qaihm-bot commited on
Commit
a50d2ca
·
verified ·
1 Parent(s): 4bcaba0

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +6 -6
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 | 0.957 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeHandDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite)
38
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.214 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeHandLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite)
39
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.014 ms | 0 - 20 MB | FP16 | NPU | [MediaPipeHandDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.so)
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.284 ms | 0 - 49 MB | FP16 | NPU | [MediaPipeHandLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.so)
41
 
42
 
43
  ## Installation
@@ -98,14 +98,14 @@ python -m qai_hub_models.models.mediapipe_hand.export
98
  Profile Job summary of MediaPipeHandDetector
99
  --------------------------------------------------
100
  Device: Snapdragon X Elite CRD (11)
101
- Estimated Inference Time: 1.05 ms
102
  Estimated Peak Memory Range: 0.75-0.75 MB
103
  Compute Units: NPU (196) | Total (196)
104
 
105
  Profile Job summary of MediaPipeHandLandmarkDetector
106
  --------------------------------------------------
107
  Device: Snapdragon X Elite CRD (11)
108
- Estimated Inference Time: 1.46 ms
109
  Estimated Peak Memory Range: 0.75-0.75 MB
110
  Compute Units: NPU (209) | Total (209)
111
 
 
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 | 0.955 ms | 0 - 2 MB | FP16 | NPU | [MediaPipeHandDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite)
38
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.205 ms | 0 - 1 MB | FP16 | NPU | [MediaPipeHandLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite)
39
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.012 ms | 0 - 10 MB | FP16 | NPU | [MediaPipeHandDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.so)
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.299 ms | 1 - 9 MB | FP16 | NPU | [MediaPipeHandLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.so)
41
 
42
 
43
  ## Installation
 
98
  Profile Job summary of MediaPipeHandDetector
99
  --------------------------------------------------
100
  Device: Snapdragon X Elite CRD (11)
101
+ Estimated Inference Time: 1.06 ms
102
  Estimated Peak Memory Range: 0.75-0.75 MB
103
  Compute Units: NPU (196) | Total (196)
104
 
105
  Profile Job summary of MediaPipeHandLandmarkDetector
106
  --------------------------------------------------
107
  Device: Snapdragon X Elite CRD (11)
108
+ Estimated Inference Time: 1.47 ms
109
  Estimated Peak Memory Range: 0.75-0.75 MB
110
  Compute Units: NPU (209) | Total (209)
111