qaihm-bot commited on
Commit
9e8d913
1 Parent(s): bdd6053

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +7 -7
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 | 0.771 ms | 0 - 110 MB | FP16 | NPU | [MediaPipePoseDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.tflite)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.811 ms | 0 - 176 MB | FP16 | NPU | [MediaPipePoseLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.tflite)
41
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.836 ms | 0 - 104 MB | FP16 | NPU | [MediaPipePoseDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.so)
42
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.942 ms | 0 - 172 MB | FP16 | NPU | [MediaPipePoseLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.so)
43
 
44
 
45
 
@@ -101,14 +101,14 @@ python -m qai_hub_models.models.mediapipe_pose.export
101
  Profile Job summary of MediaPipePoseDetector
102
  --------------------------------------------------
103
  Device: Snapdragon X Elite CRD (11)
104
- Estimated Inference Time: 0.95 ms
105
- Estimated Peak Memory Range: 0.42-0.42 MB
106
  Compute Units: NPU (138) | Total (138)
107
 
108
  Profile Job summary of MediaPipePoseLandmarkDetector
109
  --------------------------------------------------
110
  Device: Snapdragon X Elite CRD (11)
111
- Estimated Inference Time: 1.13 ms
112
  Estimated Peak Memory Range: 0.75-0.75 MB
113
  Compute Units: NPU (290) | Total (290)
114
 
 
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 | 0.774 ms | 0 - 2 MB | FP16 | NPU | [MediaPipePoseDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.tflite)
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.832 ms | 0 - 2 MB | FP16 | NPU | [MediaPipePoseLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.tflite)
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.838 ms | 0 - 6 MB | FP16 | NPU | [MediaPipePoseDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.so)
42
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.915 ms | 0 - 38 MB | FP16 | NPU | [MediaPipePoseLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.so)
43
 
44
 
45
 
 
101
  Profile Job summary of MediaPipePoseDetector
102
  --------------------------------------------------
103
  Device: Snapdragon X Elite CRD (11)
104
+ Estimated Inference Time: 0.98 ms
105
+ Estimated Peak Memory Range: 0.45-0.45 MB
106
  Compute Units: NPU (138) | Total (138)
107
 
108
  Profile Job summary of MediaPipePoseLandmarkDetector
109
  --------------------------------------------------
110
  Device: Snapdragon X Elite CRD (11)
111
+ Estimated Inference Time: 1.12 ms
112
  Estimated Peak Memory Range: 0.75-0.75 MB
113
  Compute Units: NPU (290) | Total (290)
114