search

tkuanlun350 / 3DUnet-Tensorflow-Brats18

3D Unet biomedical segmentation model powered by tensorpack with fast io speed
202 stars 69 forks source link

use 3d non-medical dataset #3

Open huazai-1994 opened 5 years ago

huazai-1994 commented 5 years ago

First of all, let me congratulate you on this great project! Many Thanks for making it public! I am trying to make it work with my own 3d non-medical dataset.so i want to consult you that how to make the standary trainning dataset with the origingal dataset which has the format of ".raw"(both of the data and the label)?could you please share me some code? I have never done with 3D dataset .so I really need your help.Thanks a lot

tkuanlun350 commented 5 years ago

The basic idea is that you convert your data into 3d numpy array. For example, you can use whatever tool to convert .raw file into the format that python can handle (.jpg, .png) and carefully make sure the resolution or other properties are not corrupted. Then use standard libraries such as opencv to handle the rest.

One issue need to be considered is that you have to make sure the memory usage is not too high. If that is the case, you have to crop the data during training and assemble them back when evaluation.