AlexHex7 / Non-local_pytorch

Implementation of Non-local Block.
Apache License 2.0
1.57k stars 277 forks source link

net.train() again in demo_MNIST_train.py file #48

Open Dylee-y opened 2 years ago

Dylee-y commented 2 years ago

Hi, I started to learn pytorch a few months ago, so I might be questioning basic stuff.

in [Non-local_pytorch](https://github.com/AlexHex7/Non-local_pytorch)/demo_MNIST_train.py file, there was net.train() in the 50th line, within the training loop. after the testing loop, net.train() is called once more in the 70th line. I know that switching the network into training mode after the testing loop is important, but why is net.train() in the 70th line necessary when it would be called at the beginning of the training loop anyways?

AlexHex7 commented 2 years ago

@Dylee-y Hi.

I think that net.train() in the 70th line is unnecessary. Thanks for pointing it out. And I'll delete it.

Dylee-y commented 2 years ago

Ohh thank you very much!