How to use own data for training?

meetps / pytorch-semseg

Semantic Segmentation Architectures Implemented in PyTorch

https://meetshah.dev/semantic-segmentation/deep-learning/pytorch/visdom/2017/06/01/semantic-segmentation-over-the-years.html

MIT License

3.39k stars 796 forks source link

How to use own data for training? #223

Open keishatsai opened 5 years ago

keishatsai commented 5 years ago

Hi,

I am wondering that how to train with my own dataset and mask. I have searched issues, but it seems that there was not any update for the customise dataset.

Thanks.

GutlapalliNikhil commented 4 years ago

Hi,

Is your problem solved? I want to know how to train our own dataset.

Thank you

kubitz commented 3 years ago

You need to write your own data loader like in the loader module. I recommend going through the code with a known dataset and trying to understand what it does. If you find this too difficult, you can also copy the file/labelling structure from one of the supported datasets and simply change the number of classes and resolution.

twsha commented 1 year ago

hi i would like to know how to train your own dataset,thank you

hjhjb commented 1 year ago

我已收到，谢谢