modnn 3.0.0__tar.gz → 3.0.2__tar.gz

{modnn-3.0.0 → modnn-3.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: modnn
-Version: 3.0.0
+Version: 3.0.2
 Summary: Physics-Informed Modularized Neural Network for Building Energy Modeling
 Author-email: Zixin Jiang <zjiang19@syr.edu>
 License-Expression: MIT

{modnn-3.0.0 → modnn-3.0.2}/modnn/Models/ModNN_data.py

@@ -385,4 +385,4 @@ class ModNN_step(nn.Module):
             # After get total flux, we can predict the ΔTzone, and use residual connection to predict Tzone step by step
             E_Zone_T =  input_X[:, i:i+1, [0]] + self.Zone(total_flux)
 
-        return E_Zone_T, _, (_, _, _)
+        return E_Zone_T, None, (None, None, None)

{modnn-3.0.0 → modnn-3.0.2}/modnn/utils.py

@@ -820,36 +820,30 @@ class Mod:
         # savemodel = os.path.join(folder_name, mdl_name)
         # torch.save(self.control_mdl.state_dict(), savemodel)
 
-    def emulator(self, mdl_name=None):
-        """
-        :param mdl_name: load an existing model or load just trained model
-        :return: model
-        """
-        start_time = time.time()
-        print("Loading emulator model")
+    def step_mdl(self, mdl_name=None):
         if "modnn" in self.args["modeltype"]:
             if self.args["envelop_mdl"] == "physics":
                 model = ModNN_phy.ModNN(self.args).to(self.device)
             else:
-                model = ModNN_data.ModNN(self.args).to(self.device)
+                model = ModNN_data.ModNN_step(self.args).to(self.device)
         if self.args["modeltype"] == "LSTM":
             model = BaseNN.Baseline(self.args).to(self.device)
 
         folder_name = ("../Saved/{}/Trained_mdl".format(self.args['save_name']) +
-                       'Enco{}_Deco{}'.format(str(self.args['enLen']),str(self.args['deLen'])))
+                       'Enco{}_Deco{}'.format(str(self.args['enLen']), str(self.args['deLen'])))
         if mdl_name is None:
             mdl_name = '{}_{}daysTest_on{}.pth'.format(self.args["modeltype"],
                                                        str(self.args["trainday"]),
                                                        self.dataset.test_start)
         else:
-            mdl_name=mdl_name
+            mdl_name = mdl_name
         if not os.path.exists(folder_name):
             os.makedirs(folder_name)
         loadmodel = os.path.join(folder_name, mdl_name)
         model.load_state_dict(torch.load(loadmodel))
         model.eval()
         self.model = model
-        print("--- %s seconds ---" % (time.time() - start_time))
+        return model
 
 
 

{modnn-3.0.0 → modnn-3.0.2}/modnn.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: modnn
-Version: 3.0.0
+Version: 3.0.2
 Summary: Physics-Informed Modularized Neural Network for Building Energy Modeling
 Author-email: Zixin Jiang <zjiang19@syr.edu>
 License-Expression: MIT

{modnn-3.0.0 → modnn-3.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "modnn"
-version = "3.0.0"
+version = "3.0.2"
 description = "Physics-Informed Modularized Neural Network for Building Energy Modeling"
 readme = "README.md"
 requires-python = ">=3.7"