseQuantized.so](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.so) |
43
- | HRNetPoseQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.611 ms | 0 - 126 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.onnx) |
44
- | HRNetPoseQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.654 ms | 0 - 51 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
45
- | HRNetPoseQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.774 ms | 0 - 50 MB | INT8 | NPU | Use Export Script |
46
- | HRNetPoseQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 2.138 ms | 0 - 88 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.onnx) |
47
- | HRNetPoseQuantized | SA7255P ADP | SA7255P | TFLITE | 13.89 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
48
- | HRNetPoseQuantized | SA7255P ADP | SA7255P | QNN | 14.128 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
49
- | HRNetPoseQuantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.99 ms | 0 - 128 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
50
- | HRNetPoseQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.161 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
51
- | HRNetPoseQuantized | SA8295P ADP | SA8295P | TFLITE | 1.703 ms | 0 - 50 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
52
- | HRNetPoseQuantized | SA8295P ADP | SA8295P | QNN | 1.856 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
53
- | HRNetPoseQuantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.981 ms | 0 - 133 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
54
- | HRNetPoseQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.183 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
55
- | HRNetPoseQuantized | SA8775P ADP | SA8775P | TFLITE | 1.427 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
56
- | HRNetPoseQuantized | SA8775P ADP | SA8775P | QNN | 1.596 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
57
- | HRNetPoseQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 3.944 ms | 0 - 74 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
58
- | HRNetPoseQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 5.211 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
59
- | HRNetPoseQuantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 16.865 ms | 0 - 2 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
60
- | HRNetPoseQuantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 13.89 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
61
- | HRNetPoseQuantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 14.128 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
62
- | HRNetPoseQuantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.968 ms | 0 - 137 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
63
- | HRNetPoseQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.142 ms | 0 - 4 MB | INT8 | NPU | Use Export Script |
64
- | HRNetPoseQuantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 1.427 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
65
- | HRNetPoseQuantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 1.596 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
66
- | HRNetPoseQuantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.329 ms | 0 - 91 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) |
67
- | HRNetPoseQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.502 ms | 0 - 78 MB | INT8 | NPU | Use Export Script |
68
- | HRNetPoseQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.276 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
69
- | HRNetPoseQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.334 ms | 28 - 28 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.onnx) |
70
 
71
 
72
 
@@ -76,7 +76,7 @@ More details on model performance across various devices, can be found
76
 
77
  Install the package via pip:
78
  ```bash
79
- pip install "qai-hub-models[hrnet-pose-quantized]" torch==2.4.1 -f https://download.openmmlab.com/mmcv/dist/cpu/torch2.4/index.html -f https://qaihub-public-python-wheels.s3.us-west-2.amazonaws.com/index.html
80
  ```
81
 
82
 
@@ -127,11 +127,11 @@ python -m qai_hub_models.models.hrnet_pose_quantized.export
127
  ```
128
  Profiling Results
129
  ------------------------------------------------------------
130
- HRNetPoseQuantized
131
  Device : Samsung Galaxy S23 (13)
132
  Runtime : TFLITE
133
  Estimated inference time (ms) : 1.0
134
- Estimated peak memory usage (MB): [0, 126]
135
  Total # Ops : 518
136
  Compute Unit(s) : NPU (518 ops)
137
  ```
@@ -215,20 +215,6 @@ AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
215
 
216
 
217
 
218
- ## Run demo on a cloud-hosted device
219
-
220
- You can also run the demo on-device.
221
-
222
- ```bash
223
- python -m qai_hub_models.models.hrnet_pose_quantized.demo --on-device
224
- ```
225
-
226
- **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
227
- environment, please add the following to your cell (instead of the above).
228
- ```
229
- %run -m qai_hub_models.models.hrnet_pose_quantized.demo -- --on-device
230
- ```
231
-
232
 
233
  ## Deploying compiled model to Android
234
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.988 ms | 0 - 131 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
39
+ | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.131 ms | 0 - 3 MB | INT8 | NPU | [HRNetPoseQuantized.so](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.so) |
40
+ | HRNetPose | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 4.587 ms | 0 - 108 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.onnx) |
41
+ | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.715 ms | 0 - 90 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
42
+ | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.833 ms | 0 - 18 MB | INT8 | NPU | [HRNetPoseQuantized.so](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.so) |
43
+ | HRNetPose | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 3.383 ms | 0 - 163 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.onnx) |
44
+ | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.586 ms | 0 - 49 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
45
+ | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.693 ms | 0 - 52 MB | INT8 | NPU | Use Export Script |
46
+ | HRNetPose | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 3.935 ms | 0 - 120 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.onnx) |
47
+ | HRNetPose | SA7255P ADP | SA7255P | TFLITE | 13.956 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
48
+ | HRNetPose | SA7255P ADP | SA7255P | QNN | 14.2 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
49
+ | HRNetPose | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.98 ms | 0 - 131 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
50
+ | HRNetPose | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.14 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
51
+ | HRNetPose | SA8295P ADP | SA8295P | TFLITE | 1.714 ms | 0 - 50 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
52
+ | HRNetPose | SA8295P ADP | SA8295P | QNN | 1.871 ms | 0 - 18 MB | INT8 | NPU | Use Export Script |
53
+ | HRNetPose | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.978 ms | 0 - 134 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
54
+ | HRNetPose | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.149 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
55
+ | HRNetPose | SA8775P ADP | SA8775P | TFLITE | 1.44 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
56
+ | HRNetPose | SA8775P ADP | SA8775P | QNN | 1.585 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
57
+ | HRNetPose | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 3.842 ms | 0 - 75 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
58
+ | HRNetPose | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 5.281 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
59
+ | HRNetPose | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 17.054 ms | 0 - 2 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
60
+ | HRNetPose | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 13.956 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
61
+ | HRNetPose | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 14.2 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
62
+ | HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.963 ms | 0 - 132 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
63
+ | HRNetPose | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.134 ms | 0 - 4 MB | INT8 | NPU | Use Export Script |
64
+ | HRNetPose | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 1.44 ms | 0 - 48 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
65
+ | HRNetPose | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 1.585 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
66
+ | HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.366 ms | 0 - 94 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.tflite) |
67
+ | HRNetPose | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.506 ms | 0 - 82 MB | INT8 | NPU | Use Export Script |
68
+ | HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.303 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
69
+ | HRNetPose | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.826 ms | 26 - 26 MB | INT8 | NPU | [HRNetPoseQuantized.onnx](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPose.onnx) |
70
 
71
 
72
 
 
76
 
77
  Install the package via pip:
78
  ```bash
79
+ pip install "qai-hub-models[hrnet-pose-quantized]"
80
  ```
81
 
82
 
 
127
  ```
128
  Profiling Results
129
  ------------------------------------------------------------
130
+ HRNetPose
131
  Device : Samsung Galaxy S23 (13)
132
  Runtime : TFLITE
133
  Estimated inference time (ms) : 1.0
134
+ Estimated peak memory usage (MB): [0, 131]
135
  Total # Ops : 518
136
  Compute Unit(s) : NPU (518 ops)
137
  ```
 
215
 
216
 
217
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
218
 
219
  ## Deploying compiled model to Android
220