v0.30.5

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

README.md

@@ -0,0 +1,269 @@
+---
+library_name: pytorch
+license: other
+tags:
+- android
+pipeline_tag: keypoint-detection
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/rtmpose_body2d/web-assets/model_demo.png)
+
+# RTMPose-Body2d: Optimized for Mobile Deployment
+## Human pose estimation
+
+
+RTMPose is a machine learning model that detects human pose and returns a location and confidence for each of 133 joints.
+
+This model is an implementation of RTMPose-Body2d found [here](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose).
+
+
+This repository provides scripts to run RTMPose-Body2d on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/rtmpose_body2d).
+
+
+### Model Details
+
+- **Model Type:** Model_use_case.pose_estimation
+- **Model Stats:**
+  - Input resolution: 256x192
+  - Number of parameters: 17.9M
+  - Model size (float): 68.5 MB
+  - Model size (w8a8): 17.52MB
+
+| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| RTMPose-Body2d | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 46.335 ms | 0 - 32 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 46.222 ms | 1 - 10 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 3.033 ms | 0 - 62 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 3.544 ms | 0 - 31 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 1.873 ms | 0 - 253 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 1.776 ms | 1 - 3 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.595 ms | 0 - 32 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 2.456 ms | 1 - 10 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 46.335 ms | 0 - 32 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | SA7255P ADP | Qualcomm® SA7255P | QNN | 46.222 ms | 1 - 10 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 1.868 ms | 0 - 251 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN | 1.786 ms | 1 - 3 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 3.625 ms | 0 - 35 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | SA8295P ADP | Qualcomm® SA8295P | QNN | 3.56 ms | 0 - 17 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 1.87 ms | 0 - 263 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN | 1.784 ms | 1 - 3 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2.595 ms | 0 - 32 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | SA8775P ADP | Qualcomm® SA8775P | QNN | 2.456 ms | 1 - 10 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 1.836 ms | 0 - 261 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 1.782 ms | 0 - 114 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 1.987 ms | 0 - 94 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.onnx) |
+| RTMPose-Body2d | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.377 ms | 0 - 60 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 1.31 ms | 0 - 30 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.436 ms | 0 - 30 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.onnx) |
+| RTMPose-Body2d | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.324 ms | 0 - 38 MB | NPU | [RTMPose-Body2d.tflite](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.tflite) |
+| RTMPose-Body2d | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 1.267 ms | 0 - 21 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 1.443 ms | 0 - 23 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.onnx) |
+| RTMPose-Body2d | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.873 ms | 1 - 1 MB | NPU | Use Export Script |
+| RTMPose-Body2d | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.973 ms | 37 - 37 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d.onnx) |
+| RTMPose-Body2d | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 2.799 ms | 0 - 33 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d_w8a16.onnx) |
+| RTMPose-Body2d | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 1.962 ms | 0 - 48 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d_w8a16.onnx) |
+| RTMPose-Body2d | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.013 ms | 0 - 32 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d_w8a16.onnx) |
+| RTMPose-Body2d | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 3.028 ms | 19 - 19 MB | NPU | [RTMPose-Body2d.onnx](https://huggingface.co/qualcomm/RTMPose-Body2d/blob/main/RTMPose-Body2d_w8a16.onnx) |
+
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+pip install "qai-hub-models[rtmpose-body2d]" torch==2.4.1 -f https://download.openmmlab.com/mmcv/dist/cpu/torch2.4/index.html -f https://qaihub-public-python-wheels.s3.us-west-2.amazonaws.com/index.html
+```
+
+
+## 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.rtmpose_body2d.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.rtmpose_body2d.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.rtmpose_body2d.export
+```
+```
+Profiling Results
+------------------------------------------------------------
+RTMPose-Body2d
+Device                          : cs_8275 (ANDROID 14)                 
+Runtime                         : TFLITE                               
+Estimated inference time (ms)   : 46.3                                 
+Estimated peak memory usage (MB): [0, 32]                              
+Total # Ops                     : 256                                  
+Compute Unit(s)                 : npu (256 ops) gpu (0 ops) cpu (0 ops)
+```
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/rtmpose_body2d/qai_hub_models/models/RTMPose-Body2d/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.rtmpose_body2d 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.rtmpose_body2d.demo --eval-mode 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.rtmpose_body2d.demo -- --eval-mode 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 RTMPose-Body2d's performance across various devices [here](https://aihub.qualcomm.com/models/rtmpose_body2d).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of RTMPose-Body2d can be found
+  [here](https://github.com/open-mmlab/mmpose/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
+* [RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose](https://arxiv.org/abs/2303.07399)
+* [Source Model Implementation](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose)
+
+
+
+## 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:ai-hub-support@qti.qualcomm.com).
+
+

RTMPose-Body2d.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2925e13813c91928dfae95035ef61bf2d1f43978546b5286cc701f60bfb0b2aa
+size 71842158

RTMPose-Body2d.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d7b949903d4a9b8293c1859e03a1355e8edc04bf04d609d4c39a9670edfa87
+size 71821100

RTMPose-Body2d_w8a16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:706d38d3943100b2ed8654a94887eeaaf6e2f41c220d8c53612f1e25322efdb1
+size 72145341