training with custom dataset

[mhyeonsoo]

Hello,

Thanks for the great idea. I am now trying to train the model with my own dataset which has 1 class. Can you briefly guide me how to / what to modify for training own dataset?

What I've changed is,

1. edited config by coping imagenet configs and changing number of classes / name in it.
2. added class for loading my own dataset in inputs.py script

Any other things should be required?

thank you

[stevliu]

Yes, changing the config by changing data['type'] and changing the number of classes to 1 should do it.

The class that you write should be a torch.data.Dataset class.

[woshichunge12]

@mhyeonsoo How did you do it? Did you train successfully later?thanks a lot.