checkpoint

trainingModel/run_training.py

@@ -1,15 +1,18 @@
 import os
 import numpy as np
-
 from clearml import Task, Dataset
 from datasets import load_dataset
-from dataPrep.helpers.transforms_loaders import make_dataset_loaders
 
-import torch
-from models.modelOne import modelOne
-from trainingModel.Training import train_model
+# Latest Data Prep Task 
+all_tasks = Task.get_tasks(project_name="Small Group Project")
+if not all_tasks:
+    raise RuntimeError("No tasks found in project 'Small Group Project'")
 
+dp_tasks = [t for t in all_tasks if t.name == "Data Preparation"]
+if not dp_tasks:
+    raise RuntimeError("No 'Data Preparation' tasks found in this project!")
 
+<<<<<<< HEAD
 # -------------- Load Data --------------
 
 all_tasks = Task.get_tasks(project_name="Small Group Project")
@@ -25,6 +28,12 @@ latest_task = max(dp_tasks, key=lambda t: t.id)
 DYNAMIC_TASK_ID = latest_task.id
 DATA_PREP = Task.get_task(task_id=DYNAMIC_TASK_ID)
 
+=======
+latest_task = max(dp_tasks, key=lambda t: t.id)
+DYNAMIC_TASK_ID = latest_task.id
+DATA_PREP = Task.get_task(task_id=DYNAMIC_TASK_ID)
+
+>>>>>>> 20050ad82ebca27a376e15837a7abf79fca23e98
 # Dataset ID 
 config_objects = DATA_PREP.get_configuration_objects()
 raw_meta = config_objects["Dataset Metadata"]
@@ -34,7 +43,12 @@ dataset_id = raw_meta.split("=")[1].strip().replace('"', "")
 subset_clearml = Dataset.get(dataset_id=dataset_id)
 local_folder = subset_clearml.get_local_copy()
 
+<<<<<<< HEAD
 subset_indices = np.load(os.path.join(local_folder, "subset_indices.npy"))
+=======
+subset_indices_path = os.path.join(local_folder, "subset_indices.npy")
+subset_indices = np.load(subset_indices_path)
+>>>>>>> 20050ad82ebca27a376e15837a7abf79fca23e98
 
 # Load Dataset Parameters 
 data_params = DATA_PREP.get_parameters()
@@ -116,8 +130,15 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
 # ------- Train the model (on subset for now) -------
  
+<<<<<<< HEAD
 print("\n--- Starting Model Training on Subset ---")
 training_metrics = train_model(
+=======
+#When calling this function, the model should be trained on the given dataset
+
+print("\n--- Starting Model Training on Subset ---")
+train_model(
+>>>>>>> 20050ad82ebca27a376e15837a7abf79fca23e98
     model=model,
     train_loader=subset_loaders['train'],
     val_loader=subset_loaders['val'],
@@ -126,6 +147,7 @@ training_metrics = train_model(
     lr=training_config["learning_rate"],
     save_path=training_config["save_path"],
 )
+<<<<<<< HEAD
 
 
 # ----------- Log metrics to ClearML -----------
@@ -146,4 +168,6 @@ training_logger.report_single_value("best_val_accuracy", training_metrics["best_
 training_task.upload_artifact("best_model", training_config["save_path"])
 
 print("\nTraining complete.")
-training_task.close()
+training_task.close()
+=======
+>>>>>>> 20050ad82ebca27a376e15837a7abf79fca23e98