search

pumpikano / tf-dann

Domain-Adversarial Neural Network in Tensorflow
MIT License
628 stars 224 forks source link

Strange results after porting from Python2 to Python3 #9

Closed jaejun-yoo closed 6 years ago

jaejun-yoo commented 7 years ago

I have tried to fix the reason of errors discussed in this other issue and found the way to avoid using "one_hot()" function in tensorflow. The code runs fine but the results are strange. As I have not touched your code except the three things ("one_hot()" function, division (/) -> (//), object.next() -> next(object)), I cannot find other reason to have those results. Could you please visit my github repository and check if the results are wrong and maybe figure out the reason...? You can see the results from three different amendments I tried.

jaejun-yoo commented 7 years ago

I found that these issues are now resolved by updating the tensorflow version to 1.0.0.rc2. Here, you can find how I modified pumpikano's original work to deal with python version change from 2~ to 3.