[Example] Add allen cahn example (#845)

* allow empty optimizer when saving checkpoint

* add model averaging module

* fix return dtype inconsistency with global dtype

* use python func instead of sympy function for pow(u,3) get a bit poor L2 error than multiply(u*u*u)

* refine AllenCahn docstring

* support save and load for average model module

* add 3 ema unitests

* update 2023 to 2024

* add ema config pydantic scheme

* add avg_range for SWA

* update field_validator for swa and ema

* support period embedding for MLP

* Keep non-float data when reading file

* update ema and save_load, printer and eval, solver module code

* add allen_cahn example

* refine code

* save buffer and non-grad required params in ema

* add unitest for ema with buffer

* fix epoch_ema saving

* add unitest for ema state_dict

* refine allen_cahn_plain.py

* fix string to floating conversion in reader.py

* fix string to floating conversion in reader.py

* remove print code in solver

* Update allen_cahn_plain.py

* Update misc.py

---------

Co-authored-by: zzm <[email protected]>

Author: HydrogenSulfate

deploy/python_infer/pinn_predictor.py

@@ -97,7 +97,7 @@ def predict(
 
         # inference by batch
         for batch_id in range(1, batch_num + 1):
-            if batch_id % self.log_freq == 0 or batch_id == batch_num:
+            if batch_id == 1 or batch_id % self.log_freq == 0 or batch_id == batch_num:
                 logger.info(f"Predicting batch {batch_id}/{batch_num}")
 
             # prepare batch input dict

docs/zh/api/data/dataset.md

@@ -9,6 +9,7 @@
         - ChipHeatDataset
         - CSVDataset
         - IterableCSVDataset
+        - ContinuousNamedArrayDataset
         - ERA5Dataset
         - ERA5SampledDataset
         - IterableMatDataset

examples/allen_cahn/allen_cahn_plain.py

@@ -0,0 +1,298 @@
+"""
+Reference: https://docs.nvidia.com/deeplearning/modulus/modulus-v2209/user_guide/intermediate/adding_stl_files.html
+"""
+
+from os import path as osp
+
+import hydra
+import numpy as np
+import paddle
+import scipy.io as sio
+from matplotlib import pyplot as plt
+from omegaconf import DictConfig
+
+import ppsci
+from ppsci.utils import misc
+
+dtype = paddle.get_default_dtype()
+
+
+def plot(
+    t_star: np.ndarray,
+    x_star: np.ndarray,
+    u_ref: np.ndarray,
+    u_pred: np.ndarray,
+    output_dir: str,
+):
+    fig = plt.figure(figsize=(18, 5))
+    TT, XX = np.meshgrid(t_star, x_star, indexing="ij")
+    u_ref = u_ref.reshape([len(t_star), len(x_star)])
+
+    plt.subplot(1, 3, 1)
+    plt.pcolor(TT, XX, u_ref, cmap="jet")
+    plt.colorbar()
+    plt.xlabel("t")
+    plt.ylabel("x")
+    plt.title("Exact")
+    plt.tight_layout()
+
+    plt.subplot(1, 3, 2)
+    plt.pcolor(TT, XX, u_pred, cmap="jet")
+    plt.colorbar()
+    plt.xlabel("t")
+    plt.ylabel("x")
+    plt.title("Predicted")
+    plt.tight_layout()
+
+    plt.subplot(1, 3, 3)
+    plt.pcolor(TT, XX, np.abs(u_ref - u_pred), cmap="jet")
+    plt.colorbar()
+    plt.xlabel("t")
+    plt.ylabel("x")
+    plt.title("Absolute error")
+    plt.tight_layout()
+
+    fig_path = osp.join(output_dir, "ac.png")
+    fig.savefig(fig_path, bbox_inches="tight", dpi=400)
+    plt.close()
+
+
+def train(cfg: DictConfig):
+    # set model
+    model = ppsci.arch.MLP(**cfg.MODEL)
+
+    # set equation
+    equation = {"AllenCahn": ppsci.equation.AllenCahn(0.01**2)}
+
+    data = sio.loadmat(cfg.DATA_PATH)
+    u_ref = data["usol"].astype(dtype)  # (nt, nx)
+    t_star = data["t"].flatten().astype(dtype)  # [nt, ]
+    x_star = data["x"].flatten().astype(dtype)  # [nx, ]
+
+    u0 = u_ref[0, :]  # [nx, ]
+
+    t0 = t_star[0]  # float
+    t1 = t_star[-1]  # float
+
+    x0 = x_star[0]  # float
+    x1 = x_star[-1]  # float
+
+    # set constraint
+    def gen_input_batch():
+        tx = np.random.uniform(
+            [t0, x0],
+            [t1, x1],
+            (cfg.TRAIN.batch_size, 2),
+        ).astype(dtype)
+        return {
+            "t": tx[:, 0:1],
+            "x": tx[:, 1:2],
+        }
+
+    def gen_label_batch(input_batch):
+        return {"allen_cahn": np.zeros([cfg.TRAIN.batch_size, 1], dtype)}
+
+    pde_constraint = ppsci.constraint.SupervisedConstraint(
+        {
+            "dataset": {
+                "name": "ContinuousNamedArrayDataset",
+                "input": gen_input_batch,
+                "label": gen_label_batch,
+            },
+        },
+        output_expr=equation["AllenCahn"].equations,
+        loss=ppsci.loss.MSELoss(),
+        name="PDE",
+    )
+
+    ic_input = {"t": np.full([len(x_star), 1], t0), "x": x_star.reshape([-1, 1])}
+    ic_label = {"u": u0.reshape([-1, 1])}
+    ic = ppsci.constraint.SupervisedConstraint(
+        {
+            "dataset": {
+                "name": "IterableNamedArrayDataset",
+                "input": ic_input,
+                "label": ic_label,
+            },
+        },
+        output_expr={"u": lambda out: out["u"]},
+        loss=ppsci.loss.MSELoss("mean"),
+        name="IC",
+    )
+    # wrap constraints together
+    constraint = {
+        pde_constraint.name: pde_constraint,
+        ic.name: ic,
+    }
+
+    # set optimizer
+    lr_scheduler = ppsci.optimizer.lr_scheduler.ExponentialDecay(
+        **cfg.TRAIN.lr_scheduler
+    )()
+    optimizer = ppsci.optimizer.Adam(lr_scheduler)(model)
+
+    # set validator
+    tx_star = misc.cartesian_product(t_star, x_star).astype(dtype)
+    eval_data = {"t": tx_star[:, 0:1], "x": tx_star[:, 1:2]}
+    eval_label = {"u": u_ref.reshape([-1, 1])}
+    u_validator = ppsci.validate.SupervisedValidator(
+        {
+            "dataset": {
+                "name": "NamedArrayDataset",
+                "input": eval_data,
+                "label": eval_label,
+            },
+            "batch_size": cfg.EVAL.batch_size,
+        },
+        ppsci.loss.MSELoss("mean"),
+        {"u": lambda out: out["u"]},
+        metric={"L2Rel": ppsci.metric.L2Rel()},
+        name="u_validator",
+    )
+    validator = {u_validator.name: u_validator}
+
+    # initialize solver
+    solver = ppsci.solver.Solver(
+        model,
+        constraint,
+        cfg.output_dir,
+        optimizer,
+        lr_scheduler,
+        cfg.TRAIN.epochs,
+        cfg.TRAIN.iters_per_epoch,
+        save_freq=cfg.TRAIN.save_freq,
+        log_freq=cfg.log_freq,
+        eval_during_train=True,
+        eval_freq=cfg.TRAIN.eval_freq,
+        seed=cfg.seed,
+        equation=equation,
+        validator=validator,
+        pretrained_model_path=cfg.TRAIN.pretrained_model_path,
+        checkpoint_path=cfg.TRAIN.checkpoint_path,
+        eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
+        use_tbd=True,
+        cfg=cfg,
+    )
+    # train model
+    solver.train()
+    # evaluate after finished training
+    solver.eval()
+    # visualize prediction after finished training
+    u_pred = solver.predict(
+        eval_data, batch_size=cfg.EVAL.batch_size, return_numpy=True
+    )["u"]
+    u_pred = u_pred.reshape([len(t_star), len(x_star)])
+
+    # plot
+    plot(t_star, x_star, u_ref, u_pred, cfg.output_dir)
+
+
+def evaluate(cfg: DictConfig):
+    # set model
+    model = ppsci.arch.MLP(**cfg.MODEL)
+
+    data = sio.loadmat(cfg.DATA_PATH)
+    u_ref = data["usol"].astype(dtype)  # (nt, nx)
+    t_star = data["t"].flatten().astype(dtype)  # [nt, ]
+    x_star = data["x"].flatten().astype(dtype)  # [nx, ]
+
+    # set validator
+    tx_star = misc.cartesian_product(t_star, x_star).astype(dtype)
+    eval_data = {"t": tx_star[:, 0:1], "x": tx_star[:, 1:2]}
+    eval_label = {"u": u_ref.reshape([-1, 1])}
+    u_validator = ppsci.validate.SupervisedValidator(
+        {
+            "dataset": {
+                "name": "NamedArrayDataset",
+                "input": eval_data,
+                "label": eval_label,
+            },
+            "batch_size": cfg.EVAL.batch_size,
+        },
+        ppsci.loss.MSELoss("mean"),
+        {"u": lambda out: out["u"]},
+        metric={"L2Rel": ppsci.metric.L2Rel()},
+        name="u_validator",
+    )
+    validator = {u_validator.name: u_validator}
+
+    # initialize solver
+    solver = ppsci.solver.Solver(
+        model,
+        output_dir=cfg.output_dir,
+        log_freq=cfg.log_freq,
+        validator=validator,
+        pretrained_model_path=cfg.EVAL.pretrained_model_path,
+        eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
+    )
+
+    # evaluate after finished training
+    solver.eval()
+    # visualize prediction after finished training
+    u_pred = solver.predict(
+        eval_data, batch_size=cfg.EVAL.batch_size, return_numpy=True
+    )["u"]
+    u_pred = u_pred.reshape([len(t_star), len(x_star)])
+
+    # plot
+    plot(t_star, x_star, u_ref, u_pred, cfg.output_dir)
+
+
+def export(cfg: DictConfig):
+    # set model
+    model = ppsci.arch.MLP(**cfg.MODEL)
+
+    # initialize solver
+    solver = ppsci.solver.Solver(
+        model,
+        pretrained_model_path=cfg.INFER.pretrained_model_path,
+    )
+    # export model
+    from paddle.static import InputSpec
+
+    input_spec = [
+        {key: InputSpec([None, 1], "float32", name=key) for key in model.input_keys},
+    ]
+    solver.export(input_spec, cfg.INFER.export_path, with_onnx=False)
+
+
+def inference(cfg: DictConfig):
+    from deploy.python_infer import pinn_predictor
+
+    predictor = pinn_predictor.PINNPredictor(cfg)
+    data = sio.loadmat(cfg.DATA_PATH)
+    u_ref = data["usol"].astype(dtype)  # (nt, nx)
+    t_star = data["t"].flatten().astype(dtype)  # [nt, ]
+    x_star = data["x"].flatten().astype(dtype)  # [nx, ]
+    tx_star = misc.cartesian_product(t_star, x_star).astype(dtype)
+
+    input_dict = {"t": tx_star[:, 0:1], "x": tx_star[:, 1:2]}
+    output_dict = predictor.predict(input_dict, cfg.INFER.batch_size)
+    output_dict = {
+        store_key: output_dict[infer_key]
+        for store_key, infer_key in zip(cfg.MODEL.output_keys, output_dict.keys())
+    }
+    u_pred = output_dict["u"].reshape([len(t_star), len(x_star)])
+    # mapping data to cfg.INFER.output_keys
+
+    plot(t_star, x_star, u_ref, u_pred, cfg.output_dir)
+
+
+@hydra.main(version_base=None, config_path="./conf", config_name="allen_cahn.yaml")
+def main(cfg: DictConfig):
+    if cfg.mode == "train":
+        train(cfg)
+    elif cfg.mode == "eval":
+        evaluate(cfg)
+    elif cfg.mode == "export":
+        export(cfg)
+    elif cfg.mode == "infer":
+        inference(cfg)
+    else:
+        raise ValueError(
+            f"cfg.mode should in ['train', 'eval', 'export', 'infer'], but got '{cfg.mode}'"
+        )
+
+
+if __name__ == "__main__":
+    main()