search

FluxML / GeometricFlux.jl

Geometric Deep Learning for Flux
https://fluxml.ai/GeometricFlux.jl/stable/
MIT License
348 stars 30 forks source link

examples/gde.jl not working #264

Closed gcrth closed 2 years ago

gcrth commented 2 years ago

The example in https://github.com/FluxML/GeometricFlux.jl/blob/master/examples/gde.jl can not run. There will be an error when running the last line of code, and the error is shown below.

julia> @epochs epochs Flux.train!(loss, ps, train_data, opt, cb=throttle(evalcb, 10))
[ Info: Epoch 1
┌ Warning: Expected 7344092 params, got 272
└ @ Flux ~/.julia/packages/Flux/BPPNj/src/utils.jl:647
ERROR: LoadError: DimensionMismatch("array could not be broadcast to match destination")

I cannot find any solution for solving this, and I wonder if there is any suggestion for fixing this.

Any help is appreciated, thank you.

yuehhua commented 2 years ago

Yeah, it comes from broken GCNConv layer. I will got it fixed soon.