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: 513x513
   - Number of parameters: 5.80M
   - Model size: 22.2 MB
+  - Number of output classes: 21
 
 
 
 
 | 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 | 13.087 ms | 18 - 20 MB | FP16 | NPU |  [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 12.849 ms | 3 - 17 MB | FP16 | NPU |  [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 13.088 ms | 21 - 36 MB | FP16 | NPU |  [DeepLabV3-Plus-MobileNet.tflite](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 12.906 ms | 3 - 18 MB | FP16 | NPU |  [DeepLabV3-Plus-MobileNet.so](https://huggingface.co/qualcomm/DeepLabV3-Plus-MobileNet/blob/main/DeepLabV3-Plus-MobileNet.so) 
 
 
 
@@ -99,8 +100,8 @@ python -m qai_hub_models.models.deeplabv3_plus_mobilenet.export
 Profile Job summary of DeepLabV3-Plus-MobileNet
 --------------------------------------------------
 Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 12.92 ms
-Estimated Peak Memory Range: 3.04-17.74 MB
+Estimated Inference Time: 12.94 ms
+Estimated Peak Memory Range: 3.05-18.20 MB
 Compute Units: NPU (124) | Total (124)