Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -36,39 +36,39 @@ More details on model performance across various devices, can be found
|
|
36 |
|
37 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
|---|---|---|---|---|---|---|---|---|
|
39 |
-
| Person-Foot-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.
|
40 |
-
| Person-Foot-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.
|
41 |
-
| Person-Foot-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 5.
|
42 |
-
| Person-Foot-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.
|
43 |
-
| Person-Foot-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.
|
44 |
-
| Person-Foot-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 3.
|
45 |
-
| Person-Foot-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE |
|
46 |
-
| Person-Foot-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.
|
47 |
-
| Person-Foot-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 3.
|
48 |
-
| Person-Foot-Detection | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.
|
49 |
-
| Person-Foot-Detection | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.
|
50 |
-
| Person-Foot-Detection | SA7255P ADP | SA7255P | TFLITE | 156.
|
51 |
-
| Person-Foot-Detection | SA7255P ADP | SA7255P | QNN | 156.
|
52 |
-
| Person-Foot-Detection | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.
|
53 |
-
| Person-Foot-Detection | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.
|
54 |
-
| Person-Foot-Detection | SA8295P ADP | SA8295P | TFLITE | 8.
|
55 |
-
| Person-Foot-Detection | SA8295P ADP | SA8295P | QNN | 8.
|
56 |
-
| Person-Foot-Detection | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.
|
57 |
-
| Person-Foot-Detection | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.
|
58 |
-
| Person-Foot-Detection | SA8775P ADP | SA8775P | TFLITE | 9.
|
59 |
-
| Person-Foot-Detection | SA8775P ADP | SA8775P | QNN | 9.
|
60 |
-
| Person-Foot-Detection | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE |
|
61 |
-
| Person-Foot-Detection | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.
|
62 |
-
| Person-Foot-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.
|
63 |
-
| Person-Foot-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.
|
64 |
|
65 |
|
66 |
|
67 |
|
68 |
## Installation
|
69 |
|
70 |
-
This model can be installed as a Python package via pip.
|
71 |
|
|
|
72 |
```bash
|
73 |
pip install qai-hub-models
|
74 |
```
|
@@ -124,8 +124,8 @@ Profiling Results
|
|
124 |
Person-Foot-Detection
|
125 |
Device : Samsung Galaxy S23 (13)
|
126 |
Runtime : TFLITE
|
127 |
-
Estimated inference time (ms) : 4.
|
128 |
-
Estimated peak memory usage (MB): [
|
129 |
Total # Ops : 135
|
130 |
Compute Unit(s) : NPU (135 ops)
|
131 |
```
|
@@ -152,7 +152,7 @@ from qai_hub_models.models.foot_track_net import Model
|
|
152 |
torch_model = Model.from_pretrained()
|
153 |
|
154 |
# Device
|
155 |
-
device = hub.Device("Samsung Galaxy
|
156 |
|
157 |
# Trace model
|
158 |
input_shape = torch_model.get_input_spec()
|
@@ -230,7 +230,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
|
|
230 |
|
231 |
|
232 |
## License
|
233 |
-
* The license for the original implementation of Person-Foot-Detection can be found
|
|
|
234 |
* 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)
|
235 |
|
236 |
|
|
|
36 |
|
37 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
38 |
|---|---|---|---|---|---|---|---|---|
|
39 |
+
| Person-Foot-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.837 ms | 5 - 16 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
40 |
+
| Person-Foot-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.069 ms | 4 - 11 MB | FP16 | NPU | [Person-Foot-Detection.so](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.so) |
|
41 |
+
| Person-Foot-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 5.169 ms | 12 - 35 MB | FP16 | NPU | [Person-Foot-Detection.onnx](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.onnx) |
|
42 |
+
| Person-Foot-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 3.354 ms | 3 - 29 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
43 |
+
| Person-Foot-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.509 ms | 0 - 26 MB | FP16 | NPU | [Person-Foot-Detection.so](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.so) |
|
44 |
+
| Person-Foot-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 3.778 ms | 9 - 46 MB | FP16 | NPU | [Person-Foot-Detection.onnx](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.onnx) |
|
45 |
+
| Person-Foot-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.427 ms | 4 - 30 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
46 |
+
| Person-Foot-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.037 ms | 4 - 31 MB | FP16 | NPU | Use Export Script |
|
47 |
+
| Person-Foot-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 3.554 ms | 2 - 34 MB | FP16 | NPU | [Person-Foot-Detection.onnx](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.onnx) |
|
48 |
+
| Person-Foot-Detection | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.87 ms | 5 - 15 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
49 |
+
| Person-Foot-Detection | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.903 ms | 3 - 7 MB | FP16 | NPU | Use Export Script |
|
50 |
+
| Person-Foot-Detection | SA7255P ADP | SA7255P | TFLITE | 156.772 ms | 5 - 22 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
51 |
+
| Person-Foot-Detection | SA7255P ADP | SA7255P | QNN | 156.798 ms | 2 - 12 MB | FP16 | NPU | Use Export Script |
|
52 |
+
| Person-Foot-Detection | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.785 ms | 5 - 17 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
53 |
+
| Person-Foot-Detection | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.931 ms | 4 - 6 MB | FP16 | NPU | Use Export Script |
|
54 |
+
| Person-Foot-Detection | SA8295P ADP | SA8295P | TFLITE | 8.324 ms | 5 - 29 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
55 |
+
| Person-Foot-Detection | SA8295P ADP | SA8295P | QNN | 8.515 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
|
56 |
+
| Person-Foot-Detection | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.775 ms | 0 - 10 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
57 |
+
| Person-Foot-Detection | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.904 ms | 4 - 6 MB | FP16 | NPU | Use Export Script |
|
58 |
+
| Person-Foot-Detection | SA8775P ADP | SA8775P | TFLITE | 9.237 ms | 5 - 22 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
59 |
+
| Person-Foot-Detection | SA8775P ADP | SA8775P | QNN | 9.543 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
|
60 |
+
| Person-Foot-Detection | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 6.978 ms | 5 - 29 MB | FP16 | NPU | [Person-Foot-Detection.tflite](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.tflite) |
|
61 |
+
| Person-Foot-Detection | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 7.375 ms | 4 - 31 MB | FP16 | NPU | Use Export Script |
|
62 |
+
| Person-Foot-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.364 ms | 4 - 4 MB | FP16 | NPU | Use Export Script |
|
63 |
+
| Person-Foot-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.491 ms | 17 - 17 MB | FP16 | NPU | [Person-Foot-Detection.onnx](https://huggingface.co/qualcomm/Person-Foot-Detection/blob/main/Person-Foot-Detection.onnx) |
|
64 |
|
65 |
|
66 |
|
67 |
|
68 |
## Installation
|
69 |
|
|
|
70 |
|
71 |
+
Install the package via pip:
|
72 |
```bash
|
73 |
pip install qai-hub-models
|
74 |
```
|
|
|
124 |
Person-Foot-Detection
|
125 |
Device : Samsung Galaxy S23 (13)
|
126 |
Runtime : TFLITE
|
127 |
+
Estimated inference time (ms) : 4.8
|
128 |
+
Estimated peak memory usage (MB): [5, 16]
|
129 |
Total # Ops : 135
|
130 |
Compute Unit(s) : NPU (135 ops)
|
131 |
```
|
|
|
152 |
torch_model = Model.from_pretrained()
|
153 |
|
154 |
# Device
|
155 |
+
device = hub.Device("Samsung Galaxy S24")
|
156 |
|
157 |
# Trace model
|
158 |
input_shape = torch_model.get_input_spec()
|
|
|
230 |
|
231 |
|
232 |
## License
|
233 |
+
* The license for the original implementation of Person-Foot-Detection can be found
|
234 |
+
[here](https://github.com/qcom-ai-hub/ai-hub-models-internal/blob/main/LICENSE).
|
235 |
* 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)
|
236 |
|
237 |
|