I have data that consists of a sequence of word-part of speech pairs. I currently have it set up where each pair is represented as a list of two tensors, one tensor with the one-hot for the word and the other with the one-hot for the part of speech. Each sentence is a list of lists. I use dataloader on this data. I am trying to implement batching in training but when try to train, I get this error:
“TypeError: embedding(): argument ‘indices’ (position 2) must be Tensor, not list”
I am not sure how to represent my data in a way where I can implement batching. I am also happy to provide code.
Thanks so much!