Some issues with data preparation

xmindflow / DermoSegDiff

[MICCAI 2023] DermoSegDiff: A Boundary-aware Segmentation Diffusion Model for Skin Lesion Delineation

https://arxiv.org/abs/2308.02959

MIT License

57 stars 9 forks source link

Some issues with data preparation #3

Closed ChaiJinhao closed 7 months ago

ChaiJinhao commented 8 months ago

Inside of this folder the required numpy files will create inside of folder. Does this sentence mean to convert the images and Groundtruth into numpy format data and then put them in the same folder?

tobi-ore commented 8 months ago

When you run training.py, it checks for an np folder in the data_dir for the X and Y in .npy. However, the code is written so that if the numpy file does not exist, it checks the training_input and ground_truth folder for the .jpg or .png files and converts them all to a .npy file X and Y respectively, then save it in a folder called np in the data_dir.

bravo-hq commented 7 months ago

@ChaiJinhao Has the issue you encountered been satisfactorily addressed through the solution provided by @tobi-ore?