Timeline for My training accuray is 1.0 but the predictions on the training data are wrong
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 13, 2019 at 16:25 | comment | added | Keren | It could be, how can I check that? | |
| Jan 13, 2019 at 23:02 | comment | added | Juan Antonio Gomez Moriano | Predicting means doing a forward propagation... which you do during training anyway... is there any chance you are saving your model, and then restoring it (from a file I mean) in an incorrect manner? | |
| Jan 12, 2019 at 14:19 | comment | added | Keren | Yes. Again, this is in no way me trying to actually teach my neural network or see how it's working, it's just me trying to debug and see what the issues are. If the training accuracy is 1.0 but when I try to predict the outcome for the SAME data as my training and the outcome is wrong, then how is my training accuracy 1.0? | |
| Jan 9, 2019 at 23:39 | comment | added | Juan Antonio Gomez Moriano | Just for the record, are you saying that the three pictures you use to train are the same ones you try to predict? | |
| Jan 9, 2019 at 10:25 | comment | added | Keren | Hey, thanks for the answer. Of course I am not trying to teach my cnn with just three pictures. I am at a stage of debugging issues I had when trying to run it on a larger group of images. In order to debug, I first entered three pictures of the same class. Of course I am overfitting, but the question is: how is it possible that the training accuracy is 1.0 if the predictions for the same training data are wrong? | |
| Jan 9, 2019 at 0:50 | history | answered | Juan Antonio Gomez Moriano | CC BY-SA 4.0 |