Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -38,8 +38,8 @@ More details on model performance across various devices, can be found
|
|
38 |
|
39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
| ---|---|---|---|---|---|---|---|
|
41 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 37.
|
42 |
-
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 31.
|
43 |
|
44 |
|
45 |
|
@@ -100,9 +100,9 @@ python -m qai_hub_models.models.swin_base.export
|
|
100 |
```
|
101 |
Profile Job summary of Swin-Base
|
102 |
--------------------------------------------------
|
103 |
-
Device:
|
104 |
-
Estimated Inference Time:
|
105 |
-
Estimated Peak Memory Range: 0.
|
106 |
Compute Units: NPU (1255) | Total (1255)
|
107 |
|
108 |
|
|
|
38 |
|
39 |
| Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
40 |
| ---|---|---|---|---|---|---|---|
|
41 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 37.973 ms | 0 - 3 MB | FP16 | NPU | [Swin-Base.tflite](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.tflite)
|
42 |
+
| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 31.954 ms | 0 - 43 MB | FP16 | NPU | [Swin-Base.so](https://huggingface.co/qualcomm/Swin-Base/blob/main/Swin-Base.so)
|
43 |
|
44 |
|
45 |
|
|
|
100 |
```
|
101 |
Profile Job summary of Swin-Base
|
102 |
--------------------------------------------------
|
103 |
+
Device: SA8255 (Proxy) (13)
|
104 |
+
Estimated Inference Time: 31.37 ms
|
105 |
+
Estimated Peak Memory Range: 0.05-42.23 MB
|
106 |
Compute Units: NPU (1255) | Total (1255)
|
107 |
|
108 |
|