Update README.md

README.md

@@ -1,34 +1,152 @@
-# Diffusion Policy for Pick-and-Place (SO-100)
+---
+datasets: Eshwar-2123/pick_place_blue_cube_box_clean_v1_20260706_125359
+library_name: lerobot
+license: apache-2.0
+model_name: diffusion
+pipeline_tag: robotics
+tags:
+- lerobot
+- robotics
+- diffusion
+---
 
-## Overview
-This model is a Diffusion Policy trained using Hugging Face LeRobot for a single-task pick-and-place manipulation problem.
+# Model Card for Diffusion Policy
 
-## Robot
-- SO-100 follower arm
-- Front camera
-- Wrist camera
+[Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://huggingface.co/papers/2303.04137) is an imitation learning policy that models robot actions as a denoising diffusion process. It is particularly effective for learning multi-modal manipulation behaviors from demonstrations while producing smooth action trajectories.
 
-## Task
-Pick the blue cube from one of four predefined locations and place it into a fixed target box.
+<!--
+Add a demo GIF after benchmarking.
 
-## Dataset
-- 40 teleoperated demonstrations
-- Dual-camera observations
-- Dataset:
-  Eshwar-2123/pick_place_blue_cube_box_clean_v1_20260706_125359
+<p align="center">
+  <img src="https://huggingface.co/Eshwar-2123/diffusion_pick_place_clean/resolve/main/demo.gif" width="60%"/>
+</p>
+-->
 
-## Training
-- Policy: Diffusion Policy
-- Steps: 30,000
-- Batch size: 16
-- GPU: NVIDIA RTX 5080
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
 
-## Results
-- Lowest validation loss: 0.037 (10k steps)
-- Final training loss: 0.0036
-- Final validation loss: 0.1303
+Learn how to train and run it in the [LeRobot Diffusion Policy guide](https://huggingface.co/docs/lerobot/main/en/diffusion), or browse the [full documentation](https://huggingface.co/docs/lerobot/index).
 
-## Usage
+---
 
-```python
-from lerobot.policies import DiffusionPolicy
+# Model Details
+
+- **License:** apache-2.0
+- **Robot type:** `so_follower`
+- **Cameras:** `front`, `wrist`
+
+## Inputs & Outputs
+
+The policy consumes these observation features and produces these action features.
+
+### Inputs
+
+| Feature | Type | Shape |
+| --- | --- | --- |
+| `observation.state` | STATE | `(6,)` |
+| `observation.images.front` | VISUAL | `(3, 480, 640)` |
+| `observation.images.wrist` | VISUAL | `(3, 480, 640)` |
+
+### Outputs
+
+| Feature | Type | Shape |
+| --- | --- | --- |
+| `action` | ACTION | `(6,)` |
+
+---
+
+# Training Dataset
+
+- **Repository:** [Eshwar-2123/pick_place_blue_cube_box_clean_v1_20260706_125359](https://huggingface.co/datasets/Eshwar-2123/pick_place_blue_cube_box_clean_v1_20260706_125359)
+- **Episodes:** 47
+- **Frames:** 20321
+- **Frame rate:** 30 FPS
+- **Task(s):** ""
+
+<a class="flex" href="https://huggingface.co/spaces/lerobot/visualize_dataset?path=Eshwar-2123/pick_place_blue_cube_box_clean_v1_20260706_125359">
+<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl.svg"/>
+<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl-dark.svg"/>
+</a>
+
+---
+
+# Training Configuration
+
+| Setting | Value |
+| --- | --- |
+| Training steps | 30000 |
+| Batch size | 16 |
+| Optimizer | adamw |
+| Learning rate | 1e-04 |
+| Seed | 1000 |
+| LeRobot version | 0.5.2 |
+
+---
+
+# How to Get Started with the Model
+
+New to LeRobot? These guides cover the full workflow:
+
+- **[Install LeRobot](https://huggingface.co/docs/lerobot/main/en/installation)** — set up the `lerobot` package.
+- **[Hardware setup](https://huggingface.co/docs/lerobot/main/en/hardware_guide)** — assemble, wire, and calibrate your robot and cameras.
+- **[Record data & train a policy](https://huggingface.co/docs/lerobot/en/il_robots)** — the end-to-end imitation-learning walkthrough.
+- **[CLI cheat-sheet](https://huggingface.co/docs/lerobot/main/en/cheat-sheet)** — quick reference for the `lerobot-*` commands.
+
+## Run the policy on your robot
+
+```bash
+lerobot-rollout \
+  --strategy.type=base \
+  --robot.type=so_follower \
+  --robot.port=<your_robot_port> \
+  --robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
+  --policy.path=Eshwar-2123/diffusion_pick_place_clean \
+  --task="" \
+  --duration=60
+```
+
+Replace the remaining `<...>` placeholders with your own values.
+
+---
+
+## Train your own policy
+
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=diffusion \
+  --output_dir=outputs/train/<policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<policy_repo_id> \
+  --wandb.enable=true
+```
+
+_Writes checkpoints to `outputs/train/<policy_repo_id>/checkpoints/`._
+
+---
+
+# Evaluation
+
+_No evaluation results have been provided for this policy yet._
+
+---
+
+# Citation
+
+If you use this policy, please cite **Diffusion Policy**, along with **LeRobot**.
+
+```bibtex
+@article{chi2023diffusionpolicy,
+  title={Diffusion Policy: Visuomotor Policy Learning via Action Diffusion},
+  author={Chi, Cheng and Feng, Siyuan and Du, Yilun and Xu, Zheng and Cousineau, Eric and Burchfiel, Benjamin and Song, Shuran},
+  journal={RSS},
+  year={2023}
+}
+
+@misc{cadene2024lerobot,
+    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
+    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
+    howpublished = "\url{https://github.com/huggingface/lerobot}",
+    year = {2024}
+}
+```