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 | |
|---|---|---|---|---|
| Flux: 1D convolutions (on genomic data) | 20 | 2645 | May 28, 2023 | |
| Flux Conv layer method error | 4 | 688 | January 16, 2023 | |
| Size Mismatch Convolution Layer | 3 | 852 | June 24, 2021 | |
| The same network performs differently in Flux.jl and tensorflow | 13 | 3143 | December 18, 2019 | |
| Why is there a "Warning: Slow Fallback implementation" and a DimensionMismatch error? | 1 | 521 | February 16, 2021 |