Upload README.md with huggingface_hub

README.md

@@ -19,7 +19,7 @@ tags:
 
 MobileNetV2 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
 
-This model is an implementation of MobileNet-v2 found [here](https://github.com/tonylins/pytorch-mobilenet-v2/tree/master).
+This model is an implementation of MobileNet-v2 found [here]({source_repo}).
 This repository provides scripts to run MobileNet-v2 on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/mobilenet_v2).
@@ -34,15 +34,31 @@ More details on model performance across various devices, can be found
   - Number of parameters: 3.49M
   - Model size: 13.3 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Evaluation | Target Model
+|---|---|---|---|---|---|---|---|---|---|
+| MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.905 ms | 0 - 175 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.253 ms | 0 - 37 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 0.919 ms | 0 - 2 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.623 ms | 0 - 62 MB | FP16 | NPU | -- | [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) |
+| MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.862 ms | 1 - 15 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.678 ms | 0 - 66 MB | FP16 | NPU | -- | [MobileNet-v2.onnx](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.onnx) |
+| MobileNet-v2 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.902 ms | 0 - 1 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.906 ms | 0 - 8 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.188 ms | 1 - 2 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.901 ms | 0 - 2 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | SA8775 (Proxy) | SA8775P Proxy | QNN | 1.189 ms | 1 - 2 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.901 ms | 0 - 2 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.189 ms | 1 - 2 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.083 ms | 0 - 63 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.43 ms | 1 - 19 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.503 ms | 0 - 24 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.848 ms | 0 - 14 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.681 ms | 0 - 24 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.348 ms | 1 - 1 MB | FP16 | NPU | -- | -- |
+| MobileNet-v2 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 0.971 ms | 9 - 9 MB | FP16 | NPU | -- | -- |
 
 
 
-| 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 | 0.906 ms | 0 - 177 MB | FP16 | NPU |  [MobileNet-v2.tflite](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.253 ms | 0 - 49 MB | FP16 | NPU |  [MobileNet-v2.so](https://huggingface.co/qualcomm/MobileNet-v2/blob/main/MobileNet-v2.so) 
-
-
 
 ## Installation
 
@@ -97,16 +113,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.mobilenet_v2.export
 ```
-
 ```
-Profile Job summary of MobileNet-v2
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 1.38 ms
-Estimated Peak Memory Range: 0.57-0.57 MB
-Compute Units: NPU (105) | Total (105)
-
-
+Profiling Results
+------------------------------------------------------------
+MobileNet-v2
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 0.9                    
+Estimated peak memory usage (MB): [0, 175]               
+Total # Ops                     : 72                     
+Compute Unit(s)                 : NPU (72 ops)           
 ```
 
 
@@ -205,15 +221,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on MobileNet-v2's performance across various devices [here](https://aihub.qualcomm.com/models/mobilenet_v2).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of MobileNet-v2 can be found
-  [here](https://github.com/tonylins/pytorch-mobilenet-v2/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 MobileNet-v2 can be found [here](https://github.com/tonylins/pytorch-mobilenet-v2/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
 * [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://arxiv.org/abs/1801.04381)
 * [Source Model Implementation](https://github.com/tonylins/pytorch-mobilenet-v2/tree/master)
 
+
+
 ## 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]).