Skip to content

Fix FNO inverse pipeline for InitialConditionInterp with multi-step inputs #101

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Mattia-PCS wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix FNO inverse pipeline for InitialConditionInterp with multi-step inputs #101

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
88 changes: 70 additions & 18 deletions pdebench/models/inverse/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -186,7 +186,6 @@ def main(cfg: DictConfig):
logger.info(cfg.args.filename)
logger.info(cfg.args)

# we use the test data
if cfg.args.model_name in ["FNO"]:
inverse_data = FNODatasetSingle(
cfg.args.filename,
Expand All @@ -199,7 +198,13 @@ def main(cfg: DictConfig):
num_samples_max=cfg.args.num_samples_max,
)

_data, _, _ = next(iter(inverse_data))
inverse_loader = torch.utils.data.DataLoader(
inverse_data,
batch_size=1,
shuffle=False,
)

_, _data, _ = next(iter(inverse_loader))
dimensions = len(_data.shape)
spatial_dim = dimensions - 3

Expand All @@ -216,8 +221,11 @@ def main(cfg: DictConfig):
)

inverse_loader = torch.utils.data.DataLoader(
inverse_data, batch_size=1, shuffle=False
inverse_data,
batch_size=1,
shuffle=False,
)

_data, _ = next(iter(inverse_loader))
dimensions = len(_data.shape)
spatial_dim = dimensions - 3
Expand Down Expand Up @@ -267,6 +275,7 @@ def main(cfg: DictConfig):
model = load_model(model, model_path, device)

model.eval()

if cfg.args.inverse_model_type in ["ProbRasterLatent"]:
assert spatial_dim == 1, "give me time"
if spatial_dim == 1:
Expand All @@ -283,9 +292,22 @@ def main(cfg: DictConfig):

if cfg.args.inverse_model_type in ["InitialConditionInterp"]:
loss_fn = nn.MSELoss(reduction="mean")

input_dims = list(_data.shape[1 : 1 + spatial_dim])
latent_dims = len(input_dims) * [cfg.args.in_channels_hid]
if cfg.args.num_channels > 1:

if cfg.args.model_name in ["FNO"]:
input_dims = [
*input_dims,
cfg.args.initial_step,
cfg.args.num_channels,
]
latent_dims = [
*latent_dims,
cfg.args.initial_step,
cfg.args.num_channels,
]
elif cfg.args.num_channels > 1:
input_dims = [*input_dims, cfg.args.num_channels]
latent_dims = [*latent_dims, cfg.args.num_channels]

Expand All @@ -298,18 +320,21 @@ def main(cfg: DictConfig):
inverse_u0_l2_full, inverse_y_l2_full = 0, 0
all_metric = []
t1 = default_timer()

for ks, sample in enumerate(inverse_loader):
if cfg.args.model_name in ["FNO"]:
(xx, yy, grid) = sample
xx, yy, grid = sample
xx = xx.to(device)
yy = yy.to(device)
grid = grid.to(device)

def model_(x, grid):
if x.dim() == grid.dim() + 1:
x = x.reshape(*x.shape[:-2], x.shape[-2] * x.shape[-1])
return model(x, grid)

if cfg.args.model_name in ["UNET", "Unet"]:
(xx, yy) = sample
xx, yy = sample
grid = None
xx = xx.to(device)
yy = yy.to(device)
Expand All @@ -319,23 +344,32 @@ def model_(x, grid):

num_samples = ks + 1

x = xx[..., 0, :]
if cfg.args.model_name in ["FNO"]:
x = xx[..., : cfg.args.initial_step, :]
x = x.reshape(
*x.shape[:-2],
cfg.args.initial_step * cfg.args.num_channels,
)
else:
x = xx[..., 0, :]

y = yy[..., t_train : t_train + 1, :]

if ks == 0:
msg = f"{x.shape}, {y.shape}"
logger.info(msg)

# scale the input and output
x = scaler.fit_transform(x)
y = scaler.transform(y)

if cfg.args.inverse_model_type in ["ProbRasterLatent"]:
# Create model
model_inverse.to(device)
nuts_kernel = NUTS(
model_inverse, full_mass=False, max_tree_depth=5, jit_compile=True
) # high performacne config
model_inverse,
full_mass=False,
max_tree_depth=5,
jit_compile=True,
)

mcmc = MCMC(
nuts_kernel,
Expand All @@ -344,12 +378,12 @@ def model_(x, grid):
num_chains=cfg.args.mcmc_num_chains,
disable_progbar=True,
)

mcmc.run(grid, y)
mc_samples = {
k: v.detach().cpu().numpy() for k, v in mcmc.get_samples().items()
}

# get the initial solution
latent = torch.tensor(mc_samples["latent"])
u0 = model_inverse.latent2source(latent[0]).to(device)
pred_u0 = model(u0, grid)
Expand All @@ -360,18 +394,27 @@ def model_(x, grid):
lr=cfg.args.inverse_learning_rate,
weight_decay=1e-4,
)
# scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=scheduler_step, gamma=scheduler_gamma)

if cfg.args.inverse_verbose_flag:
_iter = tqdm(range(cfg.args.inverse_epochs))
else:
_iter = range(cfg.args.inverse_epochs)

for _ in _iter:
if cfg.args.num_channels > 1:
u0 = model_ic().unsqueeze(0)
else:
u0 = model_ic().unsqueeze(0).unsqueeze(-1)

pred_u0 = model_(u0, grid)
if cfg.args.model_name in ["FNO"]:
u0_for_model = u0.reshape(
*u0.shape[:-2],
u0.shape[-2] * u0.shape[-1],
)
else:
u0_for_model = u0

pred_u0 = model_(u0_for_model, grid)

loss_u0 = loss_fn(pred_u0, y)
optimizer.zero_grad()
Expand All @@ -382,13 +425,21 @@ def model_(x, grid):
if cfg.args.inverse_verbose_flag:
_iter.set_description(f"loss={loss_u0.item()}, t2-t1= {t2-t1}")

# compute losses
loss_u0 = loss_fn(u0.reshape(1, -1), x.reshape(1, -1)).item()
if cfg.args.model_name in ["FNO"]:
u0_metric = u0.reshape(
*u0.shape[:-2],
u0.shape[-2] * u0.shape[-1],
)
else:
u0_metric = u0

loss_u0 = loss_fn(u0_metric.reshape(1, -1), x.reshape(1, -1)).item()
loss_y = loss_fn(pred_u0.reshape(1, -1), y.reshape(1, -1)).item()

inverse_u0_l2_full += loss_u0
inverse_y_l2_full += loss_y

metric = inverse_metrics(u0, x, pred_u0, y)
metric = inverse_metrics(u0_metric, x, pred_u0, y)
metric["sample"] = ks

all_metric += [metric]
Expand All @@ -407,6 +458,7 @@ def model_(x, grid):
logger.info(msg)

df_metric = pd.DataFrame(all_metric)

inverse_metric_filename = (
cfg.args.base_path
+ cfg.args.filename[:-5]
Expand Down Expand Up @@ -449,4 +501,4 @@ def model_(x, grid):


if __name__ == "__main__":
main()
main()