qaihm-bot commited on
Commit
dc42abe
·
verified ·
1 Parent(s): d944231

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -32,8 +32,8 @@ More details on model performance across various devices, can be found
32
 
33
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
34
  | ---|---|---|---|---|---|---|---|
35
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.519 ms | 0 - 3 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite)
36
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.608 ms | 0 - 55 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so)
37
 
38
 
39
  ## Installation
@@ -95,16 +95,16 @@ python -m qai_hub_models.models.hrnet_pose.export
95
  Profile Job summary of HRNetPose
96
  --------------------------------------------------
97
  Device: Samsung Galaxy S24 (14)
98
- Estimated Inference Time: 1.88 ms
99
- Estimated Peak Memory Range: 0.02-98.61 MB
100
- Compute Units: NPU (515) | Total (515)
101
 
102
  Profile Job summary of HRNetPose
103
  --------------------------------------------------
104
  Device: Samsung Galaxy S24 (14)
105
- Estimated Inference Time: 1.92 ms
106
- Estimated Peak Memory Range: 0.58-169.97 MB
107
- Compute Units: NPU (747) | Total (747)
108
 
109
 
110
  ```
 
32
 
33
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
34
  | ---|---|---|---|---|---|---|---|
35
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 2.297 ms | 0 - 3 MB | FP16 | NPU | [HRNetPose.tflite](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.tflite)
36
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.295 ms | 0 - 56 MB | FP16 | NPU | [HRNetPose.so](https://huggingface.co/qualcomm/HRNetPose/blob/main/HRNetPose.so)
37
 
38
 
39
  ## Installation
 
95
  Profile Job summary of HRNetPose
96
  --------------------------------------------------
97
  Device: Samsung Galaxy S24 (14)
98
+ Estimated Inference Time: 1.72 ms
99
+ Estimated Peak Memory Range: 0.02-101.37 MB
100
+ Compute Units: NPU (514) | Total (514)
101
 
102
  Profile Job summary of HRNetPose
103
  --------------------------------------------------
104
  Device: Samsung Galaxy S24 (14)
105
+ Estimated Inference Time: 1.72 ms
106
+ Estimated Peak Memory Range: 0.58-169.46 MB
107
+ Compute Units: NPU (745) | Total (745)
108
 
109
 
110
  ```