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

Is it accessible to train my own dataset? #3

Open
binbinlan opened this issue Oct 7, 2022 · 1 comment
Open

Is it accessible to train my own dataset? #3

binbinlan opened this issue Oct 7, 2022 · 1 comment

Comments

@binbinlan
Copy link

Dear author, I am very interested in your works. After seeing your excellent results, I want to train the network on my own dataset. Can you tell me how to customize a training dataset? It mainly refers to the creation process of NPZ files, including scripts used by experts for manual annotation.

@gzegers
Copy link

gzegers commented Mar 15, 2023

Hi @binbinlan,

The NPZ files are exported directly from numpy arrays. You need to create an array for each necessary variable (images. histograms, tiles_names, and dm). Then you can export the NPZ using the following function:

import numpy as np
np.savez_compressed('Data_V1.npz', images=images, histograms=histograms,tile_names=tile_names,dm=dm)

Best,

Gerardo

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