DGDataset indexing for training

yurujaja / DGInStyle-SegModel

Downstream semantic segmentation evaluation of DGInStyle.

Apache License 2.0

17 stars 1 forks source link

DGDataset indexing for training #3

Open amundra15 opened 1 month ago

amundra15 commented 1 month ago

Could you please explain how the datasets are getting samples?

Suppose I am trying to run exp-id 60 with the GTA and DG datasets. Here I see that initially the source dataset is sampled and then source2. Is that correct?

Can you also confirm the expected sizes of these two datasets?

amundra15 commented 1 month ago

And could it be possible that source2 is getting completely ignored while building the Dataset here?