Upload README.md with huggingface_hub

README.md

@@ -14,7 +14,7 @@ tags:
 
 AOT-GAN is a machine learning model that allows to erase and in-paint part of given input image.
 
-This model is an implementation of AOT-GAN found [here](https://github.com/researchmm/AOT-GAN-for-Inpainting).
+This model is an implementation of AOT-GAN found [here]({source_repo}).
 This repository provides scripts to run AOT-GAN on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/aotgan).
@@ -29,15 +29,28 @@ More details on model performance across various devices, can be found
   - Number of parameters: 15.2M
   - Model size: 58.0 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| AOT-GAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 152.996 ms | 4 - 7 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 153.279 ms | 4 - 24 MB | FP16 | NPU | [AOT-GAN.so](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.so) |
+| AOT-GAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 120.324 ms | 3 - 215 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 139.029 ms | 4 - 61 MB | FP16 | NPU | [AOT-GAN.so](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.so) |
+| AOT-GAN | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 152.722 ms | 3 - 6 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 92.37 ms | 4 - 5 MB | FP16 | NPU | Use Export Script |
+| AOT-GAN | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 153.035 ms | 3 - 6 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | SA8255 (Proxy) | SA8255P Proxy | QNN | 92.574 ms | 4 - 6 MB | FP16 | NPU | Use Export Script |
+| AOT-GAN | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 152.757 ms | 3 - 5 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | SA8775 (Proxy) | SA8775P Proxy | QNN | 93.61 ms | 4 - 6 MB | FP16 | NPU | Use Export Script |
+| AOT-GAN | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 152.642 ms | 3 - 5 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | SA8650 (Proxy) | SA8650P Proxy | QNN | 92.421 ms | 4 - 5 MB | FP16 | NPU | Use Export Script |
+| AOT-GAN | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 193.915 ms | 3 - 187 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 195.48 ms | 1 - 47 MB | FP16 | NPU | Use Export Script |
+| AOT-GAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 118.959 ms | 3 - 86 MB | FP16 | NPU | [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) |
+| AOT-GAN | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 118.56 ms | 3 - 65 MB | FP16 | NPU | Use Export Script |
+| AOT-GAN | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 96.258 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 | 153.234 ms | 3 - 5 MB | FP16 | NPU |  [AOT-GAN.tflite](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 153.843 ms | 4 - 22 MB | FP16 | NPU |  [AOT-GAN.so](https://huggingface.co/qualcomm/AOT-GAN/blob/main/AOT-GAN.so) 
-
-
 
 ## Installation
 
@@ -92,16 +105,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.aotgan.export
 ```
-
 ```
-Profile Job summary of AOT-GAN
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 96.41 ms
-Estimated Peak Memory Range: 4.01-4.01 MB
-Compute Units: NPU (274) | Total (274)
-
-
+Profiling Results
+------------------------------------------------------------
+AOT-GAN
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 153.0                  
+Estimated peak memory usage (MB): [4, 7]                 
+Total # Ops                     : 235                    
+Compute Unit(s)                 : NPU (235 ops)          
 ```
 
 
@@ -200,15 +213,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on AOT-GAN's performance across various devices [here](https://aihub.qualcomm.com/models/aotgan).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of AOT-GAN can be found
-  [here](https://github.com/taki0112/AttnGAN-Tensorflow/blob/master/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 AOT-GAN can be found [here](https://github.com/taki0112/AttnGAN-Tensorflow/blob/master/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
 * [Aggregated Contextual Transformations for High-Resolution Image Inpainting](https://arxiv.org/abs/2104.01431)
 * [Source Model Implementation](https://github.com/researchmm/AOT-GAN-for-Inpainting)
 
+
+
 ## 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]).