Hugging Face's logo

qualcomm
/
Movenet

Keypoint Detection
PyTorch
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
032c2af
·
verified ·
1 Parent(s): f53bd29

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +29 -29
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: apache-2.0
4
  tags:
5
  - android
6
  pipeline_tag: keypoint-detection
@@ -25,35 +25,35 @@ More details on model performance across various devices, can be found
25
 
26
  ### Model Details
27
 
28
- - **Model Type:** Pose estimation
29
  - **Model Stats:**
30
  - Model checkpoint: None
31
  - Input resolution: 192x192
32
  - Number of parameters: 3.31M
33
  - Model size: 9.2 MB
34
 
35
- | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
- | Movenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 3.826 ms | 0 - 2 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
38
- | Movenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 19.874 ms | 13 - 15 MB | FP32 | CPU | [Movenet.so](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.so) |
39
- | Movenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 11.361 ms | 9 - 19 MB | FP32 | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
40
- | Movenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.418 ms | 0 - 19 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
41
- | Movenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 10.384 ms | 12 - 31 MB | FP32 | CPU | [Movenet.so](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.so) |
42
- | Movenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 10.23 ms | 6 - 28 MB | FP32 | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
43
- | Movenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.609 ms | 1 - 15 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
44
- | Movenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 9.063 ms | 18 - 32 MB | FP32 | CPU | Use Export Script |
45
- | Movenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.09 ms | 10 - 25 MB | FP32 | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
46
- | Movenet | SA7255P ADP | SA7255P | TFLITE | 7.624 ms | 1 - 10 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
47
- | Movenet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 3.798 ms | 0 - 2 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
48
- | Movenet | SA8295P ADP | SA8295P | TFLITE | 3.851 ms | 1 - 18 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
49
- | Movenet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 3.857 ms | 1 - 4 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
50
- | Movenet | SA8775P ADP | SA8775P | TFLITE | 6.388 ms | 1 - 10 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
51
- | Movenet | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 7.624 ms | 1 - 10 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
52
- | Movenet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 3.854 ms | 1 - 4 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
53
- | Movenet | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 6.388 ms | 1 - 10 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
54
- | Movenet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.701 ms | 1 - 21 MB | FP32 | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
55
- | Movenet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 21.999 ms | 13 - 30 MB | FP32 | CPU | Use Export Script |
56
- | Movenet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.142 ms | 18 - 18 MB | FP32 | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
57
 
58
 
59
 
@@ -115,12 +115,12 @@ python -m qai_hub_models.models.movenet.export
115
  Profiling Results
116
  ------------------------------------------------------------
117
  Movenet
118
- Device : Samsung Galaxy S23 (13)
119
- Runtime : TFLITE
120
- Estimated inference time (ms) : 3.8
121
- Estimated peak memory usage (MB): [0, 2]
122
- Total # Ops : 152
123
- Compute Unit(s) : CPU (152 ops)
124
  ```
125
 
126
 
 
1
  ---
2
  library_name: pytorch
3
+ license: other
4
  tags:
5
  - android
6
  pipeline_tag: keypoint-detection
 
25
 
26
  ### Model Details
27
 
28
+ - **Model Type:** Model_use_case.pose_estimation
29
  - **Model Stats:**
30
  - Model checkpoint: None
31
  - Input resolution: 192x192
32
  - Number of parameters: 3.31M
33
  - Model size: 9.2 MB
34
 
35
+ | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | Movenet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 6.258 ms | 1 - 10 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
38
+ | Movenet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 4.69 ms | 1 - 24 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
39
+ | Movenet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 24.014 ms | 13 - 36 MB | CPU | Use Export Script |
40
+ | Movenet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 3.765 ms | 0 - 2 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
41
+ | Movenet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 5.496 ms | 1 - 15 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
42
+ | Movenet | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 6.258 ms | 1 - 10 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
43
+ | Movenet | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 4.718 ms | 1 - 4 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
44
+ | Movenet | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 3.848 ms | 1 - 18 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
45
+ | Movenet | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 4.038 ms | 1 - 4 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
46
+ | Movenet | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 5.496 ms | 1 - 15 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
47
+ | Movenet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.565 ms | 1 - 4 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
48
+ | Movenet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 18.677 ms | 13 - 15 MB | CPU | Use Export Script |
49
+ | Movenet | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 10.683 ms | 7 - 18 MB | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
50
+ | Movenet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.437 ms | 0 - 19 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
51
+ | Movenet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 7.328 ms | 12 - 33 MB | CPU | Use Export Script |
52
+ | Movenet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 14.255 ms | 5 - 28 MB | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
53
+ | Movenet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.974 ms | 1 - 15 MB | CPU | [Movenet.tflite](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.tflite) |
54
+ | Movenet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 7.05 ms | 12 - 27 MB | CPU | Use Export Script |
55
+ | Movenet | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 8.358 ms | 8 - 23 MB | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
56
+ | Movenet | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.449 ms | 18 - 18 MB | CPU | [Movenet.onnx](https://huggingface.co/qualcomm/Movenet/blob/main/Movenet.onnx) |
57
 
58
 
59
 
 
115
  Profiling Results
116
  ------------------------------------------------------------
117
  Movenet
118
+ Device : cs_8275 (ANDROID 14)
119
+ Runtime : TFLITE
120
+ Estimated inference time (ms) : 6.3
121
+ Estimated peak memory usage (MB): [1, 10]
122
+ Total # Ops : 152
123
+ Compute Unit(s) : npu (0 ops) gpu (0 ops) cpu (152 ops)
124
  ```
125
 
126