Upload README.md with huggingface_hub

README.md

@@ -1,10 +1,10 @@
 ---
 library_name: pytorch
 license: agpl-3.0
-pipeline_tag: image-segmentation
 tags:
 - real_time
 - android
+pipeline_tag: image-segmentation
 
 ---
 
@@ -19,10 +19,7 @@ Ultralytics YOLOv11 is a machine learning model that predicts bounding boxes, se
 This model is an implementation of YOLOv11-Segmentation found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment).
 
 
-This repository provides scripts to run YOLOv11-Segmentation on Qualcomm® devices.
-More details on model performance across various devices, can be found
-[here](https://aihub.qualcomm.com/models/yolov11_seg).
-
+ More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov11_seg).
 
 ### Model Details
 
@@ -36,200 +33,24 @@ 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
 |---|---|---|---|---|---|---|---|---|
-| YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 6.693 ms | 4 - 23 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 123.821 ms | 95 - 109 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
-| YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.927 ms | 4 - 61 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 83.391 ms | 101 - 129 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
-| YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 4.723 ms | 4 - 57 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 88.892 ms | 100 - 115 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
-| YOLOv11-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.725 ms | 4 - 27 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | SA7255P ADP | SA7255P | TFLITE | 81.221 ms | 4 - 51 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.681 ms | 4 - 27 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | SA8295P ADP | SA8295P | TFLITE | 12.22 ms | 4 - 42 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.739 ms | 4 - 22 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | SA8775P ADP | SA8775P | TFLITE | 10.058 ms | 4 - 52 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 10.725 ms | 4 - 43 MB | FP16 | NPU | [YOLOv11-Segmentation.tflite](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.tflite) |
-| YOLOv11-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 32.261 ms | 117 - 117 MB | FP32 | CPU | [YOLOv11-Segmentation.onnx](https://huggingface.co/qualcomm/YOLOv11-Segmentation/blob/main/YOLOv11-Segmentation.onnx) |
-
-
-
-
-## Installation
-
-
-Install the package via pip:
-```bash
-pip install "qai-hub-models[yolov11-seg]"
-```
-
-
-## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
-
-Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
-Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
-
-With this API token, you can configure your client to run models on the cloud
-hosted devices.
-```bash
-qai-hub configure --api_token API_TOKEN
-```
-Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
-
-
-
-## Demo off target
-
-The package contains a simple end-to-end demo that downloads pre-trained
-weights and runs this model on a sample input.
-
-```bash
-python -m qai_hub_models.models.yolov11_seg.demo
-```
-
-The above demo runs a reference implementation of pre-processing, model
-inference, and post processing.
-
-**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
-environment, please add the following to your cell (instead of the above).
-```
-%run -m qai_hub_models.models.yolov11_seg.demo
-```
-
-
-### Run model on a cloud-hosted device
-
-In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
-device. This script does the following:
-* Performance check on-device on a cloud-hosted device
-* Downloads compiled assets that can be deployed on-device for Android.
-* Accuracy check between PyTorch and on-device outputs.
-
-```bash
-python -m qai_hub_models.models.yolov11_seg.export
-```
-```
-Profiling Results
-------------------------------------------------------------
-YOLOv11-Segmentation
-Device                          : Samsung Galaxy S23 (13)
-Runtime                         : TFLITE                 
-Estimated inference time (ms)   : 6.7                    
-Estimated peak memory usage (MB): [4, 23]                
-Total # Ops                     : 429                    
-Compute Unit(s)                 : NPU (429 ops)          
-```
-
-
-## How does this work?
-
-This [export script](https://aihub.qualcomm.com/models/yolov11_seg/qai_hub_models/models/YOLOv11-Segmentation/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.
+| YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 6.633 ms | 4 - 30 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 104.404 ms | 95 - 108 MB | FP32 | CPU | -- |
+| YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 4.766 ms | 0 - 53 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 86.584 ms | 97 - 120 MB | FP32 | CPU | -- |
+| YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 3.908 ms | 0 - 54 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 88.869 ms | 98 - 114 MB | FP32 | CPU | -- |
+| YOLOv11-Segmentation | SA7255P ADP | SA7255P | TFLITE | 81.11 ms | 4 - 50 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 6.575 ms | 4 - 22 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | SA8295P ADP | SA8295P | TFLITE | 11.829 ms | 4 - 38 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 6.586 ms | 4 - 31 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | SA8775P ADP | SA8775P | TFLITE | 9.978 ms | 4 - 51 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 81.11 ms | 4 - 50 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 6.612 ms | 4 - 31 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 9.978 ms | 4 - 51 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 10.242 ms | 4 - 43 MB | FP16 | NPU | -- |
+| YOLOv11-Segmentation | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 31.289 ms | 116 - 116 MB | FP32 | CPU | -- |
 
-```python
-import torch
 
-import qai_hub as hub
-from qai_hub_models.models.yolov11_seg 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).
-
-
-
-## Run demo on a cloud-hosted device
-
-You can also run the demo on-device.
-
-```bash
-python -m qai_hub_models.models.yolov11_seg.demo --on-device
-```
-
-**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
-environment, please add the following to your cell (instead of the above).
-```
-%run -m qai_hub_models.models.yolov11_seg.demo -- --on-device
-```
-
-
-## Deploying compiled model to Android
-
-
-The models can be deployed using multiple runtimes:
-- TensorFlow Lite (`.tflite` export): [This
-  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
-  guide to deploy the .tflite model in an Android application.
-
-
-- QNN (`.so` export ): This [sample
-  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
-provides instructions on how to use the `.so` shared library  in an Android application.
-
-
-## View on Qualcomm® AI Hub
-Get more details on YOLOv11-Segmentation's performance across various devices [here](https://aihub.qualcomm.com/models/yolov11_seg).
-Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
 
 ## License
@@ -246,7 +67,26 @@ Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
 
 
 ## Community
-* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
+* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI.
 * For questions or feedback please [reach out to us](mailto:[email protected]).
 
-
+## Usage and Limitations
+
+Model may not be used for or in connection with any of the following applications:
+
+- Accessing essential private and public services and benefits;
+- Administration of justice and democratic processes;
+- Assessing or recognizing the emotional state of a person;
+- Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
+- Education and vocational training;
+- Employment and workers management;
+- Exploitation of the vulnerabilities of persons resulting in harmful behavior;
+- General purpose social scoring;
+- Law enforcement;
+- Management and operation of critical infrastructure;
+- Migration, asylum and border control management;
+- Predictive policing;
+- Real-time remote biometric identification in public spaces;
+- Recommender systems of social media platforms;
+- Scraping of facial images (from the internet or otherwise); and/or
+- Subliminal manipulation