Possible error in computing performance metrics

[bbrito]

@amiryanj I realized that in the script train.py in 577 and so on you divide the ade_avg etc by n_test_samples which does not match the number of times that you add up those error in the for loop in line 532, if you check the ii index. Do you have any explanation for this?

[bbrito]

I actually create some variables to count the number os samples that you are accumulating the error, and for the hotel dataset, the number of n_test_samples should be 181 which equals the size of the the_batches variables minus the train_size. I guess there is some mistake with the n_train_samples computation.

[amiryanj]

Probably it should be because of just_one variable at the following line:
https://github.com/amiryanj/socialways/blob/0b13f2da00a071e0c5546614ea6f579e3139c094/train.py#L668
This is supposed to be True just for Toy Dataset.