-
Notifications
You must be signed in to change notification settings - Fork 39
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Loss barely decreases and accuracy barely increases. #3
Comments
How are you running it and with which versions of Keras, Theano/TF? |
Tensorflow 0.11 and the latest Keras version. That shouldn't make a difference though, right? |
Maybe, I know that the master version of Theano was breaking this code because they changed something in the random generator so one of the calculations was resulting in NaN. I don't know about TF. |
With TF 1.0.0 & Keras 1.2.2, i met the issue mentiond by sixsamuraisoldier. My "~/.keras/keras.json" is: and part info about training loss is as below: Using TensorFlow backend. |
I don't have a ML box now to check it again. I'm pretty sure that all the problems are in the random column selection as it's a little hackish. |
actually I meet this problem too, but I add the --deepest in command and it works fine and my backend is tensorflow, I ran 40 epoches and got the accuracy of 0.69 while 20/40 epoches, but I did not run further since it costs a lot of time. |
|
I am thinking maybe there is some problem when doing the dropout task, but I am still not so familiar with this so I will try it too today |
I have the same with Keras/TF. In addition to a couple of bugs related to using TF as a backend. some parts of the code will run only if you use Theano as a backend. I can work on fixing those TF bugs |
I guess this was fixed by #4 and #5 so I'm closing it. Please reopen if that wasn't the case. |
@WayneZww @aicentral I meet same problem, when i set global_p, the loss is low and acc doesn't increase. Do you solve this problem? |
I meet the same problem with Keras/TF. the loss not decreases and the predicted label seems is the same label, therefore validation acc is 0.1 @snf |
Hi @EigenvectorOfFate, unfortunately too much changed in Keras and TF since I made this code. |
So I've been training for a while now (40 epochs) and my accuracy hasn't increased at all (and my loss hasn't decreased either).
I've reproduced this with both Adam and SGD.
The text was updated successfully, but these errors were encountered: