Mohammad Sadil Khan* · Sankalp Sinha* · Talha Uddin Sheikh · Didier Stricker · Sk Aziz Ali · Muhammad Zeshan Afzal
*equal contributions
- 🐧 Linux
- 🐍 Python >=3.9
$ conda env create --file environment.yml- Release Data Preparation Code
- Release Training Code
- Release Inference Code
Download the DeepCAD data from here.
Generate Vector Representation from DeepCAD Json
You can also download the processed cad vec from here.
$ cd CadSeqProc
$ python3 json2vec.py --input_dir $DEEPCAD_JSON --split_json $TRAIN_TEST_VAL_JSON --output_dir $OUTPUT_DIR --max_workers $WORKERS --padding --deduplicateDownload the text annotations from here. Download the preprocessed training and validation data and place it in Cad_VLM/dataprep folder.
In the Cad_VLM/config/trainer.yaml, provide the following path.
Required Updates in yaml
cache_dir: The directory to load model weights from Huggingface.cad_seq_dir: The root directory that contains the ground truth CAD vector.prompt_path: Path for the text annotation.split_filepath: Json file containing the UIDs for train, test or validation.log_dir: Directory for saving logs, outputs, checkpoints.checkpoint_path(Optional): For resuming training after some epochs.
$ cd Cad_VLM
$ python3 train.py --config_path config/trainer.yamlIn the Cad_VLM/config/inference.yaml, provide the following path. Download the checkpoint for v1.0 here.
Required Updates in yaml
cache_dir: The directory to load model weights from Huggingface.cad_seq_dir: The root directory that contains the ground truth CAD vector.prompt_path: Path for the text annotation.split_filepath: Json file containing the UIDs for train, test or validation.log_dir: Directory for saving logs, outputs, checkpoints.checkpoint_path: The path to model weights.
$ cd Cad_VLM
$ python3 test.py --config_path config/inference.yaml$ cd Evaluation
$ python3 eval_seq.py --input_path ./output.pkl --output_dir ./outputIn the Cad_VLM/config/inference_user_input.yaml, provide the following path.
Required Updates in yaml
cache_dir: The directory to load model weights from Huggingface.log_dir: Directory for saving logs, outputs, checkpoints.checkpoint_path: The path to model weights.prompt_file(Optional): For single prompt ignore it, for multiple prompts provide a txt file.
$ cd Cad_VLM
$ python3 test_user_input.py --config_path config/inference_user_input.yaml --prompt "A rectangular prism with a hole in the middle."$ cd Cad_VLM
$ python3 test_user_input.py --config_path config/inference_user_input.yamlIn the Cad_VLM/config/inference_user_input.yaml, provide the following path.
Required Updates in yaml
cache_dir: The directory to load model weights from Huggingface.log_dir: Directory for saving logs, outputs, checkpoints.checkpoint_path: The path to model weights.
$ cd App
$ gradio app.pyOur project owes its success to the invaluable contributions of these remarkable individuals. We extend our heartfelt gratitude for their dedication and support.
We thank the authors of DeepCAD and SkexGen and acknowledge the use of their code.
If you use this dataset in your work, please consider citing the following publications.
@inproceedings{text2cad,
author = {Khan, Mohammad Sadil and Sinha, Sankalp and Sheikh, Talha Uddin and Stricker, Didier and Ali, Sk Aziz and Afzal, Muhammad Zeshan},
booktitle = {Advances in Neural Information Processing Systems},
editor = {A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang},
pages = {7552--7579},
publisher = {Curran Associates, Inc.},
title = {Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts},
url = {https://proceedings.neurips.cc/paper_files/paper/2024/file/0e5b96f97c1813bb75f6c28532c2ecc7-Paper-Conference.pdf},
volume = {37},
year = {2024},
bdsk-url-1 = {https://proceedings.neurips.cc/paper_files/paper/2024/file/0e5b96f97c1813bb75f6c28532c2ecc7-Paper-Conference.pdf}}