Hugging Face's logo

qualcomm
/
MediaPipe-Face-Detection

Object Detection
PyTorch
TF Lite
real_time
android
Model card Files Community
qaihm-bot commited on
Commit
eb6a5fe
•
1 Parent(s): 87ef731

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +7 -7
README.md CHANGED
@@ -37,10 +37,10 @@ More details on model performance across various devices, can be found
37
 
38
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  | ---|---|---|---|---|---|---|---|
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.577 ms | 0 - 1 MB | FP16 | NPU | [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite)
41
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.207 ms | 0 - 13 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite)
42
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.638 ms | 0 - 5 MB | FP16 | NPU | [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so)
43
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.285 ms | 2 - 10 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so)
44
 
45
 
46
 
@@ -102,15 +102,15 @@ python -m qai_hub_models.models.mediapipe_face.export
102
  Profile Job summary of MediaPipeFaceDetector
103
  --------------------------------------------------
104
  Device: Snapdragon X Elite CRD (11)
105
- Estimated Inference Time: 0.76 ms
106
  Estimated Peak Memory Range: 0.75-0.75 MB
107
  Compute Units: NPU (146) | Total (146)
108
 
109
  Profile Job summary of MediaPipeFaceLandmarkDetector
110
  --------------------------------------------------
111
  Device: Snapdragon X Elite CRD (11)
112
- Estimated Inference Time: 0.37 ms
113
- Estimated Peak Memory Range: 0.42-0.42 MB
114
  Compute Units: NPU (105) | Total (105)
115
 
116
 
 
37
 
38
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  | ---|---|---|---|---|---|---|---|
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.547 ms | 0 - 1 MB | FP16 | NPU | [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite)
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.189 ms | 0 - 1 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.622 ms | 0 - 6 MB | FP16 | NPU | [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so)
43
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.286 ms | 0 - 3 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so)
44
 
45
 
46
 
 
102
  Profile Job summary of MediaPipeFaceDetector
103
  --------------------------------------------------
104
  Device: Snapdragon X Elite CRD (11)
105
+ Estimated Inference Time: 0.77 ms
106
  Estimated Peak Memory Range: 0.75-0.75 MB
107
  Compute Units: NPU (146) | Total (146)
108
 
109
  Profile Job summary of MediaPipeFaceLandmarkDetector
110
  --------------------------------------------------
111
  Device: Snapdragon X Elite CRD (11)
112
+ Estimated Inference Time: 0.46 ms
113
+ Estimated Peak Memory Range: 1.39-1.39 MB
114
  Compute Units: NPU (105) | Total (105)
115
 
116