Upload README.md with huggingface_hub

README.md

@@ -28,13 +28,14 @@ More details on model performance across various devices, can be found
   - Input resolution: 513x513
   - Number of parameters: 39.6M
   - Model size: 151 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 | 294.244 ms | 0 - 142 MB | FP16 | GPU |  [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 292.637 ms | 0 - 23 MB | FP16 | GPU |  [DeepLabV3-ResNet50.tflite](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.tflite) 
 
 
 
@@ -95,9 +96,9 @@ python -m qai_hub_models.models.deeplabv3_resnet50.export
 ```
 Profile Job summary of DeepLabV3-ResNet50
 --------------------------------------------------
-Device: SA8775 (Proxy) (13)
-Estimated Inference Time: 291.81 ms
-Estimated Peak Memory Range: 2.10-142.41 MB
+Device: QCS8550 (Proxy) (12)
+Estimated Inference Time: 291.45 ms
+Estimated Peak Memory Range: 2.10-142.83 MB
 Compute Units: GPU (95) | Total (95)