Answer by Maosi Chen for how to deal with padded 0 during feedforward process
I think you may use attention mechanism to convert the variable-length inputs to some fixed length tensor before you feed them into a feed forward network.
View Articlehow to deal with padded 0 during feedforward process
Assume I have a lists of inputs of different sizes, for example, some are of the shape[10,9,5] some are [7,6,5], I have to pad 0s to feed them into tensor flow with the same size, say [10,9,5], I need...
View Article
More Pages to Explore .....