Closed BUAAZhangHaonan closed 2 months ago
Please see our guide here - you can compare with the config there to see how to change the data loading options in the config.
My oversight, I didn't notice this tutorial. I tried it, it works! Thank you for this!
Thank you for your excellent work! I have a question about how to train on
bc_transformer
correctly? Inscript/train.py
, we userun_epoch()
to execute the training process, and we do this as follows:In this way, we can get the data one by one from the dataloader through the
next()
operation, which means the shape ofbatch["actions"]
is[_, 1, _]
. Inprocess_batch_for_training
ofBC_Transformer
,batch["actions"]
is used in this way:and the
h
isself.context_length
which is not 1 and leads to a mistake as the default parmcontext_length
inbc.json
is 10:How can I adjust the code to fit the struct of
bc_transformer
?