Upload README.md with huggingface_hub

README.md

@@ -35,8 +35,8 @@ 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 | 48.448 ms | 4 - 17 MB | FP16 | NPU |  [SAMDecoder.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) 
-| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 12267.436 ms | 2517 - 2522 MB | FP32 | CPU |  [SAMEncoder.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 47.928 ms | 4 - 22 MB | FP16 | NPU |  [SAMDecoder.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMDecoder.tflite) 
+| Samsung Galaxy S23 Ultra (Android 13) | Snapdragon® 8 Gen 2 | TFLite | 10523.061 ms | 2482 - 2528 MB | FP32 | CPU |  [SAMEncoder.tflite](https://huggingface.co/qualcomm/Segment-Anything-Model/blob/main/SAMEncoder.tflite) 
 
 
 
@@ -98,17 +98,17 @@ python -m qai_hub_models.models.sam.export
 ```
 Profile Job summary of SAMDecoder
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 47.86 ms
-Estimated Peak Memory Range: 3.86-6.07 MB
-Compute Units: NPU (341) | Total (341)
+Device: SA8255 (Proxy) (13)
+Estimated Inference Time: 48.42 ms
+Estimated Peak Memory Range: 2.11-19.94 MB
+Compute Units: NPU (337) | Total (337)
 
 Profile Job summary of SAMEncoder
 --------------------------------------------------
-Device: QCS8550 (Proxy) (12)
-Estimated Inference Time: 11666.28 ms
-Estimated Peak Memory Range: 2526.26-2529.86 MB
-Compute Units: GPU (37),CPU (783) | Total (820)
+Device: SA8255 (Proxy) (13)
+Estimated Inference Time: 11251.67 ms
+Estimated Peak Memory Range: 2591.24-2594.47 MB
+Compute Units: GPU (36),CPU (782) | Total (818)
 
 
 ```
@@ -129,29 +129,49 @@ 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.sam import Model
+from qai_hub_models.models.sam import SAMDecoder,SAMEncoder
 
 # Load the model
-torch_model = Model.from_pretrained()
+get_sam_decoder()_model = SAMDecoder.from_pretrained()
+
+get_sam_encoder()_model = SAMEncoder.from_pretrained()
+
 
 # Device
 device = hub.Device("Samsung Galaxy S23")
 
+
 # Trace model
-input_shape = torch_model.get_input_spec()
-sample_inputs = torch_model.sample_inputs()
+get_sam_decoder()_input_shape = get_sam_decoder()_model.get_input_spec()
+get_sam_decoder()_sample_inputs = get_sam_decoder()_model.sample_inputs()
 
-pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+traced_get_sam_decoder()_model = torch.jit.trace(get_sam_decoder()_model, [torch.tensor(data[0]) for _, data in get_sam_decoder()_sample_inputs.items()])
 
 # Compile model on a specific device
-compile_job = hub.submit_compile_job(
-    model=pt_model,
+get_sam_decoder()_compile_job = hub.submit_compile_job(
+    model=traced_get_sam_decoder()_model ,
     device=device,
-    input_specs=torch_model.get_input_spec(),
+    input_specs=get_sam_decoder()_model.get_input_spec(),
 )
 
 # Get target model to run on-device
-target_model = compile_job.get_target_model()
+get_sam_decoder()_target_model = get_sam_decoder()_compile_job.get_target_model()
+
+# Trace model
+get_sam_encoder()_input_shape = get_sam_encoder()_model.get_input_spec()
+get_sam_encoder()_sample_inputs = get_sam_encoder()_model.sample_inputs()
+
+traced_get_sam_encoder()_model = torch.jit.trace(get_sam_encoder()_model, [torch.tensor(data[0]) for _, data in get_sam_encoder()_sample_inputs.items()])
+
+# Compile model on a specific device
+get_sam_encoder()_compile_job = hub.submit_compile_job(
+    model=traced_get_sam_encoder()_model ,
+    device=device,
+    input_specs=get_sam_encoder()_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+get_sam_encoder()_target_model = get_sam_encoder()_compile_job.get_target_model()
 
 ```
 
@@ -163,10 +183,16 @@ 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,
-)
+
+get_sam_decoder()_profile_job = hub.submit_profile_job(
+        model=get_sam_decoder()_target_model,
+        device=device,
+        )       
+
+get_sam_encoder()_profile_job = hub.submit_profile_job(
+        model=get_sam_encoder()_target_model,
+        device=device,
+        )       
 
 ```
 
@@ -175,14 +201,20 @@ 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()
+get_sam_decoder()_input_data = get_sam_decoder()_model.sample_inputs()
+get_sam_decoder()_inference_job = hub.submit_inference_job(
+        model=get_sam_decoder()_target_model,
+        device=device,
+        inputs=get_sam_decoder()_input_data,
+    )
+get_sam_decoder()_inference_job.download_output_data()
+get_sam_encoder()_input_data = get_sam_encoder()_model.sample_inputs()
+get_sam_encoder()_inference_job = hub.submit_inference_job(
+        model=get_sam_encoder()_target_model,
+        device=device,
+        inputs=get_sam_encoder()_input_data,
+    )
+get_sam_encoder()_inference_job.download_output_data()
 
 ```
 With the output of the model, you can compute like PSNR, relative errors or