Upload README.md with huggingface_hub

README.md

@@ -30,14 +30,15 @@ More details on model performance across various devices, can be found
   - Input resolution: 2048x1024
   - Number of parameters: 27.5M
   - Model size: 105 MB
+  - Number of output classes: 19
 
 
 
 
 | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 | ---|---|---|---|---|---|---|---|
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 23.277 ms | 0 - 2 MB | FP16 | NPU |  [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 24.928 ms | 24 - 45 MB | FP16 | NPU |  [FFNet-78S.so](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 23.829 ms | 2 - 5 MB | FP16 | NPU |  [FFNet-78S.tflite](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 23.711 ms | 26 - 46 MB | FP16 | NPU |  [FFNet-78S.so](https://huggingface.co/qualcomm/FFNet-78S/blob/main/FFNet-78S.so) 
 
 
 
@@ -100,8 +101,8 @@ python -m qai_hub_models.models.ffnet_78s.export
 Profile Job summary of FFNet-78S
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 23.86 ms
-Estimated Peak Memory Range: 24.07-45.49 MB
+Estimated Inference Time: 23.75 ms
+Estimated Peak Memory Range: 23.07-40.26 MB
 Compute Units: NPU (235) | Total (235)