Error bcz of loading all images

[akirs82]

Hello ydwen,
I am trying to load dataset from QMUL-Survface. I am getting the following error,

Traceback (most recent call last): File "train.py", line 92, in <module> mp.spawn( File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 230, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 188, in start_processes while not context.join(): File "/opt/conda/lib/python3.8/site-packages/torch/multiprocessing/spawn.py", line 130, in join raise ProcessExitedException( torch.multiprocessing.spawn.ProcessExitedException: process 0 terminated with signal SIGKILL

I think this is happening bcz of three lines where the all image data are stored in a list in a single stretch as the training data is 2,26,207 images. Can you tell how to batch load this data such that it will not hamper the training process ?

regards
akirs