Adding new information

notebooks/training_visualization.ipynb

@@ -10,9 +10,22 @@
         },
         {
             "cell_type": "code",
-            "execution_count": null,
+            "execution_count": 1,
             "metadata": {},
-            "outputs": [],
+            "outputs": [
+                {
+                    "ename": "FileNotFoundError",
+                    "evalue": "[Errno 2] No such file or directory: 'config.yaml'",
+                    "output_type": "error",
+                    "traceback": [
+                        "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+                        "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
+                        "Cell \u001b[0;32mIn[1], line 5\u001b[0m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01mjson\u001b[39;00m\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21;01myaml\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28;43mopen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mconfig.yaml\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mr\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;28;01mas\u001b[39;00m f: \n\u001b[1;32m      6\u001b[0m     config \u001b[38;5;241m=\u001b[39m yaml\u001b[38;5;241m.\u001b[39msafe_load(f)\n\u001b[1;32m      8\u001b[0m \u001b[38;5;66;03m# Load training log file\u001b[39;00m\n",
+                        "File \u001b[0;32m~/studies/northEastern/Computer Vision/Assigments/objectlocalization/venv/lib/python3.12/site-packages/IPython/core/interactiveshell.py:324\u001b[0m, in \u001b[0;36m_modified_open\u001b[0;34m(file, *args, **kwargs)\u001b[0m\n\u001b[1;32m    317\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m file \u001b[38;5;129;01min\u001b[39;00m {\u001b[38;5;241m0\u001b[39m, \u001b[38;5;241m1\u001b[39m, \u001b[38;5;241m2\u001b[39m}:\n\u001b[1;32m    318\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    319\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIPython won\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt let you open fd=\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mfile\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m by default \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    320\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mas it is likely to crash IPython. If you know what you are doing, \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    321\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124myou can use builtins\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m open.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    322\u001b[0m     )\n\u001b[0;32m--> 324\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mio_open\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfile\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
+                        "\u001b[0;31mFileNotFoundError\u001b[0m: [Errno 2] No such file or directory: 'config.yaml'"
+                    ]
+                }
+            ],
             "source": [
                 "import matplotlib.pyplot as plt\n",
                 "import json\n",
@@ -67,7 +80,7 @@
             "name": "python",
             "nbconvert_exporter": "python",
             "pygments_lexer": "ipython3",
-            "version": "3.8"
+            "version": "3.12.2"
         }
     },
     "nbformat": 4,

src/traina.py

@@ -1,100 +0,0 @@
-import os
-import torch
-import torchvision
-import json
-import yaml
-from tqdm import tqdm
-from torch.utils.data import DataLoader, random_split
-from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
-from torchvision.transforms import functional as F
-from src.dataset import LegoDataset
-from src.evaluate import calculate_map
-
-# Load Configuration
-with open("config.yaml", "r") as f:
-    config = yaml.safe_load(f)
-
-# Load Pretrained Model
-model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights="DEFAULT")
-
-# Freeze Backbone
-for param in model.backbone.parameters():
-    param.requires_grad = False
-
-# Modify Predictor
-num_classes = config["model"]["num_classes"]
-in_features = model.roi_heads.box_predictor.cls_score.in_features
-model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes)
-
-# Training Setup
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
-
-optimizer = torch.optim.Adam(model.parameters(), lr=config["model"]["learning_rate"])
-
-# Load Dataset
-image_dir = config["dataset"]["image_dir"]
-annotation_dir = config["dataset"]["annotation_dir"]
-dataset = LegoDataset(image_dir, annotation_dir)
-train_size = int(config["dataset"]["train_split"] * len(dataset))
-val_size = len(dataset) - train_size
-train_dataset, val_dataset = random_split(dataset, [train_size, val_size])
-train_loader = DataLoader(train_dataset, batch_size=config["model"]["batch_size"], shuffle=True, collate_fn=lambda x: tuple(zip(*x)))
-val_loader = DataLoader(val_dataset, batch_size=config["model"]["batch_size"], shuffle=False, collate_fn=lambda x: tuple(zip(*x)))
-
-# Logging Function (Writes logs efficiently to file)
-log_file = "models/training_log.txt"
-def log_message(message):
-    with open(log_file, "a") as f:
-        f.write(message + "\n")
-
-# Training Function with tqdm progress bar
-def train_one_epoch(model, optimizer, data_loader, device):
-    model.train()
-    running_loss = 0.0
-
-    for batch_idx, (images, targets) in enumerate(tqdm(data_loader, desc="Training Progress")):
-        images = [F.to_tensor(img).to(device) for img in images]
-        targets = [{k: v.to(device) for k, v in t.items()} for t in targets]
-
-        loss_dict = model(images, targets)
-        loss = sum(loss for loss in loss_dict.values())
-
-        optimizer.zero_grad()
-        loss.backward()
-        optimizer.step()
-
-        running_loss += loss.item()
-
-    return running_loss / len(data_loader)
-
-# Train Model with Logging
-num_epochs = config["model"]["epochs"]
-os.makedirs("models", exist_ok=True)  # Ensure model directory exists
-
-for epoch in range(num_epochs):
-    log_message(f"Starting Epoch {epoch+1}/{num_epochs}")
-    loss = train_one_epoch(model, optimizer, train_loader, device)
-    log_message(f"Epoch [{epoch+1}/{num_epochs}], Loss: {loss:.4f}")
-
-    # Evaluate mAP after each epoch
-    mAP = calculate_map(model, val_loader, device)
-    log_message(f"Validation mAP: {mAP:.4f}")
-
-    # Save log in JSON for visualization
-    log_json = "models/training_log.json"
-    if not os.path.exists(log_json):
-        log_data = {"loss": [], "mAP": []}
-    else:
-        with open(log_json, "r") as f:
-            log_data = json.load(f)
-
-    log_data["loss"].append(loss)
-    log_data["mAP"].append(mAP)
-
-    with open(log_json, "w") as f:
-        json.dump(log_data, f, indent=4)
-
-# Save the trained model
-torch.save(model.state_dict(), "models/lego_fasterrcnn.pth")
-log_message("Model saved as models/lego_fasterrcnn.pth")