Upload README.md with huggingface_hub

README.md

@@ -1,25 +1,25 @@
 ---
 library_name: pytorch
 license: bsd-3-clause
-pipeline_tag: image-classification
 tags:
 - quantized
 - android
+pipeline_tag: image-classification
 
 ---
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/convnext_tiny_w8a16_quantized/web-assets/model_demo.png)
 
-# ConvNext-Tiny-w8a16-Quantized: Optimized for Mobile Deployment
+# ConvNext-Tiny-W8A16-Quantized: Optimized for Mobile Deployment
 ## Imagenet classifier and general purpose backbone
 
 
 ConvNextTiny 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 ConvNext-Tiny-w8a16-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
+This model is an implementation of ConvNext-Tiny-W8A16-Quantized found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/convnext.py).
 
 
-This repository provides scripts to run ConvNext-Tiny-w8a16-Quantized on Qualcomm® devices.
+This repository provides scripts to run ConvNext-Tiny-W8A16-Quantized on Qualcomm® devices.
 More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized).
 
@@ -36,17 +36,10 @@ More details on model performance across various devices, can be found
 
 | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| ConvNext-Tiny-w8a16-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 3.426 ms | 0 - 126 MB | INT8 | NPU | [ConvNext-Tiny-w8a16-Quantized.so](https://huggingface.co/qualcomm/ConvNext-Tiny-w8a16-Quantized/blob/main/ConvNext-Tiny-w8a16-Quantized.so) |
-| ConvNext-Tiny-w8a16-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.459 ms | 0 - 42 MB | INT8 | NPU | [ConvNext-Tiny-w8a16-Quantized.so](https://huggingface.co/qualcomm/ConvNext-Tiny-w8a16-Quantized/blob/main/ConvNext-Tiny-w8a16-Quantized.so) |
-| ConvNext-Tiny-w8a16-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 2.445 ms | 0 - 44 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 13.081 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 3.088 ms | 0 - 4 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 3.098 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | SA8295P ADP | SA8295P | QNN | 5.267 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 3.113 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | SA8775P ADP | SA8775P | QNN | 4.498 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 4.174 ms | 0 - 38 MB | INT8 | NPU | Use Export Script |
-| ConvNext-Tiny-w8a16-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 3.393 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
+| ConvNext-Tiny-W8A16-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 83.478 ms | 210 - 361 MB | INT8 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny-W8A16-Quantized.onnx) |
+| ConvNext-Tiny-W8A16-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 71.551 ms | 218 - 531 MB | INT8 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny-W8A16-Quantized.onnx) |
+| ConvNext-Tiny-W8A16-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 61.189 ms | 216 - 511 MB | INT8 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny-W8A16-Quantized.onnx) |
+| ConvNext-Tiny-W8A16-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 82.39 ms | 232 - 232 MB | INT8 | NPU | [ConvNext-Tiny-W8A16-Quantized.onnx](https://huggingface.co/qualcomm/ConvNext-Tiny-W8A16-Quantized/blob/main/ConvNext-Tiny-W8A16-Quantized.onnx) |
 
 
 
@@ -56,7 +49,7 @@ More details on model performance across various devices, can be found
 
 Install the package via pip:
 ```bash
-pip install "qai-hub-models[convnext-tiny-w8a16-quantized]"
+pip install qai-hub-models
 ```
 
 
@@ -107,15 +100,91 @@ python -m qai_hub_models.models.convnext_tiny_w8a16_quantized.export
 ```
 Profiling Results
 ------------------------------------------------------------
-ConvNext-Tiny-w8a16-Quantized
-Device                          : Samsung Galaxy S23 (13)
-Runtime                         : QNN                    
-Estimated inference time (ms)   : 3.4                    
-Estimated peak memory usage (MB): [0, 126]               
-Total # Ops                     : 215                    
-Compute Unit(s)                 : NPU (215 ops)          
+ConvNext-Tiny-W8A16-Quantized
+Device                          : Samsung Galaxy S23 (13)   
+Runtime                         : ONNX                      
+Estimated inference time (ms)   : 83.5                      
+Estimated peak memory usage (MB): [210, 361]                
+Total # Ops                     : 397                       
+Compute Unit(s)                 : NPU (357 ops) CPU (40 ops)
+```
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized/qai_hub_models/models/ConvNext-Tiny-W8A16-Quantized/export.py)
+leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
+on-device. Lets go through each step below in detail:
+
+Step 1: **Compile model for on-device deployment**
+
+To compile a PyTorch model for on-device deployment, we first trace the model
+in memory using the `jit.trace` and then call the `submit_compile_job` API.
+
+```python
+import torch
+
+import qai_hub as hub
+from qai_hub_models.models.convnext_tiny_w8a16_quantized import Model
+
+# Load the model
+torch_model = Model.from_pretrained()
+
+# Device
+device = hub.Device("Samsung Galaxy S24")
+
+# Trace model
+input_shape = torch_model.get_input_spec()
+sample_inputs = torch_model.sample_inputs()
+
+pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+
+# Compile model on a specific device
+compile_job = hub.submit_compile_job(
+    model=pt_model,
+    device=device,
+    input_specs=torch_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+target_model = compile_job.get_target_model()
+
+```
+
+
+Step 2: **Performance profiling on cloud-hosted device**
+
+After compiling models from step 1. Models can be profiled model on-device using the
+`target_model`. Note that this scripts runs the model on a device automatically
+provisioned in the cloud.  Once the job is submitted, you can navigate to a
+provided job URL to view a variety of on-device performance metrics.
+```python
+profile_job = hub.submit_profile_job(
+    model=target_model,
+    device=device,
+)
+        
+```
+
+Step 3: **Verify on-device accuracy**
+
+To verify the accuracy of the model on-device, you can run on-device inference
+on sample input data on the same cloud hosted device.
+```python
+input_data = torch_model.sample_inputs()
+inference_job = hub.submit_inference_job(
+    model=target_model,
+    device=device,
+    inputs=input_data,
+)
+    on_device_output = inference_job.download_output_data()
+
 ```
+With the output of the model, you can compute like PSNR, relative errors or
+spot check the output with expected output.
 
+**Note**: This on-device profiling and inference requires access to Qualcomm®
+AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
 
 
 
@@ -149,12 +218,12 @@ provides instructions on how to use the `.so` shared library  in an Android appl
 
 
 ## View on Qualcomm® AI Hub
-Get more details on ConvNext-Tiny-w8a16-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized).
+Get more details on ConvNext-Tiny-W8A16-Quantized's performance across various devices [here](https://aihub.qualcomm.com/models/convnext_tiny_w8a16_quantized).
 Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
 
 ## License
-* The license for the original implementation of ConvNext-Tiny-w8a16-Quantized can be found
+* The license for the original implementation of ConvNext-Tiny-W8A16-Quantized 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)