sheardetect
Science Score: 67.0%
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
Found 9 DOI reference(s) in README -
✓Academic publication links
Links to: zenodo.org -
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (8.3%) to scientific vocabulary
Repository
Basic Info
- Host: GitHub
- Owner: ILKGit
- License: mit
- Language: Python
- Default Branch: main
- Size: 3.07 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
ShearDetect
A defekt detection model for shearographic images. This model is based on a object detection model with faster R-CNN and ResNet-50 approach.
Getting Started
Clone the Code
git clone https://github.com/ILKGit/ShearDetect
Requirements
- Python >3.6
- CUDA 11.3 or higher
Install all the python dependencies using pip
pip install -r requirements.txt
Dataset
A dataset can be find here:
Strucutre of a custom Dataset has to be as following: ``` |-----train |-----annotations |-----.json |-----images |-----.tif |-----validation |-----annotations |-----.json |-----images |-----.tif |-----test |-----annotations |-----.json |-----images |-----.tif
*.json-files contain the following annotations and infos
{ "fileID": "fspecimenname+imagename", "Dataset": "specimenname", "image": "imagename", "defect": [[x1, y1, x2, y2],], #bounding box of defects as list "specimen": [[x1, y1, x2, y2],]. #bounding box of specimens as list } ```
Training / Evaluation
python train_model.py --model=NAME OF YOUR MODEL --epochs=NUMBER OF EPOCHS --save_period=CHECKPOINTS SAVE PERIOD
Detection
python detect_model.py --model=DIR to Model --data=DIR TO DATA --pred=DIR TO SAVE RESULTS
Citation (CITATION.cff)
# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: ShearDetect
message: 'If you use this software, please cite it as below.'
type: software
authors:
- orcid: 'https://orcid.org/0000-0002-6817-1020'
given-names: Christian
family-names: Düreth
email: christian.duereth@tu-dresden.de
affiliation: >-
TU Dresden - Institute for Lightweight
Engineering and Polymer Technology
GitHub Events
Total
Last Year
Dependencies
- Pillow ==9.0.1
- PyWavelets ==1.2.0
- PyYAML ==6.0
- albumentations ==1.1.0
- archspec ==0.1.2
- backoff ==1.10.0
- cachetools ==5.0.0
- cleo ==0.8.1
- clikit ==0.6.2
- crashtest ==0.3.1
- cycler ==0.11.0
- fonttools ==4.29.1
- google-api-core ==2.7.1
- google-auth ==2.6.2
- googleapis-common-protos ==1.56.0
- imageio ==2.16.0
- jeepney ==0.4.3
- kiwisolver ==1.3.2
- labelbox ==3.17.0
- matplotlib ==3.5.1
- ndjson ==0.3.1
- networkx ==2.6.3
- numpy ==1.22.2
- opencv-python ==4.5.5.62
- opencv-python-headless ==4.5.5.62
- pastel ==0.2.1
- plotly ==5.5.0
- protobuf ==3.19.4
- ptyprocess ==0.6.0
- pyasn1-modules ==0.2.8
- pycocotools ==2.0.4
- pydantic ==1.9.0
- pytigre ==2.2.0
- qudida ==0.0.4
- rsa ==4.8
- scikit-image ==0.19.1
- scikit-learn ==1.0.2
- scipy ==1.8.0
- tenacity ==8.0.1
- tifffile ==2022.2.9
- tomlkit ==0.7.0
- torch ==1.10.2
- torchaudio ==0.10.2
- torchinfo ==1.6.5
- torchsummary ==1.5.1
- torchvision ==0.11.3
- tqdm ==4.63.1
- typing-extensions ==4.1.1