Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ tags:
 
 QuickSRNet Small is designed for upscaling images on mobile platforms to sharpen in real-time.
 
-This model is an implementation of QuickSRNetSmall found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/quicksrnet).
+This model is an implementation of QuickSRNetSmall found [here]({source_repo}).
 This repository provides scripts to run QuickSRNetSmall on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/quicksrnetsmall).
@@ -29,15 +29,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 27.2K
   - Model size: 110 KB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| QuickSRNetSmall | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.34 ms | 0 - 8 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.061 ms | 0 - 7 MB | FP16 | NPU | [QuickSRNetSmall.so](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.so) |
+| QuickSRNetSmall | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.44 ms | 0 - 2 MB | FP16 | NPU | [QuickSRNetSmall.onnx](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.onnx) |
+| QuickSRNetSmall | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.83 ms | 0 - 20 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.638 ms | 0 - 12 MB | FP16 | NPU | [QuickSRNetSmall.so](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.so) |
+| QuickSRNetSmall | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.997 ms | 0 - 21 MB | FP16 | NPU | [QuickSRNetSmall.onnx](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.onnx) |
+| QuickSRNetSmall | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.36 ms | 0 - 1 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.863 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.413 ms | 0 - 22 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.877 ms | 0 - 4 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 1.361 ms | 0 - 1 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | SA8775 (Proxy) | SA8775P Proxy | QNN | 0.863 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.316 ms | 0 - 1 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.872 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.807 ms | 0 - 20 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.118 ms | 0 - 12 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.746 ms | 0 - 14 MB | FP16 | NPU | [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) |
+| QuickSRNetSmall | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.663 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.968 ms | 0 - 14 MB | FP16 | NPU | [QuickSRNetSmall.onnx](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.onnx) |
+| QuickSRNetSmall | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 0.942 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
+| QuickSRNetSmall | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.468 ms | 9 - 9 MB | FP16 | NPU | [QuickSRNetSmall.onnx](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.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 | 1.298 ms | 7 - 75 MB | FP16 | NPU |  [QuickSRNetSmall.tflite](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.01 ms | 0 - 62 MB | FP16 | NPU |  [QuickSRNetSmall.so](https://huggingface.co/qualcomm/QuickSRNetSmall/blob/main/QuickSRNetSmall.so) 
-
-
 
 ## Installation
 
@@ -92,16 +109,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.quicksrnetsmall.export
 ```
-
 ```
-Profile Job summary of QuickSRNetSmall
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 0.94 ms
-Estimated Peak Memory Range: 0.20-0.20 MB
-Compute Units: NPU (11) | Total (11)
-
-
+Profiling Results
+------------------------------------------------------------
+QuickSRNetSmall
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 1.3                    
+Estimated peak memory usage (MB): [0, 8]                 
+Total # Ops                     : 11                     
+Compute Unit(s)                 : NPU (8 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 QuickSRNetSmall's performance across various devices [here](https://aihub.qualcomm.com/models/quicksrnetsmall).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of QuickSRNetSmall 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 QuickSRNetSmall 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]).