Skip to content
This repository was archived by the owner on Jan 22, 2024. It is now read-only.

How to do it for custom dataset #7

Open
PraveenMNaik opened this issue Oct 4, 2023 · 1 comment
Open

How to do it for custom dataset #7

PraveenMNaik opened this issue Oct 4, 2023 · 1 comment

Comments

@PraveenMNaik
Copy link

Hi @christorange ,
You have done a fabulous work. I would like to run on my custom image dataset where image size is quite larger 416x416. But if i convert to csv its very large, can you please help me to execute in such configuration.

@christorange
Copy link
Owner

I'm afraid it's hard to train such large image on this toy model, I subsampled dataset to $14 \times 14$ because when I tried to train $28 \times 28$ images my RAM got eaten up, and it would throw an error. Maybe you can transform the data to binary formats, like .bin files, but you will also need some tools to make the model work with data in such formats.

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

No branches or pull requests

2 participants