Updated thesis

src/data/dataset.py

@@ -169,8 +169,7 @@ class NrvDataset(Dataset):
             all_features = torch.cat(all_features_list, dim=0)
 
         else:
-            all_features_list = [nrv_features + self.]
-            
+            all_features_list = [nrv_features.unsqueeze(1)]
 
             if self.forecast_features.numel() > 0:
                 history_forecast_features = self.forecast_features[

src/trainers/diffusion_trainer.py

@@ -80,11 +80,12 @@ class DiffusionTrainer:
         data_processor: DataProcessor,
         device: torch.device,
         policy_evaluator: PolicyEvaluator = None,
+        noise_steps: int = 300,
     ):
         self.model = model
         self.device = device
 
-        self.noise_steps = 300
+        self.noise_steps = noise_steps
         self.beta_start = 0.0001
         self.beta_end = 0.02
         self.ts_length = 96

src/training_scripts/diffusion_training.py

@@ -2,7 +2,7 @@ from src.utils.clearml import ClearMLHelper
 
 clearml_helper = ClearMLHelper(project_name="Thesis/NrvForecast")
 task = clearml_helper.get_task(
-    task_name="Diffusion Training: hidden_sizes=[1024, 1024] (300 steps), lr=0.0001, time_dim=8 + NRV + L + W + PV + NP",
+    task_name="Diffusion Training: hidden_sizes=[256, 256] (30 steps), lr=0.0001, time_dim=8",
 )
 task.execute_remotely(queue_name="default", exit_process=True)
 
@@ -19,16 +19,16 @@ from src.policies.PolicyEvaluator import PolicyEvaluator
 data_config = DataConfig()
 data_config.NRV_HISTORY = True
 
-data_config.LOAD_HISTORY = True
-data_config.LOAD_FORECAST = True
+data_config.LOAD_HISTORY = False
+data_config.LOAD_FORECAST = False
 
-data_config.PV_FORECAST = True
-data_config.PV_HISTORY = True
+data_config.PV_FORECAST = False
+data_config.PV_HISTORY = False
 
-data_config.WIND_FORECAST = True
-data_config.WIND_HISTORY = True
+data_config.WIND_FORECAST = False
+data_config.WIND_HISTORY = False
 
-data_config.NOMINAL_NET_POSITION = True
+data_config.NOMINAL_NET_POSITION = False
 
 data_config = task.connect(data_config, name="data_features")
 
@@ -42,7 +42,7 @@ print("Input dim: ", inputDim)
 model_parameters = {
     "epochs": 15000,
     "learning_rate": 0.0001,
-    "hidden_sizes": [1024, 1024],
+    "hidden_sizes": [256, 256],
     "time_dim": 8,
 }
 
@@ -71,6 +71,6 @@ policy_evaluator = PolicyEvaluator(baseline_policy, task)
 
 #### Trainer ####
 trainer = DiffusionTrainer(
-    model, data_processor, "cuda", policy_evaluator=policy_evaluator
+    model, data_processor, "cuda", policy_evaluator=policy_evaluator, noise_steps=30
 )
 trainer.train(model_parameters["epochs"], model_parameters["learning_rate"], task)