search

wouterkool / attention-learn-to-route

Attention based model for learning to solve different routing problems
MIT License
1.08k stars 341 forks source link

Runtime comparisons #1

Closed bkj closed 5 years ago

bkj commented 6 years ago

Really enjoy the paper -- have you done any comparisons between the runtimes of your method and other heuristic solvers (either learned or unlearned)? In Table 2, you should you can get a better quality solution than OR-Tools, but are the runtimes comparable? Would they be comparable as instance size grew?

Thanks Ben

ldy8665 commented 5 years ago

I think Python 3.5 is not enough when running the run.py.It occurs such errors

attention_model.py", line 26 node_embeddings: torch.Tensor SyntaxError: invalid syntax.

And Class syntax for NamedTuple is only supported in Python 3.6+

wouterkool commented 5 years ago

Thanks, I have updated the readme!