questions about the procedure of test()

[jaredwei01]

In the method "test" in model.py, it seems that there is a module about training the model using the test data.(from line 236 to 244 ).
I wonder why we should use test golden label here and in line 230, is it used as a validation ?
I'm new in tensorflow, please pardon me if there were errors in my understanding.

[ganeshjawahar]

Yes, its a bug. Change that portion to this:
loss = self.sess.run([self.loss], feed_dict={ self.input: x, self.time: time, self.target: target, self.context: context})
so that we just seek the loss without doing backprop.

Also there is a bug in data.py. We need to discard input samples from the class label: 'conflict' as suggested by the author.

Send a PR if someone had fixed this successfully.

[sidoki]

Hi @ganeshjawahar,

can you elaborate more about bug in data.py ? What should i change? Thank you!