Q1, In Algorithm 1, D{strokes} has shape hwn and w{strokes} has shape n, then there can't be max across axis 4. Or I guess it should be D (shape hwn*s) rather than D_{strokes} if there is a max across axis 4.
Q2, What are the temperature values did you use for sigmoid and softmax?
Q3, where is the corresponding code of Q1?
Q1, In Algorithm 1, D{strokes} has shape hwn and w{strokes} has shape n, then there can't be max across axis 4. Or I guess it should be D (shape hwn*s) rather than D_{strokes} if there is a max across axis 4. Q2, What are the temperature values did you use for sigmoid and softmax? Q3, where is the corresponding code of Q1?