Application to interact with a custom CNN model with VGG16 as the base model for dental X-Ray image classification.
Training was done using dental x-rays from the UFBA_UESC dental images dataset which includes structural variations regarding the number of teeth, restorations, implants, appliances, and the size of the mouth and jaws.
Using this app, you can train your model with specific hyper-parameters and use the pretrained model to classify an image.
For training a custom model
For classifying an image
To prepare the environment using poetry and python3.10
make envTo run it
streamlit run main.py You developed an amazing feature or fixed a bug, and you need to push you changes to git. To make sure we have a consistent way of writing the code, scripts for formatting are ready to be used.
Before pushing you changes, we need to have your code formatted, checked by mypy, tested, and documented. That's exactly what this command does:
make prepareTo avoid running around requirements.txt files and adding dependencies manually, we use Poetry to manage the dependencies.
To add a new library to poetry:
poetry add <name_of_library>To specify a constraint when adding a package:
# Specific library version
poetry add pendulum@^2.0.5
# Minimum library version
poetry add "pendulum>=2.0.5"
# Always use the latest version (not recommended)
poetry add pendulum@latest In order to get the latest versions of the dependencies and to update the poetry.lock file
poetry updateIf you just want to update a few packages and not all, you can list them as such:
poetry update requests tomlTo keep the virtualenv and clean everything else
make cleanFor a deep cleaning
make clean-allGil Silva, Luciano Oliveira, Matheus Pithon, Automatic segmenting teeth in X-ray images: Trends, a novel data set, benchmarking and future perspectives, Expert Systems With Applications (2018), doi: 10.1016/j.eswa.2018.04.001