ChanServ changed the topic of #mlpack to: "mlpack: a fast, flexible machine learning library :: We don't always respond instantly, but we will respond; please be patient :: Logs at http://www.mlpack.org/irc/
IrinaMats has joined #mlpack
IrinaMats has quit [Client Quit]
ImQ009 has joined #mlpack
jenkins-mlpack2 has quit [Ping timeout: 265 seconds]
jenkins-mlpack2 has joined #mlpack
ImQ009 has quit [Read error: Connection reset by peer]
< himanshu_pathak[> zoq: I was working on Neural Turing PR I tried the Gradient Test to compile seperately it was working but when I did make test it failed. I cannot able to understand why Is it so. Can you suggest what can I do for this???
< himanshu_pathak[> I think the problem is with gradient.
< himanshu_pathak[> * I think the problem is with calculating gradient.
< zoq> himanshu_pathak[: When you run the test make sure to use a new random seed for each run, e.g. by setting math::RandomSeed(std::time(NULL));
< zoq> in the test case
< zoq> himanshu_pathak[: Will take a look at the gradient test.
< himanshu_pathak[> zoq: Ok I will try it thanks for looking into this
< himanshu_pathak[> zoq: Sorry It was a silly mistake. Feeling like I should bang my head on the table. I wasted a lot of time on this. Test is working using Sequential layer There is problem with FFN I will try to look into that and update changes thanks for helping.
< himanshu_pathak[> * zoq: Sorry It was a silly mistake that I ahve done. Feeling like I should bang my head on the table. I wasted a lot of time on this. Test is working using Sequential layer There is problem with FFN I will try to look into that and update changes thanks for helping.
< himanshu_pathak[> * zoq: Sorry It was a silly mistake that I have done. Feeling like I should bang my head on the table. I wasted a lot of time on this. Test is working using Sequential layer There is problem with FFN I will try to look into that and update changes thanks for helping.