- 一直對於model.eval()和torch.no_grad()有些疑惑
- 之前看博客說，只用torch.no_grad()即可
- 但是今天查資料，發現不是這樣，而是兩者都用，因為兩者有着不同的作用
- 引用stackoverflow:
Use both. They do different things, and have different scopes.
with torch.no_grad： disables tracking of gradients in autograd.
model.eval()： changes the forward() behaviour of the module it is called upon. eg, it disables dropout and has batch norm use the entire population statistics