Why do you define W_1 as a convolutional layer?

[GiilDe]

PointerNet/PointerNet.py

Line 98 in c7ed050

self.context_linear = nn.Conv1d(input_dim, hidden_dim, 1, 1)

In this line you define W_1 as a convolutional layer whereas in the paper it seems like they mean it to be a Linear layer. Why do you define it like that?

[bluesquinn777]

Check this:
https://stackoverflow.com/questions/55576314/conv1d-with-kernel-size-1-vs-linear-layer

[johnnylili]

Have you trained this pointer network? What accuracy can you achieve on the test set?