ddacs 2.0.0

Deep Drawing and Cutting Simulations (DDACS) Dataset - Python interface

Deep Drawing and Cutting Simulations (DDACS) Dataset

A Python package for accessing and processing the Deep Drawing and Cutting Simulations (DDACS) Dataset. It includes a CLI for downloading datasets from DaRUS and a Python API for accessing simulation data with metadata.

Simulation with the tool geometries and various additional information like sheet metal thinning, stress and strain. The gif has been interpolated for a more fluid display (the simulation contains 3 to 4 timesteps).

Table of Contents

• Table of Contents
• Installation
  • Core Installation
  • PyTorch Installation
  • Examples Installation
• Download Dataset
  • Versioning
• Basic Usage
  • Core Usage
  • PyTorch Usage
• Citation
  • Dataset Citation
  • Paper Citation
• Development Installation

Installation

Note: I recommend using uv as a fast Python package installer and resolver. Simply replace pip with uv pip in the commands below.

Core Installation

For basic dataset access without high weight module dependencies:

pip install git+https://github.com/BaumSebastian/Deep-Drawing-and-Cutting-Simulations-Dataset.git

PyTorch Installation

For PyTorch integration without visualization dependencies:

pip install "git+https://github.com/BaumSebastian/Deep-Drawing-and-Cutting-Simulations-Dataset.git[torch]"

Examples Installation

For examples with PyTorch, Jupyter, and visualization capabilities:

pip install "git+https://github.com/BaumSebastian/Deep-Drawing-and-Cutting-Simulations-Dataset.git[examples]"

Download Dataset

Download the dataset using the ddacs CLI:

# Download full dataset (requires ~1TB storage)
ddacs download

# Download small test set for quick demos (requires ~50GB storage)
ddacs download --small

# Show dataset info and available versions
ddacs info

Important: The full dataset is approximately 1TB in size. Ensure you have sufficient storage space. The download may take several hours depending on your internet connection.

Options:

Flag	Description
--small	Download small test set for demos
--out ./path	Custom output directory (default: ./data)
--no-extract	Skip extraction of zip files
--keep-zip	Keep zip files after extraction
-y, --yes	Skip confirmation prompt

Versioning

The package version aligns with the dataset version on DaRUS. Running ddacs download will download dataset version 2.0 by default.

# Check available versions
ddacs info

Basic Usage

Core Usage

For basic dataset iteration:

import h5py
import numpy as np
from ddacs import iter_ddacs, count_available_simulations

# Count available simulations
count = count_available_simulations("./data")
print(f"Available simulations: {count}")

# Iterate over first few samples
for i, (sim_id, metadata, h5_file_path) in enumerate(iter_ddacs("./data")):
    print(f"Sample {i+1}: ID={sim_id}, Path={h5_file_path}")

    # Access simulation data
    with h5py.File(h5_file_path, "r") as f:
        data = np.array(f["OP10"]["blank"]["node_displacement"])
        print(f"Data shape: {data.shape}")

    if i >= 2:  # Show first 3 samples
        break

PyTorch Usage

For PyTorch-compatible dataset with DataLoader support:

from ddacs.pytorch import DDACSDataset
from torch.utils.data import DataLoader

# Create dataset
dataset = DDACSDataset("./data")
dataloader = DataLoader(dataset, batch_size=4, shuffle=True)

# Use in training loop
for batch_idx, (sim_ids, metadata_batch, h5_paths) in enumerate(dataloader):
    print(f"Batch {batch_idx}: {len(sim_ids)} samples")
    # Your training code here
    if batch_idx >= 2:  # Show first 3 batches
        break

See examples/dataset_demo.ipynb for a comprehensive tutorial including visualization and advanced usage patterns.

Citation

If you use this dataset or code in your research, please cite both the dataset and the paper:

Dataset Citation

@dataset{baum2025ddacs,
  title={Deep Drawing and Cutting Simulations Dataset},
  subtitle={FEM Simulations of a deep drawn and cut dual phase steel part},
  author={Baum, Sebastian and Heinzelmann, Pascal},
  year={2025},
  version={1.0},
  publisher={DaRUS},
  doi={10.18419/DARUS-4801},
  license={CC BY 4.0},
  url={https://doi.org/10.18419/DARUS-4801}
}

Paper Citation

@article{heinzelmann2025benchmark,
  title={A Comprehensive Benchmark Dataset for Sheet Metal Forming: Advancing Machine Learning and Surrogate Modelling in Process Simulations},
  author={Heinzelmann, Pascal and Baum, Sebastian and Riedmüller, Kim Rouven and Liewald, Mathias and Weyrich, Michael},
  journal={MATEC Web of Conferences},
  volume={408},
  year={2025},
  pages={01090},
  doi={10.1051/matecconf/202540801090},
  url={https://www.matec-conferences.org/articles/matecconf/abs/2025/02/matecconf_iddrg2025_01090/matecconf_iddrg2025_01090.html}
}

Development Installation

For developers who want to contribute to this project:

git clone https://github.com/BaumSebastian/Deep-Drawing-and-Cutting-Simulations-Dataset.git DDACS
cd DDACS

# Install in editable mode with development dependencies
pip install -e ".[dev]"

This installs the package with the ddacs CLI command and all development tools.