What does model.eval() do in pytorch?
Feb 1
When should I use .eval()? I understand it is supposed to allow me to "evaluate my model". How do I turn it back off for training?
Example training code using .eval().
pytorch
python1 answer
Accepted answer · original discussion
Feb 1
model.eval() is a kind of switch for some specific layers/parts of the model that behave differently during training and inference (evaluating) time. For example, Dropouts Layers, BatchNorm Layers etc. You need to turn them off during model evaluation, and .eval() will do it for you. In addition, the common practice for evaluating/validation is using torch.no_grad() in pair with model.eval() to turn off gradients computation:
# evaluate model:
model.eval()
with torch.no_grad():
...
out_data = model(data)
...
BUT, don't forget to turn back to training mode after eval step:
# training step
...
model.train()
...
3 question comments
Use comments to ask for clarification. Post a solution as an answer.
Feb 1
May 12
mdl.is_eval()?Dec 19
self.training via self.training = training recursively for all modules by doing self.train(False). In fact that is what self.train does, changes the flag to true recursively for all modules. see code: github.com/pytorch/pytorch/blob/…