GenCAD

Image-conditioned Computer-Aided Design Generation with Transformer-based Contrastive Representation and Diffusion Priors

---

---

📁 Dataset

Download from here and place it in the data/ directory.

---

📦 Pretrained Models

Download from here and place them in data/ckpt/.

---

🔧 Setup Options

First download the checkpoints and the dataset and put them in their respective directories.

Option 1: Docker (Recommended)

1. Clone the repo: bash git clone https://github.com/ferdous-alam/GenCAD cd GenCAD

2. Build the Docker image: bash docker build -t gencad:latest .

3. Run a script, for example training CSR: bash docker run -it gencad:latest conda run -n gencad_env python train_gencad.py csr -name test -gpu 0

4. For headless visualization (inference):

First, enter the container with GPU access and mount the appropriate folders:

bash docker run --gpus all \ -v $(pwd)/data/images:/app/data/images \ -v $(pwd)/assets:/app/assets \ -v $(pwd)/results:/app/results \ -it gencad:latest /bin/bash

Then inside the container, run:

bash xvfb-run --server-args="-screen 0 2048x2048x24" python inference_gencad.py -image_path data/images -export_img

---

Option 2: Manual (conda + pip)

1. Create and activate a virtual environment with GPU support: ```bash conda create -n gencad_env python=3.10 -y conda activate gencad_env

2. Install pythonocc-core using conda: bash conda install -c conda-forge pythonocc-core=7.9.0

3. Install the rest via pip: bash pip install -r requirements.txt

4. Now run training or inference: bash python train_gencad.py csr -name test -gpu 0

---

🚀 Training

CSR Model

python train_gencad.py csr -name test -gpu 0

Optional checkpoint:

python train_gencad.py csr -name test -gpu 0 -ckpt "model/ckpt/ae_ckpt_epoch1000.pth"

CCIP Model

python train_gencad.py ccip -name test -gpu 0 -cad_ckpt "model/ckpt/ae_ckpt_epoch1000.pth"

Diffusion Prior

python train_gencad.py dp -name test -gpu 0 -cad_emb 'data/embeddings/cad_embeddings.h5' -img_emb 'data/embeddings/sketch_embeddings.h5'

---

🧪 Inference

For headless systems (e.g. servers):

xvfb-run python inference_gencad.py

---

🖼 STL Visualization

Convert STL to PNG:

python stl2img.py -src path/to/stl/files -dst path/to/save/images

---

📊 Evaluation

Coming soon.