728x90
- model.eval() will notify all your layers that you are in eval mode, that way, batchnorm or dropout layers will work in eval mode instead of training mode.
- torch.no_grad() impacts the autograd engine and deactivate it. It will reduce memory usage and speed up computations but you won’t be able to backprop (which you don’t want in an eval script).
728x90
'Dic' 카테고리의 다른 글
| Empirical risk minimization (0) | 2019.11.17 |
|---|---|
| Graph Convolutional Networks (0) | 2019.11.14 |
| Semi-supervised learning (0) | 2019.10.31 |
| explicit and implicit solution (0) | 2019.10.28 |
| PCA (0) | 2019.10.24 |