Hi,
I am training resnet18 with pytorch. I would like to do the following experiments:
step 1: trian resnet18.
step 2: train resnet18 again.
how to remove all random and use fixed in my code?
Hi,
I am training resnet18 with pytorch. I would like to do the following experiments:
step 1: trian resnet18.
step 2: train resnet18 again.
how to remove all random and use fixed in my code?
You can set the same random seed for both training process.
in my code, I do:
`import random
random.seed(5)
torch.random.initial_seed()
torch.cuda.manual_seed_all(5)
torch.cuda.manual_seed_all(5)
torch.backends.cudnn.deterministic=True
random.seed(5)
torch.random.initial_seed()
torch.cuda.manual_seed_all(5)`
there is still something randomly changes sometimes. did I missed anything else?
or should I do the upper code in all related files? or I only need to do the upper code in the beginning of my project code?