This is a project that use U-Net to predict and classify the defect regions of steel images with Kaggle dataset Severstal: Steel Defect Detection
The defect masks of the steel images are encoded using Run-length encoding. First we decoded the labels to masks and indicated the defect regions on the images.
We built a U-Net model and trained it for 30 epochs
The metrics we use to evaluate our model is mean Dice coefficient.
The training result:
We display the prediction of a batch of images
