[Example] Add STAFNet Model for Air Quality Prediction

examples/demo/conf/stafnet.yaml

@@ -0,0 +1,85 @@
+defaults: 
+   - ppsci_default 
+   - TRAIN: train_default 
+   - TRAIN/ema: ema_default 
+   - TRAIN/swa: swa_default 
+   - EVAL: eval_default 
+   - INFER: infer_default 
+   - hydra/job/config/override_dirname/exclude_keys: exclude_keys_default 
+   - _self_ 
+hydra:
+  run:
+    # dynamic output directory according to running time and override name
+    dir: outputs_chip_heat/${now:%Y-%m-%d}/${now:%H-%M-%S}/${hydra.job.override_dirname}
+  job:
+    name: ${mode} # name of logfile
+    chdir: false # keep current working directory unchanged
+  callbacks:
+    init_callback:
+      _target_: ppsci.utils.callbacks.InitCallback
+  sweep:
+    # output directory for multirun
+    dir: ${hydra.run.dir}
+    subdir: ./
+
+# general settings
+mode: train # running mode: train/eval
+seed: 42
+output_dir: ${hydra:run.dir}
+log_freq: 20
+# dataset setting
+STAFNet_DATA_PATH: "/data6/home/yinhang2021/dataset/chongqing_1921/train_data.pkl" # 
+DATASET:
+  label_keys: ["label"]
+  data_dir: "/data6/home/yinhang2021/dataset/chongqing_1921/train_data.pkl"
+
+
+MODEL:
+  input_keys: ["aq_train_data","mete_train_data",]
+  output_keys: ["label"]
+  output_attention: True
+  seq_len: 72
+  pred_len: 48
+  aq_gat_node_features: 7
+  aq_gat_node_num: 35
+  mete_gat_node_features: 7
+  mete_gat_node_num: 18
+  gat_hidden_dim: 32
+  gat_edge_dim: 3
+  e_layers: 1
+  enc_in: 7
+  dec_in: 7
+  c_out: 7
+  d_model: 16
+  embed: "fixed"
+  freq: "t"
+  dropout: 0.05
+  factor: 3
+  n_heads: 4
+  d_ff: 32
+  num_kernels: 6
+  top_k: 4
+
+# training settings
+TRAIN: 
+  epochs: 100 
+  iters_per_epoch: 400 
+  save_freq: 10 
+  eval_during_train: true 
+  eval_freq: 10 
+  batch_size: 1 
+  lr_scheduler:  
+    epochs: ${TRAIN.epochs}  
+    iters_per_epoch: ${TRAIN.iters_per_epoch}  
+    learning_rate: 0.001  
+    step_size: 10 
+    gamma: 0.9 
+  pretrained_model_path: null 
+  checkpoint_path: null 
+
+EVAL:
+  eval_data_path: "/data6/home/yinhang2021/dataset/chongqing_1921/val_data.pkl"
+  pretrained_model_path: null
+  compute_metric_by_batch: false
+  eval_with_no_grad: true
+  batch_size: 1

examples/demo/demo.py

@@ -0,0 +1,153 @@
+import ppsci
+from ppsci.utils import logger
+from omegaconf import DictConfig
+import hydra
+import paddle
+from ppsci.data.dataset.stafnet_dataset import gat_lstmcollate_fn
+import multiprocessing
+
+def train(cfg: DictConfig):
+    # set model
+    model = ppsci.arch.STAFNet(**cfg.MODEL) 
+    train_dataloader_cfg = {
+        "dataset": {
+            "name": "STAFNetDataset",
+            "file_path": cfg.DATASET.data_dir,
+            "input_keys": cfg.MODEL.input_keys,
+            "label_keys": cfg.MODEL.output_keys,
+            "seq_len": cfg.MODEL.seq_len,
+            "pred_len": cfg.MODEL.pred_len,
+
+        },
+        "batch_size": cfg.TRAIN.batch_size,
+        "sampler": {
+            "name": "BatchSampler",
+            "drop_last": False,
+            "shuffle": True,
+        },
+        "collate_fn": gat_lstmcollate_fn,
+    }
+    eval_dataloader_cfg= {
+        "dataset": {
+            "name": "STAFNetDataset",
+            "file_path": cfg.EVAL.eval_data_path,
+            "input_keys": cfg.MODEL.input_keys,
+            "label_keys": cfg.MODEL.output_keys,
+            "seq_len": cfg.MODEL.seq_len,
+            "pred_len": cfg.MODEL.pred_len,
+        },
+        "batch_size": cfg.TRAIN.batch_size,
+        "sampler": {
+            "name": "BatchSampler",
+            "drop_last": False,
+            "shuffle": True,
+        },
+        "collate_fn": gat_lstmcollate_fn,
+    }
+
+    sup_constraint = ppsci.constraint.SupervisedConstraint(
+        train_dataloader_cfg,
+        loss=ppsci.loss.MSELoss("mean"),
+        name="STAFNet_Sup",
+    )
+    constraint = {sup_constraint.name: sup_constraint}
+    sup_validator = ppsci.validate.SupervisedValidator(
+        eval_dataloader_cfg,
+        loss=ppsci.loss.MSELoss("mean"),
+        metric={"MSE": ppsci.metric.MSE()},
+        name="Sup_Validator",
+    )
+    validator = {sup_validator.name: sup_validator}
+
+     # set optimizer
+    lr_scheduler = ppsci.optimizer.lr_scheduler.Step(**cfg.TRAIN.lr_scheduler)()
+    LEARNING_RATE = cfg.TRAIN.lr_scheduler.learning_rate
+    optimizer = ppsci.optimizer.Adam(LEARNING_RATE)(model)
+    output_dir = cfg.output_dir
+    ITERS_PER_EPOCH = len(sup_constraint.data_loader)
+
+    # initialize solver
+    solver = ppsci.solver.Solver(
+        model,
+        constraint,
+        output_dir,
+        optimizer,
+        lr_scheduler,
+        cfg.TRAIN.epochs,
+        ITERS_PER_EPOCH,
+        eval_during_train=cfg.TRAIN.eval_during_train,
+        seed=cfg.seed,
+        validator=validator,
+        compute_metric_by_batch=cfg.EVAL.compute_metric_by_batch,
+        eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
+    )
+
+    # train model
+    solver.train()
+
+def evaluate(cfg: DictConfig):
+    """
+    Validate after training an epoch
+
+    :param epoch: Integer, current training epoch.
+    :return: A log that contains information about validation
+    """
+    model = ppsci.arch.STAFNet(**cfg.MODEL) 
+    eval_dataloader_cfg= {
+        "dataset": {
+            "name": "STAFNetDataset",
+            "file_path": cfg.EVAL.eval_data_path,
+            "input_keys": cfg.MODEL.input_keys,
+            "label_keys": cfg.MODEL.output_keys,
+            "seq_len": cfg.MODEL.seq_len,
+            "pred_len": cfg.MODEL.pred_len,
+        },
+        "batch_size": cfg.TRAIN.batch_size,
+        "sampler": {
+            "name": "BatchSampler",
+            "drop_last": False,
+            "shuffle": True,
+        },
+        "collate_fn": gat_lstmcollate_fn,
+    }
+    sup_validator = ppsci.validate.SupervisedValidator(
+        eval_dataloader_cfg,
+        loss=ppsci.loss.MSELoss("mean"),
+        metric={"MSE": ppsci.metric.MSE()},
+        name="Sup_Validator",
+    )
+    validator = {sup_validator.name: sup_validator}
+
+    # initialize solver
+    solver = ppsci.solver.Solver(
+        model,
+        validator=validator,
+        cfg=cfg,
+        pretrained_model_path=cfg.EVAL.pretrained_model_path,
+        compute_metric_by_batch=cfg.EVAL.compute_metric_by_batch,
+        eval_with_no_grad=cfg.EVAL.eval_with_no_grad,
+    )
+
+    # evaluate model
+    solver.eval()
+
+
+@hydra.main(version_base=None, config_path="./conf", config_name="stafnet.yaml")
+def main(cfg: DictConfig):
+    if cfg.mode == "train":
+        train(cfg)
+    elif cfg.mode == "eval":
+        evaluate(cfg)
+    else:
+        raise ValueError(f"cfg.mode should in ['train', 'eval'], but got '{cfg.mode}'")
+
+if __name__ == "__main__":
+    # set random seed for reproducibility
+    ppsci.utils.misc.set_random_seed(42)
+    # set output directory
+    OUTPUT_DIR = "./output_example"
+    # initialize logger
+    logger.init_logger("ppsci", f"{OUTPUT_DIR}/train.log", "info")
+    multiprocessing.set_start_method("spawn")
+
+    main()

ppsci/arch/__init__.py

@@ -61,6 +61,7 @@
 from ppsci.utils import logger  # isort:skip
 from ppsci.arch.regdgcnn import RegDGCNN  # isort:skip
 from ppsci.arch.ifm_mlp import IFMMLP  # isort:skip
+from ppsci.arch.stafnet import STAFNet  # isort:skip
 
 __all__ = [
     "MoFlowNet",
@@ -111,6 +112,7 @@
     "VelocityGenerator",
     "RegDGCNN",
     "IFMMLP",
+    "STAFNet",
 ]