Data

Tools

Indexes

Applications

Experiments

Open Source Science

pbd

PBD : Plastic Bottle Dataset for Defect Detection

https://github.com/lzy-coder/pbd

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (8.9%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

PBD : Plastic Bottle Dataset for Defect Detection

Basic Info
  • Host: GitHub
  • Owner: lzy-coder
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 15.5 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

PBD: Plastic Bottle Dataset for Defect Detection

Zhenyuan Lin, Danhua Liu*, Lai Wei, Yubo Dong

PBD

  • Plastic Bottle Body : 500 images with four common defect types (stain, concave, score and squeeze).
  • Plastic Bottle Shoulder : 3,463 images with two common defect types (stain and no_burr) and one bottle neck positioning marker (pipe).

Figure 1: Some sample images from the Plastic Bottle Body dataset along with their corresponding annotations

Figure 2: Distribution of defect annotation features for the Plastic Bottle Body dataset

Figure 3: Some sample images images from the Plastic Bottle Shoulder dataset along with their corresponding annotations

Figure 4: Distribution of defect annotation features for the Plastic Bottle Shoulder dataset

Usage

This dataset is allowed for academic purposes only.

Code Configuration

This repository is modified from MMDetection. The original MMDetection repository can be found at https://github.com/open-mmlab/mmdetection.

1. Installation

  • Anaconda bash conda create -n PBD python=3.8
  • Pytorch bash # conda conda install pytorch==2.0.0 torchvision==0.15.0 torchaudio==2.0.0 pytorch-cuda=11.7 -c pytorch -c nvidia # or pip pip install torch==2.0.0 torchvision==0.15.1 torchaudio==2.0.1
  • Other Extra Dependencies ```bash # for mmcv, you can see in https://mmcv.readthedocs.io/zh-cn/latest get_started/installation.html pip install mmcv==2.0.0 -f https://download.openmmlab.com/mmcv/dist/cu117/torch2.0/index.html

for mmdetection

pip install -r requirements.txt pip install -v -e . # or "python setup.py develop" ```

2. Prepare Dataset

The PBD Dataset can be downloaded from the Baidu Cloud | Google Drive | Quark Cloud

After downloading and extracting the dataset, place it in the PBD/dataset folder.

3. How to RUN?

To start training with PBD: ```bash

In PBD folder

python tools/train.py {config_file}

Example:

python configs/atss/atssr50fpn1xcoco.py

```

4. Acknowledgment

This work is forked from MMdetection Repository https://github.com/open-mmlab/mmdetection.

Citation

@inproceedings{PBD, author = {Zhenyuan Lin,Danhua Liu,Lai Wei, Yubo Dong} title = {PBD: Plastic Bottle Dataset for Defect Detection} booktitle = {ICASSP} year = {2025} }

Owner

  • Name: henshen
  • Login: lzy-coder
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMDetection Contributors"
title: "OpenMMLab Detection Toolbox and Benchmark"
date-released: 2018-08-22
url: "https://github.com/open-mmlab/mmdetection"
license: Apache-2.0

GitHub Events

Total
  • Watch event: 1
  • Push event: 5
Last Year
  • Watch event: 1
  • Push event: 5