Merge pull request #514 from WenjieDu/(fix)model_saving

`model_saving_strategy=best` does not work

pypots/classification/base.py

@@ -347,8 +347,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):

pypots/classification/brits/model.py

@@ -228,7 +228,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/classification/grud/model.py

@@ -204,7 +204,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/classification/raindrop/model.py

@@ -248,7 +248,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/clustering/crli/model.py

@@ -295,7 +295,7 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
                     saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
@@ -354,7 +354,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/clustering/vader/model.py

@@ -303,8 +303,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):
@@ -367,7 +367,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/forecasting/base.py

@@ -346,8 +346,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):

pypots/forecasting/csdi/model.py

@@ -307,8 +307,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):
@@ -379,7 +379,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/autoformer/model.py

@@ -234,7 +234,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/base.py

@@ -346,8 +346,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):

pypots/imputation/brits/model.py

@@ -216,7 +216,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/crossformer/model.py

@@ -240,7 +240,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/csdi/model.py

@@ -287,8 +287,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):
@@ -363,7 +363,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/dlinear/model.py

@@ -211,7 +211,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/etsformer/model.py

@@ -234,7 +234,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/fedformer/model.py

@@ -248,7 +248,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/film/model.py

@@ -228,7 +228,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/frets/model.py

@@ -210,7 +210,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/gpvae/model.py

@@ -312,8 +312,8 @@ def _train_model(
 
                 # save the model if necessary
                 self._auto_save_model_if_necessary(
-                    confirm_saving=self.best_epoch == epoch,
-                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss}",
+                    confirm_saving=self.best_epoch == epoch and self.model_saving_strategy == "better",
+                    saving_name=f"{self.__class__.__name__}_epoch{epoch}_loss{mean_loss:.4f}",
                 )
 
                 if os.getenv("enable_tuning", False):
@@ -377,7 +377,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/grud/model.py

@@ -201,7 +201,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/imputeformer/model.py

@@ -253,7 +253,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/informer/model.py

@@ -228,7 +228,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/itransformer/model.py

@@ -255,7 +255,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/koopa/model.py

@@ -241,7 +241,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/micn/model.py

@@ -222,7 +222,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/moderntcn/model.py

@@ -252,7 +252,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/mrnn/model.py

@@ -218,7 +218,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/nonstationary_transformer/model.py

@@ -244,7 +244,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/patchtst/model.py

@@ -264,7 +264,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/pyraformer/model.py

@@ -240,7 +240,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/reformer/model.py

@@ -241,7 +241,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/revinscinet/model.py

@@ -246,7 +246,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/saits/model.py

@@ -268,7 +268,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/scinet/model.py

@@ -248,7 +248,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/stemgnn/model.py

@@ -222,7 +222,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/tcn/model.py

@@ -216,7 +216,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,

pypots/imputation/tefn/model.py

@@ -188,7 +188,7 @@ def fit(
         self.model.eval()  # set the model as eval status to freeze it.
 
         # Step 3: save the model if necessary
-        self._auto_save_model_if_necessary(confirm_saving=True)
+        self._auto_save_model_if_necessary(confirm_saving=self.model_saving_strategy == "best")
 
     def predict(
         self,