Open qibin-google opened 6 years ago
https://github.com/chiphuyen/stanford-tensorflow-tutorials/blob/51e53daaa2a32cfe7a1966f060b28dbbd081791c/examples/07_convnet_layers.py#L146
I don't understand how setting self.training = False turns training off in dropout. self.training is passed as an argument when building dropout layer. After the whole network is built, changing self.training should not change the network.
https://github.com/chiphuyen/stanford-tensorflow-tutorials/blob/51e53daaa2a32cfe7a1966f060b28dbbd081791c/examples/07_convnet_layers.py#L146
I don't understand how setting self.training = False turns training off in dropout. self.training is passed as an argument when building dropout layer. After the whole network is built, changing self.training should not change the network.