| """Minimal material-point inference for original or expanded DENIM weights.""" |
|
|
| import argparse |
| from pathlib import Path |
|
|
| import torch |
|
|
| from src.t2_graybox_discrete_energy import DENIM, rollout |
|
|
|
|
| ROOT = Path(__file__).resolve().parent |
| parser = argparse.ArgumentParser() |
| parser.add_argument( |
| "--checkpoint", |
| choices=("denim.pt", "denim-expanded.pt"), |
| default="denim-expanded.pt", |
| ) |
| args = parser.parse_args() |
| checkpoint = torch.load(ROOT / args.checkpoint, map_location="cpu", weights_only=False) |
| model = DENIM(channels=2) |
| model.load_state_dict(checkpoint["state_dict"]) |
| model.eval() |
|
|
| points = 121 |
| coordinate = torch.linspace(0.0, 1.0, points) |
| amplitude = torch.where(coordinate <= 0.5, 2.0 * coordinate, 2.0 * (1.0 - coordinate)) |
| scalar = 0.008 * torch.sin(2.0 * torch.pi * coordinate) * amplitude |
| basis = torch.tensor((1.0, -0.5, -0.5, 0.0, 0.0, 0.0)) |
| strain = (scalar[:, None] * basis).unsqueeze(0) |
|
|
| with torch.no_grad(): |
| result = rollout( |
| strain, |
| torch.tensor((190.0e9,)), |
| torch.tensor((0.30,)), |
| torch.tensor((280.0e6,)), |
| model, |
| ) |
|
|
| print("checkpoint", args.checkpoint) |
| print("steps", points) |
| print("maximum_abs_stress_mpa", float(result["stress"].abs().max() / 1.0e6)) |
| print("final_peeq", float(result["peeq"][0, -1])) |
| print("maximum_yield_residual_pa", float(result["yield_residual"].abs().max())) |
|
|
