About piecewise_linear_encoding

[Minhvt34]

Hi Yura!

I have run the test code, which is mentioned in your code data.piecewise_linear_encoding
I have this error: RuntimeError: The size of tensor a (4) must match the size of tensor b (100) at non-singleton dimension 1

this error causes by is_last_bin = bin_indices + 1 == as_tensor(list(map(len, bin_edges)))

while bin_indices + 1 is a torch.Size([100, 4]), and as_tensor(list(map(len, bin_edges))) returns a torch.Size([100])

[Yura52]

Hi! Are you referring to this code snippet?

[Minhvt34]

Hi! Are you referring to this code snippet?

yes, I am trying to use piecewise linear encoding but there is an error as above.

[Yura52]

Hi @Minhvt34 ! Sorry for such a long pause. There is now a new package that correctly implements piecewise-linear encoding and other embeddings:

• The package
• The announcement with more details

[Minhvt34]

Hi @Minhvt34 ! Sorry for such a long pause. There is now a new package that correctly implements piecewise-linear encoding and other embeddings:

• The package
• The announcement with more details

Awesome! I am glad that you are still working on the project. I found your method works pretty well! Keep doing such a greate work.