Upload README.md with huggingface_hub

README.md

@@ -35,6 +35,20 @@ More details on model performance across various devices, can be found
 
 | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
+| ResNet-3D | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 21.453 ms | 29 - 921 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 16.315 ms | 0 - 207 MB | FP16 | NPU | [ResNet-3D.onnx](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.onnx) |
+| ResNet-3D | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 15.639 ms | 27 - 62 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 12.253 ms | 2 - 50 MB | FP16 | NPU | [ResNet-3D.onnx](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.onnx) |
+| ResNet-3D | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 15.569 ms | 28 - 61 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 10.272 ms | 2 - 56 MB | FP16 | NPU | [ResNet-3D.onnx](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.onnx) |
+| ResNet-3D | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 20.94 ms | 29 - 921 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | SA7255P ADP | SA7255P | TFLITE | 726.595 ms | 29 - 58 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 21.278 ms | 29 - 922 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | SA8295P ADP | SA8295P | TFLITE | 36.899 ms | 29 - 61 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 21.413 ms | 29 - 921 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | SA8775P ADP | SA8775P | TFLITE | 41.373 ms | 29 - 57 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 35.552 ms | 29 - 59 MB | FP16 | NPU | [ResNet-3D.tflite](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.tflite) |
+| ResNet-3D | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 18.051 ms | 64 - 64 MB | FP16 | NPU | [ResNet-3D.onnx](https://huggingface.co/qualcomm/ResNet-3D/blob/main/ResNet-3D.onnx) |
 
 
 
@@ -94,7 +108,16 @@ device. This script does the following:
 python -m qai_hub_models.models.resnet_3d.export
 ```
 ```
-Profiling Results```
+Profiling Results
+------------------------------------------------------------
+ResNet-3D
+Device                          : Samsung Galaxy S23 (13) 
+Runtime                         : TFLITE                  
+Estimated inference time (ms)   : 21.5                    
+Estimated peak memory usage (MB): [29, 921]               
+Total # Ops                     : 55                      
+Compute Unit(s)                 : NPU (50 ops) CPU (5 ops)
+```
 
 
 ## How does this work?