It would be illuminating for both yourself and this forum if you could print out the size of the output from the GNN part in both Python and Julia. I suspect they are not the same, which may be where your confusion is coming from.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| The same network performs differently in Flux.jl and tensorflow | 13 | 3117 | December 18, 2019 | |
| Size Mismatch Convolution Layer | 3 | 838 | June 24, 2021 | |
| Help setting up convolution in NNLib.jl | 0 | 902 | December 2, 2019 | |
| Flux 3, now with 100% more Julia! | 18 | 7481 | December 18, 2017 | |
| Flux Conv layer method error | 4 | 673 | January 16, 2023 |