-
Notifications
You must be signed in to change notification settings - Fork 188
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
Weird output of xttrain()(1.#INF00) #17
Comments
The iris data set uses floating point inputs and string outputs.
5.0,3.3,1.4,0.2, Iris-setosa
...
5.7,2.8,4.1,1.3, Iris-versicolor
...
6.3,2.9,5.6,1.8, Iris-virginica
Try remapping these strings to three floating point outputs
5.0,3.3,1.4,0.2, 0,0,1
...
5.7,2.8,4.1,1.3, 0,1,0
...
6.3,2.9,5.6,1.8, 1,0,0
If you can get the data like that then there shouldn't be need to modify
test.c (apart from the input file name, the nips, and the nops, and
ofcourse nhid and learning rate to your discretion).
Let me know how it goes!
…On Wed, May 16, 2018 at 1:17 PM, derlozi ***@***.***> wrote:
Hi, I'm trying to write a small program to train a network on the iris
dataset. (https://archive.ics.uci.edu/ml/datasets/iris). When training,
xttrain returns values that are printed as 1.#INF00. I don't know whether
the fault is on the library's side or my fault. Another weird thing is that
when I run the program in debug-mode, it works just fine. Here is the
repository with my code: https://github.com/derlozi/TINN-Iris-Dataset I
hope that you can help me.
Thanks in advance!
—
You are receiving this because you are subscribed to this thread.
Reply to this email directly, view it on GitHub
<#17>, or mute the thread
<https://github.com/notifications/unsubscribe-auth/AGrSKG9AAbko9aYfUYDQh5CBBRm3Yxo-ks5tzIlOgaJpZM4UB99F>
.
|
I revisited the project and found the bug, I didn't consider line endings when reading out of a file and some data was not initialized correctly. I fixed it and it now works like a charm. |
Thanks for checking back |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, I'm trying to write a small program to train a network on the iris dataset. (https://archive.ics.uci.edu/ml/datasets/iris). When training, xttrain returns values that are printed as 1.#INF00. I don't know whether the fault is on the library's side or my fault. Another weird thing is that when I run the program in debug-mode, it works just fine. Here is the repository with my code: https://github.com/derlozi/TINN-Iris-Dataset I hope that you can help me.
Thanks in advance!
The text was updated successfully, but these errors were encountered: