【PPSCI Export&Infer No.4】laplace2d

docs/zh/examples/laplace2d.md

@@ -14,6 +14,18 @@
     python laplace2d.py mode=eval EVAL.pretrained_model_path=https://paddle-org.bj.bcebos.com/paddlescience/models/laplace2d/laplace2d_pretrained.pdparams
     ```
 
+=== "模型导出命令"
+
+    ``` sh
+    python laplace2d.py mode=export
+    ```
+
+=== "模型推理命令"
+
+    ``` sh
+    python laplace2d.py mode=infer
+    ```
+
 | 预训练模型  | 指标 |
 |:--| :--|
 | [laplace2d_pretrained.pdparams](https://paddle-org.bj.bcebos.com/paddlescience/models/laplace2d/laplace2d_pretrained.pdparams) | loss(MSE_Metric): 0.00002<br>MSE.u(MSE_Metric): 0.00002 |

examples/laplace/conf/laplace2d.yaml

@@ -22,6 +22,7 @@ hydra:
 # general settings
 mode: train # running mode: train/eval
 seed: 42
+log_freq: 20
 output_dir: ${hydra:run.dir}
 NPOINT_INTERIOR: 9801
 NPOINT_BC: 400
@@ -50,3 +51,20 @@ TRAIN:
 EVAL:
   pretrained_model_path: null
   eval_with_no_grad: true
+
+INFER:
+  pretrained_model_path: https://paddle-org.bj.bcebos.com/paddlescience/models/laplace2d/laplace2d_pretrained.pdparams
+  export_path: ./inference/laplace2d
+  pdmodel_path: ${INFER.export_path}.pdmodel
+  pdpiparams_path: ${INFER.export_path}.pdiparams
+  device: gpu
+  engine: native
+  precision: fp32
+  onnx_path: ${INFER.export_path}.onnx
+  ir_optim: true
+  min_subgraph_size: 10
+  gpu_mem: 4000
+  gpu_id: 0
+  max_batch_size: 64
+  num_cpu_threads: 4
+  batch_size: 64

examples/laplace/laplace2d.py

@@ -205,14 +205,71 @@ def u_solution_func(out):
     solver.visualize()
 
 
+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)
+
+
+def inference(cfg: DictConfig):
+    from deploy.python_infer import pinn_predictor
+
+    predictor = pinn_predictor.PINNPredictor(cfg)
+
+    # set geometry
+    geom = {
+        "rect": ppsci.geometry.Rectangle(
+            cfg.DIAGONAL_COORD.xmin, cfg.DIAGONAL_COORD.xmax
+        )
+    }
+    NPOINT_TOTAL = cfg.NPOINT_INTERIOR + cfg.NPOINT_BC
+    input_dict = geom["rect"].sample_interior(NPOINT_TOTAL, evenly=True)
+
+    output_dict = predictor.predict(
+        {key: input_dict[key] for key in cfg.MODEL.input_keys}, cfg.INFER.batch_size
+    )
+
+    # mapping data to cfg.INFER.output_keys
+    output_dict = {
+        store_key: output_dict[infer_key]
+        for store_key, infer_key in zip(cfg.MODEL.output_keys, output_dict.keys())
+    }
+
+    # save result
+    ppsci.visualize.save_vtu_from_dict(
+        "./laplace2d_pred.vtu",
+        {**input_dict, **output_dict},
+        input_dict.keys(),
+        cfg.MODEL.output_keys,
+    )
+
+
 @hydra.main(version_base=None, config_path="./conf", config_name="laplace2d.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'], but got '{cfg.mode}'")
+        raise ValueError(
+            f"cfg.mode should in ['train', 'eval', 'export', 'infer'], but got '{cfg.mode}'"
+        )
 
 
 if __name__ == "__main__":