Hugging Face's logo

qualcomm
/
Lightweight-Face-Detection-Quantized

Object Detection
PyTorch
LiteRT
ONNX
real_time
quantized
android
Model card Files Community
1
qaihm-bot commited on
Commit
8ac85ff
·
verified ·
1 Parent(s): 144132f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +34 -34
README.md CHANGED
@@ -35,38 +35,38 @@ 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
- | Lightweight-Face-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.281 ms | 0 - 9 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
39
- | Lightweight-Face-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.331 ms | 0 - 2 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.so) |
40
- | Lightweight-Face-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.702 ms | 0 - 9 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
41
- | Lightweight-Face-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.199 ms | 0 - 23 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
42
- | Lightweight-Face-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.246 ms | 0 - 19 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.so) |
43
- | Lightweight-Face-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.481 ms | 0 - 27 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
44
- | Lightweight-Face-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.169 ms | 0 - 19 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
45
- | Lightweight-Face-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.243 ms | 0 - 20 MB | INT8 | NPU | Use Export Script |
46
- | Lightweight-Face-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.464 ms | 0 - 23 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
47
- | Lightweight-Face-Detection-Quantized | SA7255P ADP | SA7255P | TFLITE | 3.059 ms | 0 - 11 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
48
- | Lightweight-Face-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 3.315 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
49
- | Lightweight-Face-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.281 ms | 0 - 9 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
50
- | Lightweight-Face-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.336 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
51
- | Lightweight-Face-Detection-Quantized | SA8295P ADP | SA8295P | TFLITE | 0.666 ms | 0 - 15 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
52
- | Lightweight-Face-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 0.974 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
53
- | Lightweight-Face-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.279 ms | 0 - 9 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
54
- | Lightweight-Face-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.334 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
55
- | Lightweight-Face-Detection-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.599 ms | 0 - 12 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
56
- | Lightweight-Face-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 0.811 ms | 0 - 7 MB | INT8 | NPU | Use Export Script |
57
- | Lightweight-Face-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.796 ms | 0 - 18 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
58
- | Lightweight-Face-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 1.055 ms | 0 - 11 MB | INT8 | NPU | Use Export Script |
59
- | Lightweight-Face-Detection-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.482 ms | 0 - 3 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
60
- | Lightweight-Face-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 3.059 ms | 0 - 11 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
61
- | Lightweight-Face-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 3.315 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
62
- | Lightweight-Face-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.28 ms | 0 - 9 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
63
- | Lightweight-Face-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.34 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
64
- | Lightweight-Face-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.599 ms | 0 - 12 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
65
- | Lightweight-Face-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.811 ms | 0 - 7 MB | INT8 | NPU | Use Export Script |
66
- | Lightweight-Face-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.333 ms | 0 - 19 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
67
- | Lightweight-Face-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.404 ms | 0 - 20 MB | INT8 | NPU | Use Export Script |
68
- | Lightweight-Face-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.455 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
69
- | Lightweight-Face-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.849 ms | 2 - 2 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
70
 
71
 
72
 
@@ -131,7 +131,7 @@ Lightweight-Face-Detection-Quantized
131
  Device : Samsung Galaxy S23 (13)
132
  Runtime : TFLITE
133
  Estimated inference time (ms) : 0.3
134
- Estimated peak memory usage (MB): [0, 9]
135
  Total # Ops : 90
136
  Compute Unit(s) : NPU (90 ops)
137
  ```
@@ -175,7 +175,7 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
175
 
176
  ## License
177
  * The license for the original implementation of Lightweight-Face-Detection-Quantized can be found
178
- [here](https://github.com/qcom-ai-hub/ai-hub-models-internal/blob/main/LICENSE).
179
  * 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)
180
 
181
 
 
35
 
36
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
37
  |---|---|---|---|---|---|---|---|---|
38
+ | Lightweight-Face-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.28 ms | 0 - 10 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
39
+ | Lightweight-Face-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 0.273 ms | 0 - 2 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.so) |
40
+ | Lightweight-Face-Detection-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.415 ms | 0 - 8 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
41
+ | Lightweight-Face-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.204 ms | 2 - 28 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
42
+ | Lightweight-Face-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.195 ms | 0 - 21 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.so](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.so) |
43
+ | Lightweight-Face-Detection-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.274 ms | 0 - 25 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
44
+ | Lightweight-Face-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.204 ms | 0 - 25 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
45
+ | Lightweight-Face-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.166 ms | 0 - 21 MB | INT8 | NPU | Use Export Script |
46
+ | Lightweight-Face-Detection-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.321 ms | 0 - 22 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
47
+ | Lightweight-Face-Detection-Quantized | SA7255P ADP | SA7255P | TFLITE | 3.066 ms | 0 - 14 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
48
+ | Lightweight-Face-Detection-Quantized | SA7255P ADP | SA7255P | QNN | 2.97 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
49
+ | Lightweight-Face-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.28 ms | 0 - 10 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
50
+ | Lightweight-Face-Detection-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.27 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
51
+ | Lightweight-Face-Detection-Quantized | SA8295P ADP | SA8295P | TFLITE | 0.668 ms | 0 - 19 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
52
+ | Lightweight-Face-Detection-Quantized | SA8295P ADP | SA8295P | QNN | 0.636 ms | 0 - 14 MB | INT8 | NPU | Use Export Script |
53
+ | Lightweight-Face-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.281 ms | 0 - 10 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
54
+ | Lightweight-Face-Detection-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.27 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
55
+ | Lightweight-Face-Detection-Quantized | SA8775P ADP | SA8775P | TFLITE | 0.574 ms | 0 - 14 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
56
+ | Lightweight-Face-Detection-Quantized | SA8775P ADP | SA8775P | QNN | 0.539 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
57
+ | Lightweight-Face-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 0.843 ms | 0 - 19 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
58
+ | Lightweight-Face-Detection-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 0.907 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
59
+ | Lightweight-Face-Detection-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 6.335 ms | 0 - 2 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
60
+ | Lightweight-Face-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 3.066 ms | 0 - 14 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
61
+ | Lightweight-Face-Detection-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 2.97 ms | 0 - 8 MB | INT8 | NPU | Use Export Script |
62
+ | Lightweight-Face-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.28 ms | 0 - 4 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
63
+ | Lightweight-Face-Detection-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.269 ms | 0 - 4 MB | INT8 | NPU | Use Export Script |
64
+ | Lightweight-Face-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 0.574 ms | 0 - 14 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
65
+ | Lightweight-Face-Detection-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 0.539 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
66
+ | Lightweight-Face-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 0.355 ms | 0 - 26 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.tflite](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.tflite) |
67
+ | Lightweight-Face-Detection-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 0.327 ms | 0 - 22 MB | INT8 | NPU | Use Export Script |
68
+ | Lightweight-Face-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.357 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
69
+ | Lightweight-Face-Detection-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.397 ms | 0 - 0 MB | INT8 | NPU | [Lightweight-Face-Detection-Quantized.onnx](https://huggingface.co/qualcomm/Lightweight-Face-Detection-Quantized/blob/main/Lightweight-Face-Detection-Quantized.onnx) |
70
 
71
 
72
 
 
131
  Device : Samsung Galaxy S23 (13)
132
  Runtime : TFLITE
133
  Estimated inference time (ms) : 0.3
134
+ Estimated peak memory usage (MB): [0, 10]
135
  Total # Ops : 90
136
  Compute Unit(s) : NPU (90 ops)
137
  ```
 
175
 
176
  ## License
177
  * The license for the original implementation of Lightweight-Face-Detection-Quantized can be found
178
+ [here](https://github.com/quic/ai-hub-models/blob/main/LICENSE).
179
  * 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)
180
 
181