Upload README.md with huggingface_hub

README.md

@@ -15,7 +15,7 @@ tags:
 
 LaMa-Dilated is a machine learning model that allows to erase and in-paint part of given input image.
 
-This model is an implementation of LaMa-Dilated found [here](https://github.com/advimman/lama).
+This model is an implementation of LaMa-Dilated found [here]({source_repo}).
 This repository provides scripts to run LaMa-Dilated on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/lama_dilated).
@@ -30,15 +30,28 @@ More details on model performance across various devices, can be found
   - Number of parameters: 45.6M
   - Model size: 174 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 74.881 ms | 3 - 132 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 70.655 ms | 2 - 43 MB | FP16 | NPU | [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) |
+| LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 55.681 ms | 3 - 261 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 52.685 ms | 4 - 91 MB | FP16 | NPU | [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) |
+| LaMa-Dilated | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 74.832 ms | 3 - 132 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 70.284 ms | 4 - 5 MB | FP16 | NPU | Use Export Script |
+| LaMa-Dilated | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 74.735 ms | 3 - 131 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | SA8255 (Proxy) | SA8255P Proxy | QNN | 70.519 ms | 4 - 5 MB | FP16 | NPU | Use Export Script |
+| LaMa-Dilated | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 74.677 ms | 7 - 297 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | SA8775 (Proxy) | SA8775P Proxy | QNN | 70.451 ms | 3 - 6 MB | FP16 | NPU | Use Export Script |
+| LaMa-Dilated | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 74.665 ms | 3 - 132 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | SA8650 (Proxy) | SA8650P Proxy | QNN | 70.62 ms | 4 - 5 MB | FP16 | NPU | Use Export Script |
+| LaMa-Dilated | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 105.083 ms | 3 - 161 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 100.5 ms | 4 - 44 MB | FP16 | NPU | Use Export Script |
+| LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 49.175 ms | 2 - 162 MB | FP16 | NPU | [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) |
+| LaMa-Dilated | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 45.997 ms | 2 - 88 MB | FP16 | NPU | Use Export Script |
+| LaMa-Dilated | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 71.913 ms | 4 - 4 MB | FP16 | NPU | Use Export Script |
 
 
 
-| 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 | 74.926 ms | 3 - 131 MB | FP16 | NPU |  [LaMa-Dilated.tflite](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 70.59 ms | 0 - 41 MB | FP16 | NPU |  [LaMa-Dilated.so](https://huggingface.co/qualcomm/LaMa-Dilated/blob/main/LaMa-Dilated.so) 
-
-
 
 ## Installation
 
@@ -94,16 +107,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.lama_dilated.export
 ```
-
 ```
-Profile Job summary of LaMa-Dilated
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 69.44 ms
-Estimated Peak Memory Range: 4.01-4.01 MB
-Compute Units: NPU (332) | Total (332)
-
-
+Profiling Results
+------------------------------------------------------------
+LaMa-Dilated
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 74.9                   
+Estimated peak memory usage (MB): [3, 132]               
+Total # Ops                     : 343                    
+Compute Unit(s)                 : NPU (343 ops)          
 ```
 
 
@@ -202,15 +215,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on LaMa-Dilated's performance across various devices [here](https://aihub.qualcomm.com/models/lama_dilated).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of LaMa-Dilated can be found
-  [here](https://github.com/advimman/lama/blob/main/LICENSE).
-- 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 LaMa-Dilated can be found [here](https://github.com/advimman/lama/blob/main/LICENSE).
+* 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
 * [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://arxiv.org/abs/2109.07161)
 * [Source Model Implementation](https://github.com/advimman/lama)
 
+
+
 ## 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).