-
Notifications
You must be signed in to change notification settings - Fork 2.2k
BagOfWordCountsTokenEmbedder & BasicClassifier not compatible #3388
Comments
@kernelmachine , could you take a look at this? (As it looks like you're the author of the |
ping @kernelmachine |
Yes, I think unsqueezing the |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
14 similar comments
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
@kernelmachine this is just a friendly ping to make sure you haven't forgotten about this issue 😜 |
Bug Description
BagOfWordCountsTokenEmbedder returns tensor with shape [batchsize, size of vocab (or projection dim)], while most of other embedders return [batchsize, num of tokens, size of hidden]
This is at some level inconsistent with the definition of embedder, so seq2vec in BasicClassifier cannot be applied (the input is not even a sequence).
To Reproduce
Use them together like
Expected behavior
At least make the output of BagOfWordCountsTokenEmbedder looks like [bs, 1, vocab size] would help. (Although it will still be a bit confusing.)
System (please complete the following information):
The text was updated successfully, but these errors were encountered: