Merge pull request #6 from K23064919/ops/clone-models

requirements.txt

@@ -1,29 +1,19 @@
 
 # Core dependencies
-torch>=2.0.0
-torchvision>=0.15.0
-gradio>=4.0.0
-numpy>=1.24.0
-Pillow>=10.0.0
+torch==2.2.2
+torchvision==0.17.2
+torcheval==0.0.7
+numpy==1.26.4
+Pillow==10.3.0
+gradio==4.19.0
 
-# For model deployment and tracking
-huggingface-hub>=0.19.0
-clearml>=1.14.0
-
-# Optional: for advanced features
-datasets>=2.14.0  # For loading PlantVillage dataset from HuggingFace
-# -- Data prep requirements --
 # Data Handling & Analysis
-numpy
-pandas
-datasets
+pandas==2.2.2
+datasets==2.18.0
 
 # Visualization
-matplotlib
+matplotlib==3.8.4
 
-# PyTorch (Machine Learning)
-torch
-torchvision
-
-# Experiment Tracking
-clearml
+# For model deployment and tracking
+huggingface-hub==0.23.0
+clearml==2.0.2

trainingModel/run_training.py

@@ -1,18 +1,15 @@
 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
 
-# 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'")
+import torch
+from models.modelOne import modelOne
+from trainingModel.Training import train_model
 
-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")
@@ -28,12 +25,6 @@ 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"]
@@ -43,12 +34,7 @@ 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()
@@ -130,15 +116,8 @@ 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'],
@@ -147,7 +126,6 @@ train_model(
     lr=training_config["learning_rate"],
     save_path=training_config["save_path"],
 )
-<<<<<<< HEAD
 
 
 # ----------- Log metrics to ClearML -----------
@@ -168,6 +146,4 @@ 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()
-=======
->>>>>>> 20050ad82ebca27a376e15837a7abf79fca23e98
+training_task.close()