We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Hi
Thanks for your code.
I executed this code for cnn.py
All epoch print "AUC : 1.0" from start step to end step.
And, for argmax mean, all epoch print "0.0"
Is this a good execution result ?
My Env is below : Python 3.5.3 Anaconda 64 bit Windows 7 64bit
The text was updated successfully, but these errors were encountered:
I found the solution to avoid "AUC : 1.0"
in cnn.py change n_sample number . default is 10 I changed to 300 then, AUC is below
Epoch : 0 AUC : 0.896296296296 Epoch : 1 AUC : 0.890740740741 Epoch : 2 AUC : 0.890740740741 Epoch : 3 AUC : 0.902777777778 Epoch : 4 AUC : 0.897222222222 Epoch : 5 AUC : 0.894444444444 Epoch : 6 AUC : 0.891666666667 Epoch : 7 AUC : 0.889814814815 Epoch : 8 AUC : 0.884259259259 Epoch : 9 AUC : 0.894444444444 Epoch : 10 AUC : 0.894444444444 Epoch : 11 AUC : 0.899074074074 Epoch : 12 AUC : 0.900925925926 Epoch : 13 AUC : 0.892592592593 Epoch : 14 AUC : 0.896296296296 Epoch : 15 AUC : 0.9 Epoch : 16 AUC : 0.892592592593 Epoch : 17 AUC : 0.893518518519 Epoch : 18 AUC : 0.900925925926 Epoch : 19 AUC : 0.887962962963 Epoch : 20 AUC : 0.89537037037 Epoch : 21 AUC : 0.887962962963 Epoch : 22 AUC : 0.894444444444 Epoch : 23 AUC : 0.896296296296 Epoch : 24 AUC : 0.896296296296 Epoch : 25 AUC : 0.896296296296
Sorry, something went wrong.
No branches or pull requests
Hi
Thanks for your code.
I executed this code for cnn.py
All epoch print "AUC : 1.0" from start step to end step.
And,
for argmax mean, all epoch print "0.0"
Is this a good execution result ?
My Env is below :
Python 3.5.3
Anaconda 64 bit
Windows 7 64bit
The text was updated successfully, but these errors were encountered: