Upload README.md with huggingface_hub

README.md

@@ -25,15 +25,15 @@ More details on model performance across various devices, can be found
 - **Model Type:** Semantic segmentation
 - **Model Stats:**
   - Model checkpoint: COCO_WITH_VOC_LABELS_V1
-  - Input resolution: 224x224
+  - Input resolution: 513x513
   - Number of parameters: 39.6M
   - Model size: 151 MB
 
 
 | 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 | 58.164 ms | 0 - 164 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 | QNN Model Library | 145.136 ms | 1 - 8 MB | FP16 | GPU |  [DeepLabV3-ResNet50.so](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 290.847 ms | 0 - 214 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 | QNN Model Library | 810.711 ms | 3 - 11 MB | FP16 | GPU |  [DeepLabV3-ResNet50.so](https://huggingface.co/qualcomm/DeepLabV3-ResNet50/blob/main/DeepLabV3-ResNet50.so) 
 
 
 ## Installation
@@ -90,6 +90,16 @@ device. This script does the following:
 python -m qai_hub_models.models.deeplabv3_resnet50.export
 ```
 
+```
+Profile Job summary of DeepLabV3-ResNet50
+--------------------------------------------------
+Device: QCS8550 (Proxy) (12)
+Estimated Inference Time: 821.17 ms
+Estimated Peak Memory Range: 3.28-11.89 MB
+Compute Units: GPU (83) | Total (83)
+
+
+```
 ## How does this work?
 
 This [export script](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/DeepLabV3-ResNet50/export.py)
@@ -169,6 +179,20 @@ spot check the output with expected output.
 AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
 
 
+## Run demo on a cloud-hosted device
+
+You can also run the demo on-device.
+
+```bash
+python -m qai_hub_models.models.deeplabv3_resnet50.demo --on-device
+```
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.deeplabv3_resnet50.demo -- --on-device
+```
+
 
 ## Deploying compiled model to Android