Closed fordanic closed 6 years ago
This is because the number of LGG images is much smaller than that of HGG images.
Is it possible to train without a GPU?
Do I need to change the directory paths in the Job_test file to test the code with the dataset, even if i dont have a GPU?
A GPU is required for training. Otherwise the training process would be very slow.
Is there a reason why the LGG dataset have multiple entries in train_names_all_lggx3.txt.