Upload README.md with huggingface_hub

README.md

@@ -36,10 +36,10 @@ More details on model performance across various devices, can be found
 
 | 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 | 0.837 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipePoseDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 1.011 ms | 0 - 2 MB | FP16 | NPU |  [MediaPipePoseLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.884 ms | 0 - 15 MB | FP16 | NPU |  [MediaPipePoseDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.so) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 1.083 ms | 0 - 16 MB | FP16 | NPU |  [MediaPipePoseLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.793 ms | 0 - 14 MB | FP16 | NPU |  [MediaPipePoseDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 0.839 ms | 0 - 174 MB | FP16 | NPU |  [MediaPipePoseLandmarkDetector.tflite](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.851 ms | 0 - 102 MB | FP16 | NPU |  [MediaPipePoseDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseDetector.so) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | QNN Model Library | 0.906 ms | 0 - 9 MB | FP16 | NPU |  [MediaPipePoseLandmarkDetector.so](https://huggingface.co/qualcomm/MediaPipe-Pose-Estimation/blob/main/MediaPipePoseLandmarkDetector.so) 
 
 
 
@@ -100,17 +100,17 @@ python -m qai_hub_models.models.mediapipe_pose.export
 ```
 Profile Job summary of MediaPipePoseDetector
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 0.89 ms
-Estimated Peak Memory Range: 0.02-5.94 MB
-Compute Units: NPU (140) | Total (140)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 0.99 ms
+Estimated Peak Memory Range: 1.61-1.61 MB
+Compute Units: NPU (138) | Total (138)
 
 Profile Job summary of MediaPipePoseLandmarkDetector
 --------------------------------------------------
-Device: SA8255 (Proxy) (13)
-Estimated Inference Time: 1.08 ms
-Estimated Peak Memory Range: 0.02-11.66 MB
-Compute Units: NPU (292) | Total (292)
+Device: Snapdragon X Elite CRD (11)
+Estimated Inference Time: 1.11 ms
+Estimated Peak Memory Range: 0.75-0.75 MB
+Compute Units: NPU (290) | Total (290)
 
 
 ```
@@ -131,29 +131,49 @@ in memory using the `jit.trace` and then call the `submit_compile_job` API.
 import torch
 
 import qai_hub as hub
-from qai_hub_models.models.mediapipe_pose import Model
+from qai_hub_models.models.mediapipe_pose import MediaPipePoseDetector,MediaPipePoseLandmarkDetector
 
 # Load the model
-torch_model = Model.from_pretrained()
+pose_detector_model = MediaPipePoseDetector.from_pretrained()
+
+pose_landmark_detector_model = MediaPipePoseLandmarkDetector.from_pretrained()
+
 
 # Device
 device = hub.Device("Samsung Galaxy S23")
 
+
 # Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
+pose_detector_input_shape = pose_detector_model.get_input_spec()
+pose_detector_sample_inputs = pose_detector_model.sample_inputs()
 
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+traced_pose_detector_model = torch.jit.trace(pose_detector_model, [torch.tensor(data[0]) for _, data in pose_detector_sample_inputs.items()])
 
 # Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
+pose_detector_compile_job = hub.submit_compile_job(
+    model=traced_pose_detector_model ,
     device=device,
-    input_specs=torch_model.get_input_spec(),
+    input_specs=pose_detector_model.get_input_spec(),
 )
 
 # Get target model to run on-device
-target_model = compile_job.get_target_model()
+pose_detector_target_model = pose_detector_compile_job.get_target_model()
+
+# Trace model
+pose_landmark_detector_input_shape = pose_landmark_detector_model.get_input_spec()
+pose_landmark_detector_sample_inputs = pose_landmark_detector_model.sample_inputs()
+
+traced_pose_landmark_detector_model = torch.jit.trace(pose_landmark_detector_model, [torch.tensor(data[0]) for _, data in pose_landmark_detector_sample_inputs.items()])
+
+# Compile model on a specific device
+pose_landmark_detector_compile_job = hub.submit_compile_job(
+    model=traced_pose_landmark_detector_model ,
+    device=device,
+    input_specs=pose_landmark_detector_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+pose_landmark_detector_target_model = pose_landmark_detector_compile_job.get_target_model()
 
 ```
 
@@ -165,10 +185,16 @@ After compiling models from step 1. Models can be profiled model on-device using
 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,
-)
+
+pose_detector_profile_job = hub.submit_profile_job(
+        model=pose_detector_target_model,
+        device=device,
+        )       
+
+pose_landmark_detector_profile_job = hub.submit_profile_job(
+        model=pose_landmark_detector_target_model,
+        device=device,
+        )       
 
 ```
 
@@ -177,14 +203,20 @@ 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()
+pose_detector_input_data = pose_detector_model.sample_inputs()
+pose_detector_inference_job = hub.submit_inference_job(
+        model=pose_detector_target_model,
+        device=device,
+        inputs=pose_detector_input_data,
+    )
+pose_detector_inference_job.download_output_data()
+pose_landmark_detector_input_data = pose_landmark_detector_model.sample_inputs()
+pose_landmark_detector_inference_job = hub.submit_inference_job(
+        model=pose_landmark_detector_target_model,
+        device=device,
+        inputs=pose_landmark_detector_input_data,
+    )
+pose_landmark_detector_inference_job.download_output_data()
 
 ```
 With the output of the model, you can compute like PSNR, relative errors or