new plotting strategy

ThermalSolver/autoregressive_module.py

@@ -15,7 +15,7 @@ def import_class(class_path: str):
     return cls
 
 
-def _plot_mesh(pos_, y_, y_pred_, y_true_, batch, i, batch_idx):
+def _plot_mesh(pos_, y_, y_pred_, y_true_, batch, cells, i, batch_idx):
     # print(pos_.shape, y_.shape, y_pred_.shape, y_true_.shape)
     for j in [0]:
         idx = (batch == j).nonzero(as_tuple=True)[0]
@@ -25,11 +25,12 @@ def _plot_mesh(pos_, y_, y_pred_, y_true_, batch, i, batch_idx):
         # print(pos.shape, y.shape, y_pred.shape)
         y_true = y_true_[idx].detach().cpu()
         y_true = torch.clamp(y_true, min=0)
-        folder = f"{j:02d}_images"
+        folder = f"{batch_idx:02d}_images"
         if os.path.exists(folder) is False:
             os.makedirs(folder)
-        tria = Triangulation(pos[:, 0], pos[:, 1])
-        plt.figure(figsize=(18, 6))
+        triangles = torch.vstack([cells[:, [0, 1, 2]], cells[:, [0, 2, 3]]])
+        tria = Triangulation(pos[:, 0], pos[:, 1], triangles=triangles)
+        plt.figure(figsize=(24, 6))
         # plt.subplot(1, 4, 1)
         # plt.tricontourf(tria, y.squeeze().numpy(), levels=100)
         # plt.colorbar()
@@ -37,61 +38,79 @@ def _plot_mesh(pos_, y_, y_pred_, y_true_, batch, i, batch_idx):
         # plt.tripcolor(tria, y_pred.squeeze().numpy()
         # plt.savefig("test_scatter_step_before.png", dpi=72)
         # x = z
-        plt.subplot(1, 3, 1)
-        # plt.tricontourf(tria, y_pred.squeeze().numpy(), levels=100)
-        plt.scatter(
-            pos[:, 0],
-            pos[:, 1],
-            c=y_pred.squeeze().numpy(),
-            s=20,
-            cmap="viridis",
-        )
+        plt.subplot(1, 4, 1)
+        plt.tricontourf(tria, y_pred.squeeze().numpy(), levels=100)
+        # plt.scatter(pos[:, 0], pos[:, 1], c=y_pred.squeeze().numpy(), s=20, cmap="viridis",)
         plt.colorbar()
-        plt.title("Step t Predicted")
-        plt.subplot(1, 3, 2)
-        # plt.tricontourf(tria, y_true.squeeze().numpy(), levels=100)
-        plt.scatter(
-            pos[:, 0],
-            pos[:, 1],
-            c=y_true.squeeze().numpy(),
-            s=20,
-            cmap="viridis",
-        )
+        plt.title(f"Prediction at timestep {i:03d}")
+        plt.subplot(1, 4, 2)
+        plt.tricontourf(tria, y_true.squeeze().numpy(), levels=100)
+        # plt.scatter(pos[:, 0], pos[:, 1], c=y_true.squeeze().numpy(), s=20, cmap="viridis")
         plt.colorbar()
-        plt.title("t True")
-        plt.subplot(1, 3, 3)
-        per_element_relative_error = torch.abs(y_pred - y_true) / torch.clamp(
-            torch.abs(y_true), min=1e-6
+        plt.title("Ground Truth Steady State")
+        plt.subplot(1, 4, 3)
+        per_element_relative_error = torch.abs(y_pred - y_true) / (
+            y_true + 1e-6
         )
-        # plt.tricontourf(tria, per_element_relative_error.squeeze(), levels=100)
-        plt.scatter(
-            pos[:, 0],
-            pos[:, 1],
-            c=per_element_relative_error.squeeze().numpy(),
-            s=20,
-            cmap="viridis",
+        per_element_relative_error = torch.clamp(
+            per_element_relative_error, max=1.0, min=0.0
         )
+        plt.tricontourf(
+            tria,
+            per_element_relative_error.squeeze(),
+            levels=100,
+            vmin=0,
+            vmax=1.0,
+        )
+        # plt.scatter(pos[:, 0], pos[:, 1], c=per_element_relative_error.squeeze().numpy(), s=20, cmap="viridis", vmin=0, vmax=1.0)
         plt.colorbar()
         plt.title("Relative Error")
+        plt.subplot(1, 4, 4)
+        absolute_error = torch.abs(y_pred - y_true)
+        plt.tricontourf(tria, absolute_error.squeeze(), levels=100)
+        # plt.scatter(pos[:, 0], pos[:, 1], c=absolute_error.squeeze().numpy(), s=20, cmap="viridis")
+        plt.colorbar()
+        plt.title("Absolute Error")
         plt.suptitle("GNO", fontsize=16)
         name = f"{folder}/{j:04d}_graph_iter_{i:04d}.png"
         plt.savefig(name, dpi=72)
         plt.close()
 
 
-def _plot_losses(test_losses, batch_idx):
-    folder = f"{batch_idx:02d}_images"
-    plt.figure()
+def _plot_losses(relative_errors, test_losses, relative_update, batch_idx):
+    # folder = f"{batch_idx:02d}_images"
+    plt.figure(figsize=(18, 6))
+    plt.subplot(1, 3, 1)
     for i, losses in enumerate(test_losses):
         plt.plot(losses)
         if i == 3:
             break
     plt.yscale("log")
     plt.xlabel("Iteration")
-    plt.ylabel("Relative Error")
+    plt.ylabel("Test Loss")
     plt.title("Test Loss over Iterations")
     plt.grid(True)
-    file_name = f"{folder}/test_loss.png"
+    plt.subplot(1, 3, 2)
+    for i, losses in enumerate(relative_errors):
+        plt.plot(losses)
+        if i == 3:
+            break
+    plt.yscale("log")
+    plt.xlabel("Iteration")
+    plt.ylabel("Relative Error")
+    plt.title("Relative error over Iterations")
+    plt.grid(True)
+    plt.subplot(1, 3, 3)
+    for i, updates in enumerate(relative_update):
+        plt.plot(updates)
+        if i == 3:
+            break
+    plt.yscale("log")
+    plt.xlabel("Iteration")
+    plt.ylabel("Relative Update")
+    plt.title("Relative update over Iterations")
+    plt.grid(True)
+    file_name = f"test_errors.png"
     plt.savefig(file_name, dpi=300)
     plt.close()
 
@@ -112,6 +131,8 @@ class GraphSolver(LightningModule):
         self.loss = loss if loss is not None else torch.nn.MSELoss()
         self.unrolling_steps = unrolling_steps
         self.test_losses = []
+        self.test_relative_errors = []
+        self.test_relative_updates = []
 
     def _compute_loss(self, x, y):
         return self.loss(x, y)
@@ -166,6 +187,7 @@ class GraphSolver(LightningModule):
         )
         losses = []
         for i in range(self.unrolling_steps):
+            # print(f"Training step {i+1}/{self.unrolling_steps}")
             out = self._compute_model_steps(
                 x,
                 edge_index,
@@ -216,20 +238,20 @@ class GraphSolver(LightningModule):
                 batch.boundary_values,
                 conductivity,
             )
-            if (
-                batch_idx == 0
-                and self.current_epoch % 10 == 0
-                and self.current_epoch > 0
-            ):
-                _plot_mesh(
-                    batch.pos,
-                    x,
-                    out,
-                    y[:, i, :],
-                    batch.batch,
-                    i,
-                    self.current_epoch,
-                )
+            # if (
+            #     batch_idx == 0
+            #     and self.current_epoch % 10 == 0
+            #     and self.current_epoch > 0
+            # ):
+            #     _plot_mesh(
+            #         batch.pos,
+            #         x,
+            #         out,
+            #         y[:, i, :],
+            #         batch.batch,
+            #         i,
+            #         self.current_epoch,
+            #     )
             x = out
             losses.append(self.loss(out, y[:, i, :]))
 
@@ -237,11 +259,11 @@ class GraphSolver(LightningModule):
         self._log_loss(loss, batch, "val")
         return loss
 
-    def _check_convergence(self, y_new, y_old, tol=1e-3):
-        l2_norm = torch.norm(y_new, p=2) - torch.norm(y_old, p=2)
+    def _check_convergence(self, y_new, y_old, tol=1e-4):
+        l2_norm = torch.norm(y_new - y_old, p=2)
         y_old_norm = torch.norm(y_old, p=2)
         rel_error = l2_norm / (y_old_norm)
-        return rel_error.item() < tol
+        return rel_error.item() < tol, rel_error.item()
 
     def test_step(self, batch: Batch, batch_idx):
         x, y, edge_index, edge_attr, conductivity = self._preprocess_batch(
@@ -251,9 +273,14 @@ class GraphSolver(LightningModule):
         losses = []
         all_losses = []
         norms = []
+        s = []
+        relative_updates = []
         sequence_length = y.size(1)
         y = y[:, -1, :].unsqueeze(1)
-        for i in range(100):
+        _plot_mesh(
+            batch.pos, x, x, y[:, -1, :], batch.batch, batch.cells, 0, batch_idx
+        )
+        for i in range(200):
             out = self._compute_model_steps(
                 # torch.cat([x,pos], dim=-1),
                 x,
@@ -265,23 +292,27 @@ class GraphSolver(LightningModule):
                 conductivity,
             )
             norms.append(torch.norm(out - x, p=2).item())
-            converged = self._check_convergence(out, x)
-            if batch_idx == 0:
+            converged, relative_update = self._check_convergence(out, x)
+            relative_updates.append(relative_update)
+            if batch_idx <= 4:
+                print(f"Plotting iteration {i}, norm diff: {norms[-1]}")
                 _plot_mesh(
                     batch.pos,
                     x,
                     out,
                     y[:, -1, :],
                     batch.batch,
-                    i,
-                    self.current_epoch,
+                    batch.cells,
+                    i + 1,
+                    batch_idx,
                 )
             x = out
             loss = self.loss(out, y[:, -1, :])
-            relative_error = torch.norm(out - y[:, -1, :], p=2) / torch.norm(
-                y[:, -1, :], p=2
+            relative_error = torch.abs(out - y[:, -1, :]) / (
+                torch.abs(y[:, -1, :]) + 1e-6
             )
-            all_losses.append(relative_error.item())
+            mean_relative_error = relative_error.mean()
+            all_losses.append(mean_relative_error.item())
             losses.append(loss)
             if converged:
                 print(
@@ -289,13 +320,20 @@ class GraphSolver(LightningModule):
                 )
                 break
         loss = torch.stack(losses).mean()
-        self.test_losses.append(all_losses)
+        self.test_losses.append(losses)
+        self.test_relative_errors.append(all_losses)
+        self.test_relative_updates.append(relative_updates)
         self._log_loss(loss, batch, "test")
         return loss
 
     def on_test_end(self):
         if len(self.test_losses) > 0:
-            _plot_losses(self.test_losses, batch_idx=0)
+            _plot_losses(
+                self.test_relative_errors,
+                self.test_losses,
+                self.test_relative_updates,
+                batch_idx=0,
+            )
 
     def configure_optimizers(self):
         optimizer = torch.optim.AdamW(self.parameters(), lr=1e-3)

ThermalSolver/graph_datamodule.py

@@ -82,7 +82,9 @@ class GraphDataModule(LightningDataModule):
         conductivity = torch.tensor(
             snapshot["conductivity"], dtype=torch.float32
         )
-        temperature = torch.tensor(snapshot["temperature"], dtype=torch.float32)
+        temperature = torch.tensor(
+            snapshot["temperature"], dtype=torch.float32
+        )[:50]
 
         pos = torch.tensor(geometry["points"], dtype=torch.float32)[:, :2]
 

ThermalSolver/graph_datamodule_unsteady.py

@@ -1,18 +1,19 @@
 import torch
 from tqdm import tqdm
 from lightning import LightningDataModule
-from datasets import load_dataset
+from datasets import load_dataset, concatenate_datasets
 from torch_geometric.data import Data
 from torch_geometric.loader import DataLoader
 from torch_geometric.utils import to_undirected
 from .mesh_data import MeshData
+from typing import List, Union
 
 
 class GraphDataModule(LightningDataModule):
     def __init__(
         self,
         hf_repo: str,
-        split_name: str,
+        split_name: Union[str, List[str]],
         n_elements: int = None,
         train_size: float = 0.2,
         val_size: float = 0.1,
@@ -22,6 +23,8 @@ class GraphDataModule(LightningDataModule):
         build_radial_graph: bool = False,
         radius: float = None,
         unrolling_steps: int = 1,
+        aggregate_timesteps: int = 1,
+        min_normalized_diff: float = 1e-3,
     ):
         super().__init__()
         self.hf_repo = hf_repo
@@ -34,6 +37,9 @@ class GraphDataModule(LightningDataModule):
             None,
         )
         self.unrolling_steps = unrolling_steps
+        self.aggregate_timesteps = aggregate_timesteps
+        self.min_normalized_diff = min_normalized_diff
+
         self.geometry_dict = {}
         self.train_size = train_size
         self.val_size = val_size
@@ -44,8 +50,30 @@ class GraphDataModule(LightningDataModule):
         self.radius = radius
 
     def prepare_data(self):
-        dataset = load_dataset(self.hf_repo, name="snapshots")[self.split_name]
-        geometry = load_dataset(self.hf_repo, name="geometry")[self.split_name]
+        if isinstance(self.split_name, list):
+            dataset_list = []
+            geometry_list = []
+            for split in self.split_name:
+                dataset_list.append(
+                    load_dataset(self.hf_repo, name="snapshots")[split]
+                )
+                geometry_list.append(
+                    load_dataset(self.hf_repo, name="geometry")[split]
+                )
+
+            dataset = concatenate_datasets(dataset_list)
+            geometry = concatenate_datasets(geometry_list)
+            idx = torch.randperm(len(dataset))
+            dataset = dataset.select(idx.tolist())
+            geometry = geometry.select(idx.tolist())
+        else:
+            dataset = load_dataset(self.hf_repo, name="snapshots")[
+                self.split_name
+            ]
+            geometry = load_dataset(self.hf_repo, name="geometry")[
+                self.split_name
+            ]
+
         if self.n_elements is not None:
             dataset = dataset.select(range(self.n_elements))
             geometry = geometry.select(range(self.n_elements))
@@ -86,10 +114,16 @@ class GraphDataModule(LightningDataModule):
                 dim=0,
             )
         )
-        print(temperatures.shape)
-
+        if not test:
+            for t in range(1, temperatures.size(0)):
+                diff = temperatures[t, :] - temperatures[t - 1, :]
+                norm_diff = torch.norm(diff, p=2) / torch.norm(
+                    temperatures[t - 1], p=2
+                )
+                if norm_diff < self.min_normalized_diff:
+                    temperatures = temperatures[: t + 1, :]
+                    break
         pos = torch.tensor(geometry["points"], dtype=torch.float32)[:, :2]
-
         if self.build_radial_graph:
             raise NotImplementedError(
                 "Radial graph building not implemented yet."
@@ -103,9 +137,7 @@ class GraphDataModule(LightningDataModule):
         boundary_mask = torch.tensor(
             geometry["constraints_mask"], dtype=torch.int64
         )
-        boundary_values = torch.tensor(
-            geometry["constraints_values"], dtype=torch.float32
-        )
+        boundary_values = temperatures[0, boundary_mask]
 
         edge_attr = torch.norm(pos[edge_index[0]] - pos[edge_index[1]], dim=1)
         if self.remove_boundary_edges:
@@ -118,6 +150,9 @@ class GraphDataModule(LightningDataModule):
         data = []
 
         if test:
+            cells = geometry.get("cells", None)
+            if cells is not None:
+                cells = torch.tensor(cells, dtype=torch.int64)
             data.append(
                 MeshData(
                     x=temperatures[0, :].unsqueeze(-1),
@@ -128,6 +163,7 @@ class GraphDataModule(LightningDataModule):
                     edge_attr=edge_attr,
                     boundary_mask=boundary_mask,
                     boundary_values=boundary_values,
+                    cells=cells,
                 )
             )
             return data
@@ -203,7 +239,7 @@ class GraphDataModule(LightningDataModule):
             batch_size=self.batch_size,
             shuffle=True,
             num_workers=8,
-            pin_memory=True,
+            pin_memory=False,
         )
 
     def val_dataloader(self):
@@ -216,7 +252,7 @@ class GraphDataModule(LightningDataModule):
             batch_size=128,
             shuffle=False,
             num_workers=8,
-            pin_memory=True,
+            pin_memory=False,
         )
 
     def test_dataloader(self):
@@ -226,5 +262,5 @@ class GraphDataModule(LightningDataModule):
             batch_size=1,
             shuffle=False,
             num_workers=8,
-            pin_memory=True,
+            pin_memory=False,
         )

ThermalSolver/model/diffusion_net.py

@@ -4,6 +4,27 @@ from torch_geometric.nn import MessagePassing
 from torch.nn.utils import spectral_norm
 
 
+class LogPhysEncoder(nn.Module):
+    """
+    Processes 1/dx in log-space to handle multiple scales of geometry
+    (from micro-meshes to macro-meshes) without numerical instability.
+    """
+
+    def __init__(self, hidden_dim):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            spectral_norm(nn.Linear(1, hidden_dim)),
+            nn.GELU(),
+            spectral_norm(nn.Linear(hidden_dim, 1)),
+            nn.Softplus(),  # Physical conductance must be positive
+        )
+
+    def forward(self, inv_dx):
+        # We use log(1/dx) to linearize the scale of different geometries
+        log_inv_dx = torch.log(inv_dx + 1e-9)
+        return self.mlp(log_inv_dx)
+
+
 class DiffusionLayer(MessagePassing):
     """
     Modella: T_new = T_old + dt * Divergenza(Flusso)
@@ -22,12 +43,7 @@ class DiffusionLayer(MessagePassing):
             spectral_norm(nn.Linear(channels, channels, bias=False)),
         )
 
-        self.phys_encoder = nn.Sequential(
-            spectral_norm(nn.Linear(1, 8, bias=True)),
-            nn.Tanh(),
-            spectral_norm(nn.Linear(8, 1, bias=True)),
-            nn.Softplus(),
-        )
+        self.phys_encoder = LogPhysEncoder(hidden_dim=channels)
 
         self.alpha_param = nn.Parameter(torch.tensor(1e-2))
 
@@ -123,3 +139,4 @@ class DiffusionNet(nn.Module):
         # 6. Final Update (Explicit Euler Step)
         # T_new = T_old + Correction
         return delta_x + x_input * self.dt
+        # return delta_x

experiments/10_steps/config_16_layer_16_hidden_adaptive_refined.yaml

@@ -0,0 +1,72 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.adaptive_refined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 15
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.adaptive_refined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.basic.1_adaptive_refined"
+    n_elements: 100
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_adaptive_refined_combined.yaml

@@ -0,0 +1,63 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.adaptive_refined.combined"
+  callbacks:
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 10
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.adaptive_refined.combined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: 
+      - "4_stripes.basic.1_adaptive_refined"
+      - "3_stripes.basic.1_adaptive_refined"
+      - "2_stripes.basic.1_adaptive_refined"
+    n_elements: 100
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+    
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_refined.yaml

@@ -0,0 +1,72 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.refined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 15
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.refined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.basic.refined"
+    n_elements: 50
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_refined_combined.yaml

@@ -0,0 +1,77 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.refined.combined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 10
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.refined.combined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 10
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: 
+      - "4_stripes.basic.refined"
+      - "3_stripes.basic.refined"
+      - "2_stripes.basic.refined"
+    n_elements: 75
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 10
+    min_normalized_diff: 1e-4
+    
+optimizer: null
+lr_scheduler: null
+ckpt_path: logs.autoregressive.wandb/10_steps/basic.refined.combined/16_layer_16_hidden/6_unrolling_best_checkpoint.ckpt

experiments/10_steps/config_16_layer_16_hidden_refined_star.yaml

@@ -0,0 +1,72 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.refined.star"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 15
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.refined.star/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.star"
+    n_elements: 100
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_star.yaml

@@ -0,0 +1,72 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.star"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 15
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.star/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.star.refined"
+    n_elements: 100
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_16_layer_16_hidden_star_combined.yaml

@@ -0,0 +1,75 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "16_layer_16_hidden.star.combined"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 15
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.star.combined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: 
+      - "4_stripes.star"
+      - "3_stripes.star"
+      - "2_stripes.star"
+    n_elements: 100
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+optimizer: null
+lr_scheduler: null

experiments/10_steps/config_8_layer_16_hidden_star.yaml

@@ -0,0 +1,72 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: gpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  logger:
+    - class_path: lightning.pytorch.loggers.WandbLogger
+      init_args:
+        save_dir: logs.autoregressive.wandb
+        project: "thermal-conduction-unsteady-10.steps"
+        name: "8_layer_16_hidden.star"
+  callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+      init_args:
+        increase_unrolling_steps_by: 4
+        patience: 5
+        last_patience: 15
+        max_unrolling_steps: 10
+        ckpt_path: logs.autoregressive.wandb/10_steps/basic.star/8_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 8
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: "3_stripes.star.refined"
+    n_elements: 100
+    batch_size: 24
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+    min_normalized_diff: 1e-4
+optimizer: null
+lr_scheduler: null

experiments/10_steps/test_config_16_layer_16_hidden_star.yaml

@@ -0,0 +1,76 @@
+# lightning.pytorch==2.5.5
+seed_everything: 1999
+trainer:
+  accelerator: cpu
+  strategy: auto
+  devices: 1
+  num_nodes: 1
+  precision: null
+  # logger:
+  #   - class_path: lightning.pytorch.loggers.WandbLogger
+  #     init_args:
+  #       save_dir: logs.autoregressive.wandb
+  #       project: "thermal-conduction-unsteady-10.steps"
+  #       name: "16_layer_16_hidden.adaptive_refined.combined"
+  # callbacks:
+    # - class_path: lightning.pytorch.callbacks.ModelCheckpoint
+    #   init_args:
+    #     dirpath: logs.autoregressive.wandb/16_refined.10_steps/checkpoints
+    #     monitor: val/loss
+    #     mode: min
+    #     save_top_k: 1
+    #     filename: best-checkpoint
+    # - class_path: lightning.pytorch.callbacks.EarlyStopping
+    #   init_args:
+    #     monitor: val/loss
+    #     mode: min
+    #     patience: 30
+    #     verbose: false
+    # - class_path: ThermalSolver.switch_dataloader_callback.SwitchDataLoaderCallback
+    #   init_args:
+    #     increase_unrolling_steps_by: 4
+    #     patience: 15
+    #     last_patience: 20
+    #     max_unrolling_steps: 10
+    #     ckpt_path: logs.autoregressive.wandb/10_steps/basic.adaptive_refined.combined/16_layer_16_hidden/
+  max_epochs: 1000
+  min_epochs: null
+  max_steps: -1
+  min_steps: null
+  overfit_batches: 0.0
+  log_every_n_steps: 0
+  accumulate_grad_batches: 1
+  default_root_dir: null
+  gradient_clip_val: 1.0
+
+model: 
+  class_path: ThermalSolver.autoregressive_module.GraphSolver
+  init_args:
+    model_class_path: ThermalSolver.model.diffusion_net.DiffusionNet
+    model_init_args: 
+      input_dim: 1
+      hidden_dim: 16
+      output_dim: 1
+      n_layers: 16
+    unrolling_steps: 2
+    
+data: 
+  class_path: ThermalSolver.graph_datamodule_unsteady.GraphDataModule
+  init_args:
+    hf_repo: "SISSAmathLab/thermal-conduction-unsteady"
+    split_name: 
+      # - "2_stripes.basic.refined"
+      # - "3_stripes.basic.refined"
+      # - "4_stripes.basic.1_adaptive_refined"
+      - "3_stripes.star"
+    n_elements: 50
+    batch_size: 32
+    train_size: 0.7
+    val_size: 0.2
+    test_size: 0.1
+    build_radial_graph: false
+    remove_boundary_edges: true
+    unrolling_steps: 2
+optimizer: null
+lr_scheduler: null
+ckpt_path: /home/folivo/storage/thermal-conduction-ml/logs.autoregressive.wandb/10_steps/basic.star.combined/16_layer_16_hidden/10_unrolling_best_checkpoint.ckpt