When I run the code below:
learn.precompute=False
learn.fit(1e-2, 3, cycle_len=1)
GPU crashed and computer rebooted. If not run learn.precompute=False ,then learn.fit(1e-2, 3, cycle_len=1) will run normally.
I use my own GPU Titan Xp and Ubuntu 18.04 system and cuda9.2. pytorch 0.4.1 support cuda 9.2.