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
f1f87a7
•
1 Parent(s): ba52278

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -6
README.md CHANGED
@@ -36,10 +36,10 @@ More details on model performance across various devices, can be found
36
 
37
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  | ---|---|---|---|---|---|---|---|
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.781 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.318 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite)
41
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.835 ms | 0 - 97 MB | FP16 | NPU | [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so)
42
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.391 ms | 0 - 94 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so)
43
 
44
 
45
 
@@ -101,7 +101,7 @@ python -m qai_hub_models.models.mediapipe_face.export
101
  Profile Job summary of MediaPipeFaceDetector
102
  --------------------------------------------------
103
  Device: Snapdragon X Elite CRD (11)
104
- Estimated Inference Time: 0.93 ms
105
  Estimated Peak Memory Range: 0.75-0.75 MB
106
  Compute Units: NPU (147) | Total (147)
107
 
@@ -135,7 +135,6 @@ from qai_hub_models.models.mediapipe_face import Model
135
 
136
  # Load the model
137
  torch_model = Model.from_pretrained()
138
- torch_model.eval()
139
 
140
  # Device
141
  device = hub.Device("Samsung Galaxy S23")
 
36
 
37
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  | ---|---|---|---|---|---|---|---|
39
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.78 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeFaceDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.tflite)
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.304 ms | 0 - 1 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.tflite)
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.847 ms | 2 - 35 MB | FP16 | NPU | [MediaPipeFaceDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceDetector.so)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.39 ms | 0 - 91 MB | FP16 | NPU | [MediaPipeFaceLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Face-Detection/blob/main/MediaPipeFaceLandmarkDetector.so)
43
 
44
 
45
 
 
101
  Profile Job summary of MediaPipeFaceDetector
102
  --------------------------------------------------
103
  Device: Snapdragon X Elite CRD (11)
104
+ Estimated Inference Time: 0.97 ms
105
  Estimated Peak Memory Range: 0.75-0.75 MB
106
  Compute Units: NPU (147) | Total (147)
107
 
 
135
 
136
  # Load the model
137
  torch_model = Model.from_pretrained()
 
138
 
139
  # Device
140
  device = hub.Device("Samsung Galaxy S23")