Automated update of model files

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+library_name: tflite
+pipeline_tag: pose-detection
+tags:
+    - Astra SR
+    - SR100
+    - MCU
+    - Person Pose Detection
+---
+# Person Pose Detection 480x640 (SR100 Series)
+
+## Model Overview
+
+The **Person Pose Detection 480x640** model developed by Synaptics, is a lightweight quantized `tflite` model developed for the **SR100 processor** in the Synaptics Astra™  SR MCU Series. 
+
+It efficiently generates bounding boxes and identifies 17 keypoints for each person, corresponding to various body parts. Each keypoint is accompanied by a confidence score that indicates the reliability of the detection, enabling accurate estimation of the person's pose. This model can fit in Flash and designed to fit in SRAM as well.
+
+## Model Features
+
+- **Model Type:** Pose Detection
+- **Input Size:** 480x640 
+- **Output:** For each detected person, the model outputs bounding box coordinates, 17 keypoint locations and confidence scores.
+- **Classes:** Single class (person); model is designed specifically for pose estimation of people.
+
+
+
+## Deployment on Astra
+
+You can optimize this model for Synaptics Astra SR100 MCU using our our hosted [SR100 Model Compiler HF Space](https://huggingface.co/spaces/Synaptics/SR100-Model-Compiler).
+
+- **Processor:**  Astra™ SR100 MCU
+- **Platform:**  Astra™ Machina Micro Dev Kit
+- **Quantization:** INT8 (fully quantized)
+- **Compiler:** [SR100 Model Compiler](https://huggingface.co/spaces/Synaptics/SR100-Model-Compiler)
+- **Preprocessing:** Input images must be resized and quantized to match model requirements
+
+## Intended Applications
+
+Designed for **real-time person pose estimation** on embedded, resource-constrained edge devices. Typical use cases include:
+
+- Human activity recognition and gesture control
+- Fitness and wellness tracking
+- Smart home automation based on body posture
+- Interactive applications and user interfaces
+
+
+## Evaluate Model
+
+You can evaluate and test this model directly in our hosted [Hugging Face Space](https://huggingface.co/spaces/Synaptics/SR100-Model-Compiler),  optimized for **Synaptics SR110** MCU. This space provides a seamless sandbox for model evaluation using hardware-specific quantization and runtime settings.
+
+For a detailed walkthrough on how to optimize and evaluate a model, please see our [Evaluate Model Guide](https://developer.synaptics.com/docs/sr/sr110/evaluate-sr?utm_source=hf) page.
+
+To get started quickly with Astra SR Series, visit our [SR Quick Start](https://developer.synaptics.com/docs/sr/sr110/quick-start?utm_source=hf) page.
+
+## License
+
+Distributed under the [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0), allowing flexible use, modification, and distribution.
+
+## Learn More
+
+- [Synaptics AI Developer Zone](https://developer.synaptics.com?utm_source=hf): Get started with documentation, tutorials and resources for your Edge AI journey.
+- [Astra Support Portal](https://synacsm.atlassian.net/servicedesk/customer/portal/543?utm_source=hf): Connect with our engineering team and community.

person_pose_detection_flash(480x640).tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65290b73151b7b7ffbb0a182abc863a3fc656e77ff67c57be25013fc1b929e50
+size 1530504