aakash-saboo

Results 7 comments of aakash-saboo

Is the code written only for nn.NLLL() loss?

Hi Pierre! Thanks for such a quick response. Although I did figure out the regression way but didnt consider changing the final loss as you mentioned. Instead what I did...

Training the network gives high AUC but low ACC

Hey the threshold used to calculate accuracy is 0.5 you can change the threshold to reach desired accuracy. You should focus on AUC and not accuracy as accuracy changes with...

ValueError: bad marshal data (unknown type code) with tensorflow 1.4.0,keras 2.2.1 and python 3.5.2

This code uses keras 2.1.2 and python 3.5. In the previous version of keras- saving of Lambda layer is reported to pose some errors. This error has been resolved in...

Error in Generalized contrastive loss

Hi This error will come when "sort" function is used. "sort" function (in its current definition), will only work when there are NO two elements which are greater than SAME...

Error in Generalized contrastive loss

@chentingpc Thank you so much for your response. Yes, tf.sort is working just fine. But I liked the implementation of the `sort` function. Is there any way you can tell...

Error in Generalized contrastive loss

@chentingpc Thanks a lot! will try that out.

ValueError: vec Nan

Hey, Thanks for your quick response. I am using nn.BCEWithLogits but not L2. I am using L1 loss. Ill try replacing it with L2.