Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ tags:
 
 QuickSRNet Large is designed for upscaling images on mobile platforms to sharpen in real-time.
 
-This model is an implementation of QuickSRNetLarge found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
+This model is an implementation of QuickSRNetLarge found [here]({source_repo}).
 This repository provides scripts to run QuickSRNetLarge on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/quicksrnetlarge).
@@ -29,15 +29,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 424K
   - Model size: 1.63 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| QuickSRNetLarge | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.476 ms | 0 - 1 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 2.107 ms | 0 - 3 MB | FP16 | NPU | [QuickSRNetLarge.so](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.so) |
+| QuickSRNetLarge | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 2.75 ms | 0 - 2 MB | FP16 | NPU | [QuickSRNetLarge.onnx](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.onnx) |
+| QuickSRNetLarge | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.933 ms | 0 - 32 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.901 ms | 0 - 11 MB | FP16 | NPU | [QuickSRNetLarge.so](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.so) |
+| QuickSRNetLarge | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 2.674 ms | 0 - 34 MB | FP16 | NPU | [QuickSRNetLarge.onnx](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.onnx) |
+| QuickSRNetLarge | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.4 ms | 0 - 2 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 2.183 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.443 ms | 0 - 14 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | SA8255 (Proxy) | SA8255P Proxy | QNN | 2.184 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 2.482 ms | 0 - 8 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | SA8775 (Proxy) | SA8775P Proxy | QNN | 2.209 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.448 ms | 0 - 6 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | SA8650 (Proxy) | SA8650P Proxy | QNN | 2.238 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 4.174 ms | 6 - 38 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 3.471 ms | 0 - 15 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.859 ms | 0 - 16 MB | FP16 | NPU | [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) |
+| QuickSRNetLarge | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 1.594 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.871 ms | 0 - 15 MB | FP16 | NPU | [QuickSRNetLarge.onnx](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.onnx) |
+| QuickSRNetLarge | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 2.388 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetLarge | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 2.684 ms | 8 - 8 MB | FP16 | NPU | [QuickSRNetLarge.onnx](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.onnx) |
 
 
 
-| 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 | 2.439 ms | 6 - 7 MB | FP16 | NPU |  [QuickSRNetLarge.tflite](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 2.106 ms | 2 - 6 MB | FP16 | NPU |  [QuickSRNetLarge.so](https://huggingface.co/qualcomm/QuickSRNetLarge/blob/main/QuickSRNetLarge.so) 
-
-
 
 ## Installation
 
@@ -92,16 +109,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.quicksrnetlarge.export
 ```
-
 ```
-Profile Job summary of QuickSRNetLarge
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 2.39 ms
-Estimated Peak Memory Range: 0.20-0.20 MB
-Compute Units: NPU (31) | Total (31)
-
-
+Profiling Results
+------------------------------------------------------------
+QuickSRNetLarge
+Device                          : Samsung Galaxy S23 (13) 
+Runtime                         : TFLITE                  
+Estimated inference time (ms)   : 2.5                     
+Estimated peak memory usage (MB): [0, 1]                  
+Total # Ops                     : 31                      
+Compute Unit(s)                 : NPU (28 ops) CPU (3 ops)
 ```
 
 
@@ -200,15 +217,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on QuickSRNetLarge's performance across various devices [here](https://aihub.qualcomm.com/models/quicksrnetlarge).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of QuickSRNetLarge can be found
-  [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
-- The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+* The license for the original implementation of QuickSRNetLarge can be found [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+
+
 
 ## References
 * [QuickSRNet: Plain Single-Image Super-Resolution Architecture for Faster Inference on Mobile Platforms](https://arxiv.org/abs/2303.04336)
 * [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet)
 
+
+
 ## Community
 * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).