Cannot allocate memory

[zxshi]

I use python train.py --vtf --pretrained imagenet --loss-on-center --batch-size 6 --optim adamw --learning-rate 5e-4 --lr-scheduler noam --basenet resnet34 --max-epochs 100 --data-fold fold0 --log-dir runs/fold0 --resume runs/fold0/checkpoints/last-checkpoint-fold0.pth to train my dataset. My train data have 71712 images and valid data have 7968 images. I got this error:

[xuyuan]

The dataset tries to preload all image to RAM, you can try to disable preload in line:

pytorch-saltnet/train.py

Line 107 in a3e63b3

transform=train_transform, preload=True, mask_threshold=args.drop_mask_threshold)

and

pytorch-saltnet/train.py

Line 109 in a3e63b3

transform=valid_transform, preload=True)