RuntimeError: view size is not compatible with input tensor's size and stride (at least one dimension spans across two contiguous subspaces). Use .reshape(...) instead.

[Weigaa]

When I use the scripts:
python train.py --auxiliary --batch_size=32 --init_ch=128 --layer=24 --arch='[2, 2, 0, 2, 1, 2, 0, 2, 2, 3, 2, 1, 2, 0, 0, 1, 1, 1, 2, 1, 1, 0, 3, 4, 3, 0, 3, 1]' --model_ema --model-ema-decay 0.9999 --auto_augment --epochs 1500
to train the cifar-10 dataset, I met this runtime error
How could I fix this?
I just use one P100 GPU
my pytorch version is 1.11.0+cu113