Timeline for Keras: why does loss decrease while val_loss increase?
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 19, 2018 at 18:07 | comment | added | matt_m | This can be a bit late, but are you sure that your data is what you think it is? Specifically it is very odd that your validation accuracy is stagnating, while the validation loss is increasing, because those two values should always move together, eg. the decrease in the loss value should be coupled with proportional increase in accuracy. You can see that in the case of training loss. As the training loss is decreasing so is the accuracy increasing. However this is not the case of the validation data you have. Therefore I would definitely looked into how you are getting validation loss and ac | |
| Nov 1, 2017 at 12:49 | answer | added | Shadi | timeline score: 11 | |
| Feb 23, 2017 at 13:27 | vote | accept | user1367204 | ||
| Feb 7, 2017 at 1:44 | comment | added | user1367204 | I used [1.000, 0.100, 0.010, 0.001] | |
| Feb 6, 2017 at 22:28 | comment | added | Hugh | You case is strange because your validation loss never got smaller. Your learning rate is suspiciously high, typical learning rates are about 0.001. What range of learning rates did you use in the grid search? | |
| Feb 6, 2017 at 21:25 | answer | added | photox | timeline score: 30 | |
| Feb 6, 2017 at 17:11 | history | asked | user1367204 | CC BY-SA 3.0 |