The code and data are used for the article Automatic Tunnel Crack Inspection Using an Efficient Mobile Imaging Module and a Lightweight CNN which is under review for the journal of IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS.
The code was tested with Anaconda and Python 3.6. After installing the Anaconda environment:
Install dependencies:
conda install --yes --file requirements.txt
Follow steps below to train your model:
- Configure your dataset path in
mypath.py - run visdom
python -m visdom.server - Input arguments: (see full input arguments via python train.py --help):
python train.py
If you want to test the image (see full input arguments via python test.py --help), run:
python test.py