Click here to Skip to main content
15,907,281 members
Please Sign up or sign in to vote.
1.00/5 (2 votes)
See more:
I am trying to build a neural network to classify data, my data are thousands of txt files, every file represent a 2D dimensional array with values 1 or -1, every array represent one configuration, and the labels that I should have are just two labels

I need a startup code snippet that build the network and train it

What I have tried:

I converted all of these txt files into images of black and white, and I used ML.NET through VS to train a network that is already built (I don't know anything about the structure of this network, it is hidden) then I wrote code to test it and it works very good

but this is nit what I need, I need to classify them without the need to convert them to images, and I want to build my own neural network, that I can control its structure at any point

Note: I just started this field, don't blame me if you find my question is very naïve or simple
Posted
Comments
[no name] 18-May-23 10:57am    
If this particulare neural net expects an "image file", a text file won't do it. The text may represent image pixels, but that's still not an "image file". Even if it did work, it would probably be using a "plugin" which is effectively what you created (according to your post).
Sabry1905 18-May-23 12:35pm    
I don't want to use images, I want to use txt files, because my configuration files will be higher dimensions more than two.

What I need is a startup code that build the network and train it, a network that expects txt files as an input

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900