Hugging Face's logo

qualcomm
/
PPE-Detection

Object Detection
PyTorch
LiteRT
ONNX
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
a8a8d2f
·
verified ·
1 Parent(s): 0ed4ff7

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +30 -29
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
- | PPE-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.678 ms | 0 - 80 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
40
- | PPE-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.741 ms | 0 - 60 MB | FP16 | NPU | [PPE-Detection.so](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.so) |
41
- | PPE-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.099 ms | 0 - 55 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
42
- | PPE-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.49 ms | 0 - 23 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
43
- | PPE-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.544 ms | 1 - 24 MB | FP16 | NPU | [PPE-Detection.so](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.so) |
44
- | PPE-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.825 ms | 0 - 28 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
45
- | PPE-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.486 ms | 0 - 17 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
46
- | PPE-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.447 ms | 0 - 20 MB | FP16 | NPU | Use Export Script |
47
- | PPE-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.852 ms | 0 - 21 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
48
- | PPE-Detection | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.682 ms | 0 - 80 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
49
- | PPE-Detection | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.737 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
50
- | PPE-Detection | SA7255P ADP | SA7255P | TFLITE | 29.056 ms | 0 - 14 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
51
- | PPE-Detection | SA7255P ADP | SA7255P | QNN | 29.325 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
52
- | PPE-Detection | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.682 ms | 0 - 79 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
53
- | PPE-Detection | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.767 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
54
- | PPE-Detection | SA8295P ADP | SA8295P | TFLITE | 1.828 ms | 0 - 17 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
55
- | PPE-Detection | SA8295P ADP | SA8295P | QNN | 2.674 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
- | PPE-Detection | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.684 ms | 0 - 79 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
57
- | PPE-Detection | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.732 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
58
- | PPE-Detection | SA8775P ADP | SA8775P | TFLITE | 1.547 ms | 0 - 14 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
59
- | PPE-Detection | SA8775P ADP | SA8775P | QNN | 1.759 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
60
- | PPE-Detection | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.413 ms | 0 - 20 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
61
- | PPE-Detection | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.476 ms | 1 - 17 MB | FP16 | NPU | Use Export Script |
62
- | PPE-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.855 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
63
- | PPE-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.178 ms | 14 - 14 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
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
  ```
@@ -125,7 +125,7 @@ PPE-Detection
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
  Estimated inference time (ms) : 0.7
128
- Estimated peak memory usage (MB): [0, 80]
129
  Total # Ops : 77
130
  Compute Unit(s) : NPU (77 ops)
131
  ```
@@ -152,7 +152,7 @@ from qai_hub_models.models.gear_guard_net import Model
152
  torch_model = Model.from_pretrained()
153
 
154
  # Device
155
- device = hub.Device("Samsung Galaxy S23")
156
 
157
  # Trace model
158
  input_shape = torch_model.get_input_spec()
@@ -244,7 +244,8 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
244
 
245
 
246
  ## License
247
- * The license for the original implementation of PPE-Detection can be found [here](https://github.com/qcom-ai-hub/ai-hub-models-internal/blob/main/LICENSE).
 
248
  * 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)
249
 
250
 
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | PPE-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.679 ms | 0 - 69 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
40
+ | PPE-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.756 ms | 0 - 50 MB | FP16 | NPU | [PPE-Detection.so](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.so) |
41
+ | PPE-Detection | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.089 ms | 0 - 41 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
42
+ | PPE-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.496 ms | 0 - 23 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
43
+ | PPE-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.541 ms | 0 - 24 MB | FP16 | NPU | [PPE-Detection.so](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.so) |
44
+ | PPE-Detection | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.827 ms | 0 - 28 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
45
+ | PPE-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.483 ms | 0 - 21 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
46
+ | PPE-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.533 ms | 1 - 21 MB | FP16 | NPU | Use Export Script |
47
+ | PPE-Detection | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.856 ms | 1 - 20 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.onnx) |
48
+ | PPE-Detection | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.686 ms | 0 - 70 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
49
+ | PPE-Detection | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.738 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
50
+ | PPE-Detection | SA7255P ADP | SA7255P | TFLITE | 28.901 ms | 0 - 14 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
51
+ | PPE-Detection | SA7255P ADP | SA7255P | QNN | 29.156 ms | 1 - 10 MB | FP16 | NPU | Use Export Script |
52
+ | PPE-Detection | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.681 ms | 0 - 69 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
53
+ | PPE-Detection | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.737 ms | 1 - 3 MB | FP16 | NPU | Use Export Script |
54
+ | PPE-Detection | SA8295P ADP | SA8295P | TFLITE | 1.806 ms | 0 - 18 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
55
+ | PPE-Detection | SA8295P ADP | SA8295P | QNN | 2.069 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
56
+ | PPE-Detection | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.687 ms | 0 - 80 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
57
+ | PPE-Detection | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.736 ms | 1 - 4 MB | FP16 | NPU | Use Export Script |
58
+ | PPE-Detection | SA8775P ADP | SA8775P | TFLITE | 1.557 ms | 0 - 14 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
59
+ | PPE-Detection | SA8775P ADP | SA8775P | QNN | 1.797 ms | 1 - 11 MB | FP16 | NPU | Use Export Script |
60
+ | PPE-Detection | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.422 ms | 0 - 17 MB | FP16 | NPU | [PPE-Detection.tflite](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-Detection.tflite) |
61
+ | PPE-Detection | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.476 ms | 1 - 18 MB | FP16 | NPU | Use Export Script |
62
+ | PPE-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.847 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
63
+ | PPE-Detection | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.138 ms | 14 - 14 MB | FP16 | NPU | [PPE-Detection.onnx](https://huggingface.co/qualcomm/PPE-Detection/blob/main/PPE-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
  ```
 
125
  Device : Samsung Galaxy S23 (13)
126
  Runtime : TFLITE
127
  Estimated inference time (ms) : 0.7
128
+ Estimated peak memory usage (MB): [0, 69]
129
  Total # Ops : 77
130
  Compute Unit(s) : NPU (77 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()
 
244
 
245
 
246
  ## License
247
+ * The license for the original implementation of PPE-Detection can be found
248
+ [here](https://github.com/qcom-ai-hub/ai-hub-models-internal/blob/main/LICENSE).
249
  * 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)
250
 
251