The spiral neural ODE was used as the training benchmark for both torchdiffeq (Python) and DiffEqFlux (Julia) which utilized the same architecture and 500 steps of ADAM. Both achived similar objective values at the end. Results:
- DiffEqFlux defaults: 7.4 seconds
- DiffEqFlux optimized: 2.7 seconds
- torchdiffeq: 288.965871299999 seconds
Relative time to train for Python vs Julia's DiffEqFlux (lower is better)
Unoptimized defaults: 39x Optimized sensitivity: 107x
Final loss values:
- DiffEqFlux defaults: 4.895287e-02
- DiffEqFlux optimized: 2.761669e-02
- torchdiffeq: 0.0596