Source Code of NeurIPS21 paper: Recognizing Vector Graphics without Rasterization

Last update: Dec 20, 2022

Overview

YOLaT-VectorGraphicsRecognition

This repository is the official PyTorch implementation of our NeurIPS-2021 paper: Recognizing Vector Graphics without Rasterization.

Environments

conda create -n your_env_name python=3.8
conda activate your_env_name
sh deepgcn_env_install.sh

YOLaT

1. Data Preparation

Floorplans

a) Download and unzip the Floorplans dataset to the dataset folder: data/FloorPlansGraph5_iter

b) Run the following scripts to prepare the dataset for training/inference.

python utils/svg_utils/build_graph_bbox.py

Diagrams

a) Download and unzip the Diagrams dataset to the dataset folder: data/diagrams

b) Run the following scripts to prepare the dataset for training/inference.

python utils/svg_utils/build_graph_bbox_diagram.py

2. Training & Inference

Floorplans

cd cad_recognition
CUDA_VISIBLE_DEVICES=0 python -u train.py --batch_size 4 --data_dir data/FloorPlansGraph5_iter --phase train --lr 2.5e-4 --lr_adjust_freq 9999999999999999999999999999999999999 --in_channels 5 --n_blocks 2 --n_blocks_out 2 --arch centernet3cc_rpn_gp_iter2  --graph bezier_cc_bb_iter --data_aug true  --weight_decay 1e-5 --postname run182_2 --dropout 0.0 --do_mixup 0 --bbox_sampling_step 10

Diagrams

cd cad_recognition
CUDA_VISIBLE_DEVICES=0 python -u train.py --batch_size 4 --data_dir data/diagrams --phase train --lr 2.5e-4 --lr_adjust_freq 9999999999999999999999999999999999999 --in_channels 5 --n_blocks 2 --n_blocks_out 2 --arch centernet3cc_rpn_gp_iter2  --graph bezier_cc_bb_iter --data_aug true  --weight_decay 1e-5 --postname run182_2 --dropout 0.0 --do_mixup 0 --bbox_sampling_step 5

Citation

  @inproceedings{jiang2021recognizing,
  title={{Recognizing Vector Graphics without Rasterization}},
  author={Jiang, Xinyang and Liu, Lu and Shan, Caihua and Shen, Yifei and Dong, Xuanyi and Li, Dongsheng},
  booktitle={Proceedings of Advances in Neural Information Processing Systems (NIPS)},
  volume={34},
  number={},
  pages={},
  year={2021}}

Source Code of NeurIPS21 paper: Recognizing Vector Graphics without Rasterization

Related tags

Overview

YOLaT-VectorGraphicsRecognition

Environments

YOLaT

1. Data Preparation

Floorplans

Diagrams

2. Training & Inference

Floorplans

Diagrams

Citation

Owner

Microsoft

UT-Sarulab MOS prediction system using SSL models

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)

Hysterese plugin with two temperature offset areas

This repo is duplication of jwyang/faster-rcnn.pytorch

3DMV jointly combines RGB color and geometric information to perform 3D semantic segmentation of RGB-D scans.

Code for reproducing our analysis in the paper titled: Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

Dcf-game-infrastructure-public - Contains all the components necessary to run a DC finals (attack-defense CTF) game from OOO

Kaggle | 9th place (part of) solution for the Bristol-Myers Squibb – Molecular Translation challenge

[ICRA 2022] An opensource framework for cooperative detection. Official implementation for OPV2V.

A python/pytorch utility library

[CVPR2021] Invertible Image Signal Processing

Signals-backend - A suite of card games written in Python

💡 Type hints for Numpy

Happywhale - Whale and Dolphin Identification Silver🥈 Solution (26/1588)

Event queue (Equeue) dialect is an MLIR Dialect that models concurrent devices in terms of control and structure.

Exploiting Robust Unsupervised Video Person Re-identification

Code for Ditto: Building Digital Twins of Articulated Objects from Interaction

Code for our paper Domain Adaptive Semantic Segmentation with Self-Supervised Depth Estimation

Translation-equivariant Image Quantizer for Bi-directional Image-Text Generation

Federated Learning - Including common test models for federated learning, like CNN, Resnet18 and lstm, controlled by different parser