UndefVarError: ones_like not defined in GNNLib in SGConv example #599
Description
Running the example code given in the documentation here
results in the error described in the title:
# test.jl
using GraphNeuralNetworks
# create data
s = [1,1,2,3]
t = [2,3,1,1]
g = GNNGraph(s, t)
x = randn(Float32, 3, g.num_nodes)
# create layer
l = SGConv(3 => 5; add_self_loops = true)
# forward pass
y = l(g, x) # size: 5 × num_nodes
# convolution with edge weights
w = [1.1, 0.1, 2.3, 0.5]
y = l(g, x, w) # ERROR HERE
# Edge weights can also be embedded in the graph.
g = GNNGraph(s, t, w)
l = SGConv(3 => 5, add_self_loops = true, use_edge_weight=true)
y = l(g, x) # same as l(g, x, w) Error message:
ERROR: UndefVarError: `ones_like` not defined in `GNNlib`
Suggestion: check for spelling errors or missing imports.
Hint: a global variable of this name also exists in MLUtils.
Stacktrace:
[1] sg_conv(l::SGConv{Matrix{…}, Vector{…}}, g::GNNGraph{Tuple{…}}, x::Matrix{Float32}, edge_weight::Vector{Float64})
@ GNNlib ~/.julia/packages/GNNlib/ynkEA/src/layers/conv.jl:515
[2] (::SGConv{Matrix{…}, Vector{…}})(g::GNNGraph{Tuple{…}}, x::Matrix{Float32}, edge_weight::Vector{Float64})
@ GraphNeuralNetworks ~/.julia/packages/GraphNeuralNetworks/3k4Ik/src/layers/conv.jl:1212
[3] top-level scope
@ ~/Development/geomentric_deeplearning_experiments/geometric.jl/src/test.jl:20