can't run on large datasets

When I correctly follow the steps in the auto3dseg_hello_world.ipynb notebook, set the corresponding paths and parameters, and run it in an environment with 48G of GPU memory, I encounter the error RuntimeError: Pin memory thread exited unexpectedly while attempting to train on a dataset with 300 .nii.gz images. In contrast, when using a dataset with 20 images, the training proceeds smoothly under the exact same conditions. During the training process with the 300-image dataset, I monitored the GPU memory usage and found it to be less than 70%. However, the error keeps occurring inexplicably. Could there be an issue with the get_data step?

Start by running auto3dseg_hello_world.ipynb with the reported paths and parameters, comparing the 20-image and 300-image datasets on a 48G GPU environment. Inspect the get_data step and the point where training raises “Pin memory thread exited unexpectedly.” Done means the notebook can train on the larger dataset without this error, with the smaller-dataset behavior preserved.