SEED = 0
torch.manual_seed(SEED)
torch.cuda.manual_seed_all(SEED)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
np.random.seed(SEED)
random.seed(SEED)
# References
https://discuss.pytorch.org/t/what-does-torch-backends-cudnn-benchmark-do/5936/7
What does torch.backends.cudnn.benchmark do?
Does it work to turn it on for training (where I have a constant input size) and turn it off for validation (where my input size isn’t constant)? Do I just set the constant before doing my validation?
discuss.pytorch.org
'LANGUAGE > PyTorch' 카테고리의 다른 글
| Solution for Runtime Error: CUDA out of memory (0) | 2020.12.01 |
|---|---|
| BiLSTM (0) | 2019.08.01 |
| PyTorch Examples (0) | 2019.08.01 |
| Random Seed Initialization for Reproducibility ... (0) | 2019.07.15 |
| Difference between model.eval() and torch.no_grad() (0) | 2019.07.15 |