Training the fine-tuned base line with standard supervised learning with union/concatenation of labels

[brando90]

Hi @mboudiaf, I wanted to train the fine-tuned baseline from meta-data set (MDS) i.e. concatenate/union all the data sets and all the labels and then train in normal supervised learning. Is the right way to do this this:

pytorch-meta-dataset/example.py

Line 173 in c6d6922

batch_loader = DataLoader(dataset=batch_dataset,

I am mainly asking because there needs to be some sort of relabling that takes into account all the data set labels and wanted to know how that was done.

Thank you!