Giters

tensorflow / skflow

Simplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

minimum loss is always set to training loss

mheilman opened this issue · comments

commented

The code in BaseMonitor.update currently sets the minimum loss so far as follows (link):

        if self.last_loss_seen < self.min_loss:
            self.min_loss = training_loss
            self.min_loss_i = self.steps

I believe the 2nd line there should be self.min_loss = self.last_loss_seen since the validation monitor sets that here.

commented

@mheilman Thanks for spotting that out! I just pushed the necessary change. You are welcome to submit PR directly to fix issues you found in the future once you signed CLA!

commented

You're welcome. Thanks for the quick fix. If I happen find anything else in the future, I'll submit a PR (once the CLA stuff is sorted out).