Skip to content
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

how can i train the Neural Network with my own Training Pictures? #141

Open
ammar88400 opened this issue Feb 10, 2022 · 1 comment
Open

Comments

@ammar88400
Copy link

let's say i have a list of Images ..how do i convert my images into F64matrix Form so i can train them with my Neural Network ..and how do i test the Network with an Image at the End
could you please make an example of this because you didn't mention that in the examples, you also didn't mention how to test the Network using a real Image..

Thanks in Advance

@ammar88400 ammar88400 changed the title How can i train the Neural Network with my own Train Pictures? how can i train the net with my own Training Pictures? Feb 10, 2022
@ammar88400 ammar88400 changed the title how can i train the net with my own Training Pictures? how can i train the Neural Network with my own Training Pictures? Feb 10, 2022
@mdabros
Copy link
Owner

mdabros commented Feb 19, 2022

Hi @ammar88400,

Currently there is no standard method for loading images in SharpLearning. So you basically have write your own methods for converting them to the `F64Matrix´. I think there are better libraries for training neural networks on images in C# than SharpLearning. I would try using one of the following:

  1. TorchSharp
  2. TensorFlow.NET
  3. CNTK

Note that CNTK is deprecated, so if using C#, I would recommend using TorchSharp.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants