search

lululxvi / deeponet

Learning nonlinear operators via DeepONet
Other
509 stars 139 forks source link

Number of parameters in `seq2seq` scales with the length**2 of the sequence #10

Closed scaomath closed 3 years ago

scaomath commented 3 years ago

https://github.com/lululxvi/deeponet/blob/44e7b5a2356b0e6e00ad101e897342a2f1e87c0b/seq2seq/learner/nn/seq2seq.py#L58-L59

This does not seem right, considering DeepONet does not have such kind of dependence.

https://github.com/lululxvi/deeponet/blob/44e7b5a2356b0e6e00ad101e897342a2f1e87c0b/seq2seq/learner/nn/deeponet.py#L39-L41

lululxvi commented 3 years ago

You are right. The Seq2Seq model and DeepONet are not used exactly in the same setup. But the length is fixed in each task.