Buckets:

Eternal2026
/

a-motion-diffusion-bucket

Files

xet

Eternal2026/a-motion-diffusion-bucket / README.md

Eternal2026

about 2 months ago

preview code

download

raw

4.67 kB

---
license: mit
library_name: pytorch
tags:
- ropedia-academy
- educational
- embodied-ai
- from-scratch
- reproducible
- diffusion
---
# Motion diffusion (DDPM)

> A denoising-diffusion model that generates motion trajectories — the MDM recipe, trained from scratch, sampled from EMA weights.

Trained from scratch in **[Ropedia Academy](https://chaoyue0307.github.io/ropedia-academy/)** — an interactive, bilingual course on embodied & spatial AI. **Educational model:** small and quick to train; the value is the *method* and a reproducible pipeline, not a leaderboard score. Try it live in the **[Ropedia demos Space](https://huggingface.co/spaces/cy0307/ropedia-demos)**.

## At a glance

| | |
|---|---|
| **Base model** | Trained **from scratch** (random initialization) — no pretrained base model. |
| **Task** | human-motion generation |
| **Training objective** | **DDPM** denoising objective (predict the added noise) over motion trajectories; sample from an EMA of the weights. |
| **Track** | A · Human modeling |
| **Notebook** | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ChaoYue0307/ropedia-academy/blob/main/notebooks/training/A_motion_diffusion.ipynb) |

## Dataset

- **Name:** Synthetic motion trajectories
- **Type:** synthetic — procedural
- **Size / stats:** 4,096 looping 2D trajectories, 32 timesteps × 2 = 64-D each (varied radius/phase/noise)
- **Split:** train only (generative model)
- **Source:** procedural

## Training config

DDPM; Adam (lr 2e-4), 4000 steps, sequence length 32; EMA of weights for sampling. `STEPS` env-overridable.

## Evaluation results

| metric | value | meaning |
|---|---|---|
| `loss (final)` | 0.159 |  |


![figure](figure.png)

## Inference example

```python
import torch
state = torch.load("denoiser.pt", map_location="cpu")   # this repo's checkpoint
# Rebuild the exact module from the lab notebook (see "Reproduce"), then:
# model.load_state_dict(state); model.eval()
```

## Limitations

**Educational scale.** Trained quickly on CPU on small or synthetic data, so absolute numbers are not competitive with production systems — the value is the *method* and a reproducible pipeline. No large-scale data, no hyperparameter sweep, and no multi-seed variance is reported. **Not for production use.**

## Failure cases

Too few sampling steps or no EMA → jittery/averaged motions; mode collapse with too little data.

## Reproduce / train your own

**One click:** open the notebook in Colab → **Runtime → GPU → Run all**, then run its *Publish to the Hugging Face Hub* cell.

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ChaoYue0307/ropedia-academy/blob/main/notebooks/training/A_motion_diffusion.ipynb)

**From a shell:**
```bash
git clone https://github.com/ChaoYue0307/ropedia-academy.git && cd ropedia-academy
pip install torch numpy matplotlib scikit-learn scikit-image gymnasium
jupyter nbconvert --to notebook --execute notebooks/training/A_motion_diffusion.ipynb --output run.ipynb
# optional: override training length, e.g.  STEPS=2000  (or EPISODES=600)  before running
```

## Files

- `denoiser.pt`
- `figure.png`
- `metrics.json`


## License

Code & weights: **MIT** (this repository) — educational use encouraged.  
Data: generated procedurally in the notebook — no external dataset.

## Citation

If you use this model or the course materials, please cite:

```bibtex
@misc{ropedia_academy,
  title  = {Ropedia Academy: an interactive course on embodied & spatial AI},
  author = {Ropedia Academy},
  year   = {2026},
  howpublished = {\url{https://chaoyue0307.github.io/ropedia-academy/}}
}
```


**Method / original work:** Tevet et al., *Human Motion Diffusion Model (MDM)*, ICLR 2023 (arXiv:2209.14916); Ho et al., *DDPM*, NeurIPS 2020.

## Related assets

- 🚀 **Live demos:** [https://huggingface.co/spaces/cy0307/ropedia-demos](https://huggingface.co/spaces/cy0307/ropedia-demos)
- 🤗 **All trained models + collection:** [https://huggingface.co/cy0307](https://huggingface.co/cy0307)
- 📚 **Course & all labs:** [https://chaoyue0307.github.io/ropedia-academy/](https://chaoyue0307.github.io/ropedia-academy/) · [Labs tab](https://chaoyue0307.github.io/ropedia-academy/labs)
- 💻 **Source / notebooks:** [github.com/ChaoYue0307/ropedia-academy](https://github.com/ChaoYue0307/ropedia-academy)


---
*Part of the [Ropedia Academy](https://chaoyue0307.github.io/ropedia-academy/) trained-model collection. Contributions & issues welcome on [GitHub](https://github.com/ChaoYue0307/ropedia-academy).*

Xet Storage Details

Size:: 4.67 kB
Xet hash:: 357d1540a5b156b76d7388791afa8669a4047c3cf97ccbcba6f5e2490f970958

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.

	---
	license: mit
	library_name: pytorch
	tags:
	- ropedia-academy
	- educational
	- embodied-ai
	- from-scratch
	- reproducible
	- diffusion
	---

	# Motion diffusion (DDPM)

	> A denoising-diffusion model that generates motion trajectories — the MDM recipe, trained from scratch, sampled from EMA weights.

	Trained from scratch in [Ropedia Academy](https://chaoyue0307.github.io/ropedia-academy/) — an interactive, bilingual course on embodied & spatial AI. Educational model: small and quick to train; the value is the method and a reproducible pipeline, not a leaderboard score. Try it live in the [Ropedia demos Space](https://huggingface.co/spaces/cy0307/ropedia-demos).

	## At a glance

	\| \| \|
	\|---\|---\|
	\| Base model \| Trained from scratch (random initialization) — no pretrained base model. \|
	\| Task \| human-motion generation \|
	\| Training objective \| DDPM denoising objective (predict the added noise) over motion trajectories; sample from an EMA of the weights. \|
	\| Track \| A · Human modeling \|
	\| Notebook \| [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ChaoYue0307/ropedia-academy/blob/main/notebooks/training/A_motion_diffusion.ipynb) \|

	## Dataset

	- Name: Synthetic motion trajectories
	- Type: synthetic — procedural
	- Size / stats: 4,096 looping 2D trajectories, 32 timesteps × 2 = 64-D each (varied radius/phase/noise)
	- Split: train only (generative model)
	- Source: procedural

	## Training config

	DDPM; Adam (lr 2e-4), 4000 steps, sequence length 32; EMA of weights for sampling. `STEPS` env-overridable.

	## Evaluation results

	\| metric \| value \| meaning \|
	\|---\|---\|---\|
	\| `loss (final)` \| 0.159 \| \|


	![figure](figure.png)

	## Inference example

	```python
	import torch
	state = torch.load("denoiser.pt", map_location="cpu") # this repo's checkpoint
	# Rebuild the exact module from the lab notebook (see "Reproduce"), then:
	# model.load_state_dict(state); model.eval()
	```

	## Limitations

	Educational scale. Trained quickly on CPU on small or synthetic data, so absolute numbers are not competitive with production systems — the value is the method and a reproducible pipeline. No large-scale data, no hyperparameter sweep, and no multi-seed variance is reported. Not for production use.

	## Failure cases

	Too few sampling steps or no EMA → jittery/averaged motions; mode collapse with too little data.

	## Reproduce / train your own

	One click: open the notebook in Colab → Runtime → GPU → Run all, then run its Publish to the Hugging Face Hub cell.

	[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/ChaoYue0307/ropedia-academy/blob/main/notebooks/training/A_motion_diffusion.ipynb)

	From a shell:
	```bash
	git clone https://github.com/ChaoYue0307/ropedia-academy.git && cd ropedia-academy
	pip install torch numpy matplotlib scikit-learn scikit-image gymnasium
	jupyter nbconvert --to notebook --execute notebooks/training/A_motion_diffusion.ipynb --output run.ipynb
	# optional: override training length, e.g. STEPS=2000 (or EPISODES=600) before running
	```

	## Files

	- `denoiser.pt`
	- `figure.png`
	- `metrics.json`


	## License

	Code & weights: MIT (this repository) — educational use encouraged.
	Data: generated procedurally in the notebook — no external dataset.

	## Citation

	If you use this model or the course materials, please cite:

	```bibtex
	@misc{ropedia_academy,
	title = {Ropedia Academy: an interactive course on embodied & spatial AI},
	author = {Ropedia Academy},
	year = {2026},
	howpublished = {\url{https://chaoyue0307.github.io/ropedia-academy/}}
	}
	```


	Method / original work: Tevet et al., Human Motion Diffusion Model (MDM), ICLR 2023 (arXiv:2209.14916); Ho et al., DDPM, NeurIPS 2020.

	## Related assets

	- 🚀 Live demos: [https://huggingface.co/spaces/cy0307/ropedia-demos](https://huggingface.co/spaces/cy0307/ropedia-demos)
	- 🤗 All trained models + collection: [https://huggingface.co/cy0307](https://huggingface.co/cy0307)
	- 📚 Course & all labs: [https://chaoyue0307.github.io/ropedia-academy/](https://chaoyue0307.github.io/ropedia-academy/) · [Labs tab](https://chaoyue0307.github.io/ropedia-academy/labs)
	- 💻 Source / notebooks: [github.com/ChaoYue0307/ropedia-academy](https://github.com/ChaoYue0307/ropedia-academy)


	---
	Part of the [Ropedia Academy](https://chaoyue0307.github.io/ropedia-academy/) trained-model collection. Contributions & issues welcome on [GitHub](https://github.com/ChaoYue0307/ropedia-academy).