Hi,
I am working on Goodreads dataset (containing userid, bookid & rating). I used Collaborative filtering on this. To understand the weights, I load the learner successfully.
learn.load(path/‘models/grcollab-p2-1’)
However when I try to extract the weight or bias, I get below error, I cant figure out why…I tried using training dataset, also test dataset. But nothing works. The same happens while extracting bias too.
learn.bias(data.train_ds, is_item=True)
> You're trying to access an item that isn't in the training data.
> If it was in your original data, it may have been split such that it's only in the validation set now.
> ---------------------------------------------------------------------------
> TypeError Traceback (most recent call last)
> <ipython-input-68-053e9336b5c9> in <module>()
> ----> 1 learn.bias(data.train_ds, is_item=True)
>
> 3 frames
> /usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
> 1482 # remove once script supports set_grad_enabled
> 1483 _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
> -> 1484 return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
> 1485
> 1486
>
> TypeError: embedding(): argument 'indices' (position 2) must be Tensor, not NoneType