How should I modify the model(G and D) structure if my input are all one-hot encoded matrix(3-D tensor) which only contains either 0 or 1

[lkqnaruto]

I'm working on something that need to convert each value in 2-D tensor to 3-D tensor where each value in the original 2-D tensor has been one-hot encoded. For example, say, I have a matrix M (51 x 51), and M(I, j) originally was a scalar, then it is converted to a one-hot vector (size 30). In the end, I will end up with a 3-D input (30x51x51). In this case, how should I modify Generator and Discriminator model structure?

Moreover, due to my project goal, the 3-D tensor which only contains one-hot vector will be concatenated another similar 3-D tensor which also only contains one-hot vectors. Thus, in the end, the input actually becomes a 3-D tensor which contains either one-hot vector or two-hot vector, or even three-hot vectors. In this case, how should I modify the model structure? Do I still have to convert all the values to (-1, 1)? for example, 1 becomes to 1, and 0 becomes to -1 ?

[Jin Liu]

Sorry for disturbing you, because of the invalid link, could you please share "fcn-8s-cityscapes" weight to me? thank you!

[e-mail]