qaihm-bot commited on
Commit
7e1f990
·
verified ·
1 Parent(s): 47c2e44

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +5 -12
README.md CHANGED
@@ -37,8 +37,8 @@ More details on model performance across various devices, can be found
37
 
38
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  | ---|---|---|---|---|---|---|---|
40
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.974 ms | 0 - 2 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite)
41
- | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.281 ms | 1 - 7 MB | FP16 | NPU | [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so)
42
 
43
 
44
  ## Installation
@@ -98,16 +98,9 @@ python -m qai_hub_models.models.mobilenet_v2.export
98
  ```
99
  Profile Job summary of MobileNet-v2
100
  --------------------------------------------------
101
- Device: QCS8550 (Proxy) (12)
102
- Estimated Inference Time: 0.96 ms
103
- Estimated Peak Memory Range: 0.05-1.54 MB
104
- Compute Units: NPU (72) | Total (72)
105
-
106
- Profile Job summary of MobileNet-v2
107
- --------------------------------------------------
108
- Device: QCS8550 (Proxy) (12)
109
- Estimated Inference Time: 1.26 ms
110
- Estimated Peak Memory Range: 0.59-122.96 MB
111
  Compute Units: NPU (105) | Total (105)
112
 
113
 
 
37
 
38
  | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
39
  | ---|---|---|---|---|---|---|---|
40
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.935 ms | 0 - 2 MB | FP16 | NPU | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite)
41
+ | Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.268 ms | 1 - 50 MB | FP16 | NPU | [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so)
42
 
43
 
44
  ## Installation
 
98
  ```
99
  Profile Job summary of MobileNet-v2
100
  --------------------------------------------------
101
+ Device: Snapdragon X Elite CRD (11)
102
+ Estimated Inference Time: 1.52 ms
103
+ Estimated Peak Memory Range: 0.57-0.57 MB
 
 
 
 
 
 
 
104
  Compute Units: NPU (105) | Total (105)
105
 
106