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
357412e
•
1 Parent(s): 31f94dc

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +12 -26
README.md CHANGED
@@ -34,10 +34,10 @@ More details on model performance across various devices, can be found
34
 
35
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  | ---|---|---|---|---|---|---|---|
37
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.785 ms | 0 - 1 MB | FP16 | NPU | [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite)
38
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.315 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite)
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.839 ms | 1 - 7 MB | FP16 | NPU | [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.39 ms | 0 - 90 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so)
41
 
42
 
43
  ## Installation
@@ -97,31 +97,17 @@ python -m qai_hub_models.models.mediapipe_face.export
97
  ```
98
  Profile Job summary of MediaPipeFaceDetector
99
  --------------------------------------------------
100
- Device: QCS8550 (Proxy) (12)
101
- Estimated Inference Time: 0.78 ms
102
- Estimated Peak Memory Range: 0.02-1.53 MB
103
- Compute Units: NPU (112) | Total (112)
104
 
105
  Profile Job summary of MediaPipeFaceLandmarkDetector
106
  --------------------------------------------------
107
- Device: QCS8550 (Proxy) (12)
108
- Estimated Inference Time: 0.33 ms
109
- Estimated Peak Memory Range: 0.02-1.79 MB
110
- Compute Units: NPU (101) | Total (101)
111
-
112
- Profile Job summary of MediaPipeFaceDetector
113
- --------------------------------------------------
114
- Device: QCS8550 (Proxy) (12)
115
- Estimated Inference Time: 0.84 ms
116
- Estimated Peak Memory Range: 0.78-5.89 MB
117
- Compute Units: NPU (148) | Total (148)
118
-
119
- Profile Job summary of MediaPipeFaceLandmarkDetector
120
- --------------------------------------------------
121
- Device: QCS8550 (Proxy) (12)
122
- Estimated Inference Time: 0.40 ms
123
- Estimated Peak Memory Range: 0.44-77.67 MB
124
- Compute Units: NPU (107) | Total (107)
125
 
126
 
127
  ```
 
34
 
35
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
36
  | ---|---|---|---|---|---|---|---|
37
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.815 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite)
38
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.325 ms | 0 - 4 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite)
39
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.843 ms | 1 - 7 MB | FP16 | NPU | [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so)
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.4 ms | 0 - 40 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so)
41
 
42
 
43
  ## Installation
 
97
  ```
98
  Profile Job summary of MediaPipeFaceDetector
99
  --------------------------------------------------
100
+ Device: Snapdragon X Elite CRD (11)
101
+ Estimated Inference Time: 0.93 ms
102
+ Estimated Peak Memory Range: 0.75-0.75 MB
103
+ Compute Units: NPU (147) | Total (147)
104
 
105
  Profile Job summary of MediaPipeFaceLandmarkDetector
106
  --------------------------------------------------
107
+ Device: Snapdragon X Elite CRD (11)
108
+ Estimated Inference Time: 0.55 ms
109
+ Estimated Peak Memory Range: 0.42-0.42 MB
110
+ Compute Units: NPU (106) | Total (106)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
 
112
 
113
  ```