Network giving ambiguous results.

[Sajid3]

I am doing 2 class classification using BLVNET-TAM. When i had given data for validation the accuracy is coming good but on testing same data accuracy is bad. for instance , validation probabilities are somewhat like [0.2 , 0.8] while during testing probabilities are like [0.5.. , 0.499..] on same data.

[chunfuchen]

do you mean that when giving the same data, the output prob is different? if so, do you mind providing the scripts you are using for both validation and test? thanks.

I used test.py to test/validate the same data (something-something v2) and give me the same results.