Dimensions for decoder g

kasparmartens / NeuralProcesses

Neural Processes implementation for 1D regression

65 stars 11 forks source link

Dimensions for decoder g #6

Closed kristpapadopoulos closed 5 years ago

kristpapadopoulos commented 5 years ago

Sorry this question might be obvious but I don't understand why n_draws and N_star are taken from [1] from shape. Shouldn't their dimension be taken from [0].

decoder g -- map (z, x) -> hidden -> y -inputs dimensions -z_sample has dim [n_draws, dim_z]

x_star has dim [N_star, dim_x]

n_draws <- z_sample$get_shape()$as_list()[1] N_star <- tf$shape(x_star)[1]

kasparmartens commented 5 years ago

Hi!

This is because indexing in R starts from 1 :).

kristpapadopoulos commented 5 years ago

I figured it was something obvious. thanks for answering.