Upload README.md with huggingface_hub

README.md

@@ -17,7 +17,7 @@ tags:
 
 GoogLeNet 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 GoogLeNet found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.py).
+This model is an implementation of GoogLeNet found [here]({source_repo}).
 This repository provides scripts to run GoogLeNet on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/googlenet).
@@ -32,15 +32,32 @@ More details on model performance across various devices, can be found
   - Number of parameters: 6.62M
   - Model size: 25.3 MB
 
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.015 ms | 0 - 24 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.077 ms | 0 - 33 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) |
+| GoogLeNet | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.143 ms | 0 - 35 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
+| GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.743 ms | 0 - 50 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.787 ms | 0 - 15 MB | FP16 | NPU | [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) |
+| GoogLeNet | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.901 ms | 0 - 53 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
+| GoogLeNet | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.013 ms | 0 - 1 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 0.899 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.015 ms | 0 - 81 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | SA8255 (Proxy) | SA8255P Proxy | QNN | 0.904 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 1.012 ms | 0 - 1 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | SA8775 (Proxy) | SA8775P Proxy | QNN | 0.896 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.011 ms | 0 - 4 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | SA8650 (Proxy) | SA8650P Proxy | QNN | 0.897 ms | 1 - 2 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.501 ms | 0 - 51 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.577 ms | 1 - 20 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.674 ms | 0 - 19 MB | FP16 | NPU | [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) |
+| GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.719 ms | 0 - 11 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.846 ms | 0 - 20 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.onnx) |
+| GoogLeNet | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.06 ms | 1 - 1 MB | FP16 | NPU | Use Export Script |
+| GoogLeNet | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.334 ms | 14 - 14 MB | FP16 | NPU | [GoogLeNet.onnx](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.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 | 1.013 ms | 0 - 1 MB | FP16 | NPU |  [GoogLeNet.tflite](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.079 ms | 0 - 35 MB | FP16 | NPU |  [GoogLeNet.so](https://huggingface.co/qualcomm/GoogLeNet/blob/main/GoogLeNet.so) 
-
-
 
 ## Installation
 
@@ -95,16 +112,16 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.googlenet.export
 ```
-
 ```
-Profile Job summary of GoogLeNet
---------------------------------------------------
-Device: Snapdragon X Elite CRD (11)
-Estimated Inference Time: 1.04 ms
-Estimated Peak Memory Range: 0.57-0.57 MB
-Compute Units: NPU (143) | Total (143)
-
-
+Profiling Results
+------------------------------------------------------------
+GoogLeNet
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 1.0                    
+Estimated peak memory usage (MB): [0, 24]                
+Total # Ops                     : 84                     
+Compute Unit(s)                 : NPU (84 ops)           
 ```
 
 
@@ -203,15 +220,19 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 Get more details on GoogLeNet's performance across various devices [here](https://aihub.qualcomm.com/models/googlenet).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
+
 ## License
-- The license for the original implementation of GoogLeNet can be found
-  [here](https://github.com/pytorch/vision/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 GoogLeNet can be found [here](https://github.com/pytorch/vision/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
 * [Going Deeper with Convolutions](https://arxiv.org/abs/1409.4842)
 * [Source Model Implementation](https://github.com/pytorch/vision/blob/main/torchvision/models/googlenet.py)
 
+
+
 ## 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]).