Hugging Face's logo

qualcomm
/
FaceAttribNet

Object Detection
PyTorch
TF Lite
ONNX
real_time
android
Model card Files Community
bhushans commited on
Commit
0f9bfdf
•
1 Parent(s): 2f365d8

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +41 -24
README.md CHANGED
@@ -35,29 +35,30 @@ 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
- | FaceAttribNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.957 ms | 0 - 2 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
39
- | FaceAttribNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.041 ms | 0 - 8 MB | FP16 | NPU | [FaceAttribNet.so](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.so) |
40
- | FaceAttribNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.2 ms | 0 - 364 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
41
- | FaceAttribNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.71 ms | 0 - 110 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
42
- | FaceAttribNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.781 ms | 0 - 20 MB | FP16 | NPU | [FaceAttribNet.so](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.so) |
43
- | FaceAttribNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.907 ms | 0 - 113 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
44
  | FaceAttribNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.658 ms | 0 - 60 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
45
- | FaceAttribNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.702 ms | 0 - 21 MB | FP16 | NPU | Use Export Script |
46
- | FaceAttribNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.76 ms | 0 - 61 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
47
- | FaceAttribNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.947 ms | 0 - 1 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
48
- | FaceAttribNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.998 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
49
- | FaceAttribNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.977 ms | 0 - 2 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
50
- | FaceAttribNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.001 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
51
- | FaceAttribNet | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.978 ms | 0 - 2 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
52
- | FaceAttribNet | SA8775 (Proxy) | SA8775P Proxy | QNN | 0.998 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
53
- | FaceAttribNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.987 ms | 0 - 2 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
54
- | FaceAttribNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.996 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
55
- | FaceAttribNet | SA8295P ADP | SA8295P | TFLITE | 1.663 ms | 0 - 52 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
56
- | FaceAttribNet | SA8295P ADP | SA8295P | QNN | 1.742 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
57
- | FaceAttribNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.258 ms | 0 - 102 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
58
- | FaceAttribNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.356 ms | 0 - 21 MB | FP16 | NPU | Use Export Script |
59
- | FaceAttribNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.14 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
60
- | FaceAttribNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.213 ms | 27 - 27 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
 
61
 
62
 
63
 
@@ -122,7 +123,7 @@ FaceAttribNet
122
  Device : Samsung Galaxy S23 (13)
123
  Runtime : TFLITE
124
  Estimated inference time (ms) : 1.0
125
- Estimated peak memory usage (MB): [0, 2]
126
  Total # Ops : 161
127
  Compute Unit(s) : NPU (161 ops)
128
  ```
@@ -143,13 +144,29 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
143
  import torch
144
 
145
  import qai_hub as hub
146
- from qai_hub_models.models.face_attrib_net import
147
 
148
  # Load the model
 
149
 
150
  # Device
151
  device = hub.Device("Samsung Galaxy S23")
152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
153
 
154
  ```
155
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | FaceAttribNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.958 ms | 0 - 106 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
39
+ | FaceAttribNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.035 ms | 0 - 66 MB | FP16 | NPU | [FaceAttribNet.so](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.so) |
40
+ | FaceAttribNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.221 ms | 0 - 30 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
41
+ | FaceAttribNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.728 ms | 0 - 21 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
42
+ | FaceAttribNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.778 ms | 0 - 23 MB | FP16 | NPU | [FaceAttribNet.so](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.so) |
43
+ | FaceAttribNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.935 ms | 0 - 114 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
44
  | FaceAttribNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.658 ms | 0 - 60 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
45
+ | FaceAttribNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.651 ms | 0 - 21 MB | FP16 | NPU | Use Export Script |
46
+ | FaceAttribNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.866 ms | 0 - 62 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
47
+ | FaceAttribNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.949 ms | 0 - 106 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
48
+ | FaceAttribNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.984 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
49
+ | FaceAttribNet | SA7255P ADP | SA7255P | QNN | 30.142 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
50
+ | FaceAttribNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.967 ms | 0 - 106 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
51
+ | FaceAttribNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.006 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
52
+ | FaceAttribNet | SA8295P ADP | SA8295P | TFLITE | 1.666 ms | 0 - 17 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
53
+ | FaceAttribNet | SA8295P ADP | SA8295P | QNN | 1.902 ms | 0 - 6 MB | FP16 | NPU | Use Export Script |
54
+ | FaceAttribNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.958 ms | 0 - 106 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
55
+ | FaceAttribNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.004 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
56
+ | FaceAttribNet | SA8775P ADP | SA8775P | TFLITE | 1.779 ms | 0 - 20 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
57
+ | FaceAttribNet | SA8775P ADP | SA8775P | QNN | 1.958 ms | 0 - 5 MB | FP16 | NPU | Use Export Script |
58
+ | FaceAttribNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.276 ms | 0 - 22 MB | FP16 | NPU | [FaceAttribNet.tflite](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.tflite) |
59
+ | FaceAttribNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.34 ms | 0 - 22 MB | FP16 | NPU | Use Export Script |
60
+ | FaceAttribNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.12 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
61
+ | FaceAttribNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.241 ms | 27 - 27 MB | FP16 | NPU | [FaceAttribNet.onnx](https://huggingface.co/qualcomm/FaceAttribNet/blob/main/FaceAttribNet.onnx) |
62
 
63
 
64
 
 
123
  Device : Samsung Galaxy S23 (13)
124
  Runtime : TFLITE
125
  Estimated inference time (ms) : 1.0
126
+ Estimated peak memory usage (MB): [0, 106]
127
  Total # Ops : 161
128
  Compute Unit(s) : NPU (161 ops)
129
  ```
 
144
  import torch
145
 
146
  import qai_hub as hub
147
+ from qai_hub_models.models.face_attrib_net import Model
148
 
149
  # Load the 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()
157
+ sample_inputs = torch_model.sample_inputs()
158
+
159
+ pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
160
+
161
+ # Compile model on a specific device
162
+ compile_job = hub.submit_compile_job(
163
+ model=pt_model,
164
+ device=device,
165
+ input_specs=torch_model.get_input_spec(),
166
+ )
167
+
168
+ # Get target model to run on-device
169
+ target_model = compile_job.get_target_model()
170
 
171
  ```
172