Timeline for Interpreting Validation and Training loss
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 22, 2016 at 8:59 | comment | added | Vikash Balasubramanian | Sorry, what i meant was every 100 epochs i am evaluating the model both on training and validation data, just for understanding this is not some production code, i just wanted to see what's going on. I just couldn't understand why the loss in training data could be less than validation data, except for the fact that i am evaluating on a batch of 50 training points and 2000 validation points, but since i am taking mean, that shouldn't matter right. | |
| Aug 19, 2016 at 14:28 | comment | added | LoulouChameau | Okay I'm not sure i understand perfectly what you are doing but from my experience never disable the dropout during the training even if it's 1 out of 100 it will mess up your network. Secondly i feel like you are confusing validation set and test set : validation set is used once every 100 epoch for example, to check the evolution of your model on a set who is not the training set. This allow you to perform early stoping of the training if necessary. Test set is what you test your model on when the training is complete. The repartition of the 3 is usually 50%/25%/25%. | |
| Aug 19, 2016 at 13:55 | comment | added | Vikash Balasubramanian | Yes! I also thought this was the issue initially. But both have the same. I am printing Training errors only for every hundredth epoch and in that epoch i am setting the keep probability = 1.0 and for validation also it is 1.0. | |
| Aug 19, 2016 at 12:22 | history | edited | LoulouChameau | CC BY-SA 3.0 |
added 13 characters in body
|
| Aug 19, 2016 at 12:16 | history | answered | LoulouChameau | CC BY-SA 3.0 |