Upload README.md with huggingface_hub

README.md

@@ -31,14 +31,15 @@ More details on model performance across various devices, can be found
   - Input resolution: 1024x512
   - Number of parameters: 26.8M
   - Model size: 102 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 | 7.397 ms | 1 - 3 MB | FP16 | NPU |  [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.65 ms | 6 - 34 MB | FP16 | NPU |  [FFNet-78S-LowRes.so](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 7.403 ms | 1 - 3 MB | FP16 | NPU |  [FFNet-78S-LowRes.tflite](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 7.697 ms | 6 - 25 MB | FP16 | NPU |  [FFNet-78S-LowRes.so](https://huggingface.co/qualcomm/FFNet-78S-LowRes/blob/main/FFNet-78S-LowRes.so) 
 
 
 
@@ -100,9 +101,9 @@ python -m qai_hub_models.models.ffnet_78s_lowres.export
 ```
 Profile Job summary of FFNet-78S-LowRes
 --------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 7.50 ms
-Estimated Peak Memory Range: 6.01-6.01 MB
+Device: SA8255 (Proxy) (13)
+Estimated Inference Time: 7.67 ms
+Estimated Peak Memory Range: 6.04-28.08 MB
 Compute Units: NPU (236) | Total (236)