https://github.com/xieenze/Trans2Seg

https://github.com/xieenze/Trans2Seg

Last synced: 3 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/xieenze/Trans2Seg
• Owner: xieenze
• License: apache-2.0
• Created: 2021-01-21T06:46:33.000Z (about 4 years ago)
• Default Branch: master
• Last Pushed: 2022-10-15T20:01:31.000Z (over 2 years ago)
• Last Synced: 2024-08-03T10:19:52.678Z (6 months ago)
• Language: Python
• Size: 2.42 MB
• Stars: 144
• Watchers: 6
• Forks: 31
• Open Issues: 16
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome_transformer - Trans2Seg
• awesome_vision_transformer - code
• awesome_vision_transformer - code

README

        
# Transparent Transformer Segmentation

## Introduction

This repository contains the data and code for IJCAI 2021 paper [Segmenting transparent object in the wild with transformer](https://arxiv.org/abs/2101.08461).

## Environments

- python 3

- torch = 1.4.0

- torchvision

- pyyaml

- Pillow

- numpy

## INSTALL

```

python setup.py develop --user

```

## Data Preparation

1. create dirs './datasets/transparent/Trans10K_v2' 

2. put the train/validation/test data under './datasets/transparent/Trans10K_v2'. 

Data Structure is shown below.

```

Trans10K_v2

├── test

│   ├── images

│   └── masks_12

├── train

│   ├── images

│   └── masks_12

└── validation

    ├── images

    └── masks_12

```

Download Dataset: [Google Drive](https://drive.google.com/file/d/1YzAAMY8xfL9BMTIDU-nFC3dcGbSIBPu5/view?usp=sharing).

[Baidu Drive](https://pan.baidu.com/s/1P-2l-Q2brbnwRd2kXi--Dg). code: oqms

## Network Define

The code of Network pipeline is in `segmentron/models/trans2seg.py`.

The code of Transformer Encoder-Decoder is in `segmentron/modules/transformer.py`.

## Train

Our experiments are based on one machine with 8 V100 GPUs with 32g memory, about 1 hour training time.

```

bash tools/dist_train.sh $CONFIG-FILE $GPUS

```

For example:

```

bash tools/dist_train.sh configs/trans10kv2/trans2seg/trans2seg_medium.yaml 8

```

## Test

```

bash tools/dist_train.sh $CONFIG-FILE $GPUS --test TEST.TEST_MODEL_PATH $MODEL_PATH

```

## Citations

Please consider citing our paper in your publications if the project helps your research. BibTeX reference is as follows.

```

@article{xie2021segmenting,

  title={Segmenting transparent object in the wild with transformer},

  author={Xie, Enze and Wang, Wenjia and Wang, Wenhai and Sun, Peize and Xu, Hang and Liang, Ding and Luo, Ping},

  journal={arXiv preprint arXiv:2101.08461},

  year={2021}

}

```