Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ tags:
 
 XLSR is designed for lightweight real-time upscaling of images.
 
-This model is an implementation of XLSR found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/xlsr).
+This model is an implementation of XLSR found [here]({source_repo}).
 This repository provides scripts to run XLSR on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/xlsr).
@@ -29,15 +29,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 22.0K
   - Model size: 92.7 KB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| XLSR | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 2.58 ms | 0 - 9 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.375 ms | 0 - 3 MB | FP16 | NPU | [XLSR.so](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.so) |
+| XLSR | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.509 ms | 0 - 2 MB | FP16 | NPU | [XLSR.onnx](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.onnx) |
+| XLSR | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 1.793 ms | 0 - 24 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 1.08 ms | 0 - 14 MB | FP16 | NPU | [XLSR.so](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.so) |
+| XLSR | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.084 ms | 0 - 23 MB | FP16 | NPU | [XLSR.onnx](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.onnx) |
+| XLSR | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 2.467 ms | 0 - 1 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.359 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| XLSR | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 2.551 ms | 0 - 88 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.344 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| XLSR | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 2.6 ms | 2 - 3 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | SA8775 (Proxy) | SA8775P Proxy | QNN | 1.364 ms | 0 - 1 MB | FP16 | NPU | Use Export Script |
+| XLSR | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 2.451 ms | 0 - 31 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.341 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| XLSR | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 3.255 ms | 6 - 30 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.541 ms | 0 - 14 MB | FP16 | NPU | Use Export Script |
+| XLSR | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 1.913 ms | 0 - 16 MB | FP16 | NPU | [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) |
+| XLSR | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.686 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
+| XLSR | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.057 ms | 0 - 15 MB | FP16 | NPU | [XLSR.onnx](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.onnx) |
+| XLSR | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.5 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
+| XLSR | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.516 ms | 9 - 9 MB | FP16 | NPU | [XLSR.onnx](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.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 | 2.483 ms | 0 - 69 MB | FP16 | NPU |  [XLSR.tflite](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.448 ms | 0 - 3 MB | FP16 | NPU |  [XLSR.so](https://huggingface.co/qualcomm/XLSR/blob/main/XLSR.so) 
-
-
 
 ## Installation
 
@@ -92,16 +109,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.xlsr.export
 ```
-
 ```
-Profile Job summary of XLSR
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 1.46 ms
-Estimated Peak Memory Range: 0.20-0.20 MB
-Compute Units: NPU (21) | Total (21)
-
-
+Profiling Results
+------------------------------------------------------------
+XLSR
+Device                          : Samsung Galaxy S23 (13) 
+Runtime                         : TFLITE                  
+Estimated inference time (ms)   : 2.6                     
+Estimated peak memory usage (MB): [0, 9]                  
+Total # Ops                     : 16                      
+Compute Unit(s)                 : NPU (13 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 XLSR's performance across various devices [here](https://aihub.qualcomm.com/models/xlsr).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of XLSR 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 XLSR 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
 * [Extremely Lightweight Quantization Robust Real-Time Single-Image Super Resolution for Mobile Devices](https://arxiv.org/abs/2105.10288)
 * [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/xlsr)
 
+
+
 ## 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:ai-hub-support@qti.qualcomm.com).