Dataset - Image-Driven Prediction of Fatigue Crack Growth in Metal Materials via Spatiotemporal Neural Network

File #1 "DataFromDIC_CSV" contains displacement fields obtained from DIC measurement for 19 specimens. The data is saved in .csv format.
File #2 "DataAfterInterpolation_PT" contains interpolated displacement fields from the DIC results for 19 specimens. The data is saved in .pt format. They are used as input for training, validation and testing. We use open-source program "Griddata" to do the interpolation.
File #3 "TrainedModel_PT" contains the trained neural networks used in the paper.
File #4 "Cycles vs Crack Length.xlsx" shows the relations between fatigue cycles and crack lengths measured from .PT files. We only measured crack lengths for 4 specimens used in the paper.
File #5 "Readme.txt" shows the naming system for the folders in File #1 and #2.