CADParser: A Learning Approach of Sequence Modeling for B-Rep CAD

Authors: Shengdi Zhou, Tianyi Tang, Bin Zhou

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate that our method can compete with the existing state-of-the-art methods quantitatively and qualitatively.
Researcher Affiliation Academia Shengdi Zhou1 , Tianyi Tang2 and Bin Zhou1 1State Key Laboratory of Virtual Reality Technology and Systems, Beihang University 2University of Waterloo {zhoushengdi9, tianyitangdhr}@gmail.com, zhoubin@buaa.edu.cn
Pseudocode No The paper describes the method and network architecture using text and diagrams but does not include any explicit pseudocode or algorithm blocks.
Open Source Code No The paper states 'Data is available at https://drive.google.com/CADParser Data' but does not mention the availability of the source code for CADParser.
Open Datasets Yes Data is available at https://drive.google.com/CADParser Data
Dataset Splits No The paper states 'We split our collected models into training and test set, where the test set counts 1000.' but does not explicitly mention a separate validation dataset split or its size.
Hardware Specification Yes We train our networks for 100 epochs with a total batch size of 96 on one 1080Ti GPU
Software Dependencies No The paper mentions using the AdamW optimizer but does not specify version numbers for any key software components or libraries (e.g., Python, PyTorch, TensorFlow, CUDA).
Experiment Setup Yes We use the Adam W[Loshchilov and Hutter, 2017] optimizer with an initial learning rate 10 3, reduced by a factor of 0.9 every 30 epochs and a linear warmup period of 10 initial epochs. We use a dropout rate of 0.1 in all transformer layers and a gradient clipping of 1.0. We train our networks for 100 epochs with a total batch size of 96 on one 1080Ti GPU