Hugging Face's logo

qualcomm
/
Posenet-Mobilenet

Keypoint Detection
PyTorch
TF Lite
ONNX
android
Model card Files Community
qaihm-bot commited on
Commit
5ab8d79
·
verified ·
1 Parent(s): 2fd0c58

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -29
README.md CHANGED
@@ -34,39 +34,39 @@ 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
- | Posenet-Mobilenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.382 ms | 0 - 32 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
38
- | Posenet-Mobilenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.46 ms | 0 - 12 MB | FP16 | NPU | [Posenet-Mobilenet.so](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.so) |
39
- | Posenet-Mobilenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.945 ms | 0 - 27 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
40
- | Posenet-Mobilenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.964 ms | 0 - 23 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
41
- | Posenet-Mobilenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.016 ms | 0 - 23 MB | FP16 | NPU | [Posenet-Mobilenet.so](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.so) |
42
- | Posenet-Mobilenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.291 ms | 0 - 23 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
43
- | Posenet-Mobilenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.962 ms | 0 - 21 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
44
- | Posenet-Mobilenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.012 ms | 0 - 20 MB | FP16 | NPU | Use Export Script |
45
- | Posenet-Mobilenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.073 ms | 0 - 22 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
46
- | Posenet-Mobilenet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.383 ms | 0 - 33 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
47
- | Posenet-Mobilenet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.406 ms | 2 - 5 MB | FP16 | NPU | Use Export Script |
48
- | Posenet-Mobilenet | SA7255P ADP | SA7255P | TFLITE | 53.849 ms | 0 - 13 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
49
- | Posenet-Mobilenet | SA7255P ADP | SA7255P | QNN | 54.045 ms | 2 - 11 MB | FP16 | NPU | Use Export Script |
50
- | Posenet-Mobilenet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.392 ms | 0 - 32 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
51
- | Posenet-Mobilenet | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.411 ms | 2 - 4 MB | FP16 | NPU | Use Export Script |
52
- | Posenet-Mobilenet | SA8295P ADP | SA8295P | TFLITE | 2.78 ms | 0 - 21 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
53
- | Posenet-Mobilenet | SA8295P ADP | SA8295P | QNN | 3.082 ms | 2 - 16 MB | FP16 | NPU | Use Export Script |
54
- | Posenet-Mobilenet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.38 ms | 0 - 12 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
55
- | Posenet-Mobilenet | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.409 ms | 2 - 4 MB | FP16 | NPU | Use Export Script |
56
- | Posenet-Mobilenet | SA8775P ADP | SA8775P | TFLITE | 2.884 ms | 0 - 14 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
57
- | Posenet-Mobilenet | SA8775P ADP | SA8775P | QNN | 3.028 ms | 2 - 11 MB | FP16 | NPU | Use Export Script |
58
- | Posenet-Mobilenet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.198 ms | 0 - 20 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
59
- | Posenet-Mobilenet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.307 ms | 2 - 26 MB | FP16 | NPU | Use Export Script |
60
- | Posenet-Mobilenet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.631 ms | 2 - 2 MB | FP16 | NPU | Use Export Script |
61
- | Posenet-Mobilenet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.217 ms | 8 - 8 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.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
72
  ```
@@ -123,7 +123,7 @@ Posenet-Mobilenet
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
  Estimated inference time (ms) : 1.4
126
- Estimated peak memory usage (MB): [0, 32]
127
  Total # Ops : 41
128
  Compute Unit(s) : NPU (41 ops)
129
  ```
@@ -150,7 +150,7 @@ from qai_hub_models.models.posenet_mobilenet import Model
150
  torch_model = Model.from_pretrained()
151
 
152
  # Device
153
- device = hub.Device("Samsung Galaxy S23")
154
 
155
  # Trace model
156
  input_shape = torch_model.get_input_spec()
@@ -242,7 +242,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
242
 
243
 
244
  ## License
245
- * The license for the original implementation of Posenet-Mobilenet can be found [here](https://github.com/rwightman/posenet-pytorch/blob/master/LICENSE.txt).
 
246
  * 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)
247
 
248
 
 
34
 
35
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  |---|---|---|---|---|---|---|---|---|
37
+ | Posenet-Mobilenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.391 ms | 0 - 23 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
38
+ | Posenet-Mobilenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.47 ms | 0 - 12 MB | FP16 | NPU | [Posenet-Mobilenet.so](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.so) |
39
+ | Posenet-Mobilenet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.893 ms | 0 - 28 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
40
+ | Posenet-Mobilenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.964 ms | 0 - 25 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
41
+ | Posenet-Mobilenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.021 ms | 0 - 29 MB | FP16 | NPU | [Posenet-Mobilenet.so](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.so) |
42
+ | Posenet-Mobilenet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.38 ms | 0 - 26 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
43
+ | Posenet-Mobilenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.971 ms | 0 - 23 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
44
+ | Posenet-Mobilenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.021 ms | 2 - 22 MB | FP16 | NPU | Use Export Script |
45
+ | Posenet-Mobilenet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.247 ms | 1 - 21 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
46
+ | Posenet-Mobilenet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.388 ms | 0 - 33 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
47
+ | Posenet-Mobilenet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.412 ms | 2 - 4 MB | FP16 | NPU | Use Export Script |
48
+ | Posenet-Mobilenet | SA7255P ADP | SA7255P | TFLITE | 53.701 ms | 0 - 14 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
49
+ | Posenet-Mobilenet | SA7255P ADP | SA7255P | QNN | 53.876 ms | 2 - 10 MB | FP16 | NPU | Use Export Script |
50
+ | Posenet-Mobilenet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.386 ms | 0 - 6 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
51
+ | Posenet-Mobilenet | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.4 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
52
+ | Posenet-Mobilenet | SA8295P ADP | SA8295P | TFLITE | 2.808 ms | 0 - 21 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
53
+ | Posenet-Mobilenet | SA8295P ADP | SA8295P | QNN | 3.22 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
54
+ | Posenet-Mobilenet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.388 ms | 0 - 33 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
55
+ | Posenet-Mobilenet | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.407 ms | 2 - 4 MB | FP16 | NPU | Use Export Script |
56
+ | Posenet-Mobilenet | SA8775P ADP | SA8775P | TFLITE | 2.888 ms | 0 - 13 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
57
+ | Posenet-Mobilenet | SA8775P ADP | SA8775P | QNN | 3.034 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
58
+ | Posenet-Mobilenet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.194 ms | 0 - 20 MB | FP16 | NPU | [Posenet-Mobilenet.tflite](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.tflite) |
59
+ | Posenet-Mobilenet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 2.272 ms | 2 - 21 MB | FP16 | NPU | Use Export Script |
60
+ | Posenet-Mobilenet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.586 ms | 2 - 2 MB | FP16 | NPU | Use Export Script |
61
+ | Posenet-Mobilenet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.226 ms | 8 - 8 MB | FP16 | NPU | [Posenet-Mobilenet.onnx](https://huggingface.co/qualcomm/Posenet-Mobilenet/blob/main/Posenet-Mobilenet.onnx) |
62
 
63
 
64
 
65
 
66
  ## Installation
67
 
 
68
 
69
+ Install the package via pip:
70
  ```bash
71
  pip install qai-hub-models
72
  ```
 
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
  Estimated inference time (ms) : 1.4
126
+ Estimated peak memory usage (MB): [0, 23]
127
  Total # Ops : 41
128
  Compute Unit(s) : NPU (41 ops)
129
  ```
 
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 Posenet-Mobilenet can be found
246
+ [here](https://github.com/rwightman/posenet-pytorch/blob/master/LICENSE.txt).
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