more epochs

.ipynb_checkpoints/train-checkpoint.ipynb

@@ -0,0 +1,296 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6a013a36-e156-4212-8ade-5fee79e33680",
+   "metadata": {},
+   "source": [
+    "Install dependencies"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "acabbaee-35be-452b-8573-4d0974fa6340",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install torch torchvision torchaudio\n",
+    "!pip3 install matplotlib\n",
+    "!pip3 install ultralytics roboflow"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fb8218b5-61c9-4fe3-b5c6-1643beb39e28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "from ultralytics import YOLO\n",
+    "from pathlib import Path\n",
+    "import os\n",
+    "import json\n",
+    "import yaml\n",
+    "import pandas as pd\n",
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.image as mpimg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4bccbb25",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
+    "\n",
+    "print(f\"Using device: {device} ({'GPU' if device != 'cpu' else 'CPU'})\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "CONFIG = {\n",
+    "    'model': 'yolo11m.pt',  # Choose model size: n, s, m, l, x\n",
+    "    'data': 'datasets/Hardhat-or-Hat.v1-without-hat.yolov11/data.yaml',  \n",
+    "    'epochs': 35,\n",
+    "    'batch': 2 if device != 'cpu' else 4,  # Adjust batch \n",
+    "    'imgsz': 640,\n",
+    "    'patience': 5,\n",
+    "    'device': device, \n",
+    "}\n",
+    "os.environ[\"PYTORCH_CUDA_ALLOC_CONF\"] = \"expandable_segments:True\"\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d349b982",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "save_dir = Path('runs/detect')\n",
+    "save_dir.mkdir(parents=True, exist_ok=True)\n",
+    "\n",
+    "this_path = os.getcwd()\n",
+    "\n",
+    "os.environ['ULTRALYTICS_CONFIG_DIR'] = this_path\n",
+    "\n",
+    "data_file = f'{this_path}/{CONFIG['data']}'\n",
+    "with open(data_file, 'r') as f:\n",
+    "    data = yaml.safe_load(f)\n",
+    "    \n",
+    "\n",
+    "data['train'] = f'{this_path}/{CONFIG['data'].rsplit('/', 1)[0]}/train/images'\n",
+    "data['val'] = f'{this_path}/{CONFIG['data'].rsplit('/', 1)[0]}/valid/images'\n",
+    "data['test'] = f'{this_path}/{CONFIG['data'].rsplit('/', 1)[0]}/test/images'\n",
+    "\n",
+    "with open(data_file, 'w') as f:\n",
+    "    yaml.safe_dump(data, f)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f831042",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "model = YOLO(CONFIG['model'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "20208cb5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "results = model.train(\n",
+    "    data=CONFIG['data'],\n",
+    "    epochs=CONFIG['epochs'],\n",
+    "    batch=CONFIG['batch'],\n",
+    "    imgsz=CONFIG['imgsz'],\n",
+    "    patience=CONFIG['patience'],\n",
+    "    device=CONFIG['device'],\n",
+    "    \n",
+    "    verbose=True,\n",
+    "    \n",
+    "    optimizer='SGD',\n",
+    "    lr0=0.001,\n",
+    "    lrf=0.01,\n",
+    "    momentum=0.9,\n",
+    "    weight_decay=0.0005,\n",
+    "    warmup_epochs=3,\n",
+    "    warmup_bias_lr=0.01,\n",
+    "    warmup_momentum=0.8,\n",
+    "    amp=False,\n",
+    "    \n",
+    "    # Augmentations\n",
+    "    augment=True,\n",
+    "    hsv_h=0.015,  # Image HSV-Hue augmentationc\n",
+    "    hsv_s=0.7,   # Image HSV-Saturation augmentation\n",
+    "    hsv_v=0.4,   # Image HSV-Value augmentation\n",
+    "    degrees=10,  # Image rotation (+/- deg)\n",
+    "    translate=0.1,  # Image translation (+/- fraction)\n",
+    "    scale=0.3,   # Image scale (+/- gain)\n",
+    "    shear=0.0,   # Image shear (+/- deg)\n",
+    "    perspective=0.0,  # Image perspective\n",
+    "    flipud=0.1,  # Image flip up-down\n",
+    "    fliplr=0.1,  # Image flip left-right\n",
+    "    mosaic=1.0,  # Image mosaic\n",
+    "    mixup=0.0,   # Image mixup\n",
+    "    \n",
+    ")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "06211243",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "file_path = f\"{str(results.save_dir)}\"  \n",
+    "results_csv_path = f\"{file_path}/results.csv\"  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e67532ea",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "try:\n",
+    "    result_metrics = pd.read_csv(results_csv_path)\n",
+    "except FileNotFoundError:\n",
+    "    print(f\"File not found: {results_csv_path}\")\n",
+    "    exit()\n",
+    "\n",
+    "\n",
+    "metrics = {\n",
+    "    \"Train Box Loss\": \"train/box_loss\",\n",
+    "    \"Train Class Loss\": \"train/cls_loss\",\n",
+    "    \"Train DFL Loss\": \"train/dfl_loss\",\n",
+    "    \"Validation Box Loss\": \"val/box_loss\",\n",
+    "    \"Validation Class Loss\": \"val/cls_loss\",\n",
+    "    \"Validation DFL Loss\": \"val/dfl_loss\",\n",
+    "    \"Precision (B)\": \"metrics/precision(B)\",\n",
+    "    \"Recall (B)\": \"metrics/recall(B)\",\n",
+    "    \"[email protected] (B)\": \"metrics/mAP50(B)\",\n",
+    "    \"[email protected]:0.95 (B)\": \"metrics/mAP50-95(B)\",\n",
+    "}\n",
+    "\n",
+    "%matplotlib inline\n",
+    "\n",
+    "available_metrics = {name: col for name, col in metrics.items() if col in result_metrics.columns}\n",
+    "missing_metrics = [name for name in metrics if name not in available_metrics]\n",
+    "\n",
+    "if missing_metrics:\n",
+    "    print(f\"Missing metrics: {', '.join(missing_metrics)}\")\n",
+    "else:\n",
+    "    print(\"All expected metrics are present.\")\n",
+    "\n",
+    "for metric_name, col in available_metrics.items():\n",
+    "    plt.figure()\n",
+    "    plt.plot(result_metrics[\"epoch\"], result_metrics[col], label=metric_name)\n",
+    "    plt.title(metric_name)\n",
+    "    plt.xlabel(\"Epoch\")\n",
+    "    plt.ylabel(metric_name)\n",
+    "    plt.legend()\n",
+    "    plt.grid()\n",
+    "    plt.show()\n",
+    "\n",
+    "final_epoch = result_metrics.iloc[-1]\n",
+    "final_metrics = {name: final_epoch[col] for name, col in available_metrics.items()}\n",
+    "\n",
+    "print(\"\\nFinal Metrics Summary (Last Epoch):\")\n",
+    "for name, value in final_metrics.items():\n",
+    "    print(f\"{name}: {value:.4f}\")\n",
+    "\n",
+    "print(\"\\nImprovement Trends:\")\n",
+    "for metric_name, col in available_metrics.items():\n",
+    "    initial = result_metrics[col].iloc[0]\n",
+    "    final = result_metrics[col].iloc[-1]\n",
+    "    trend = \"improved\" if final < initial else \"worsened\"\n",
+    "    print(f\"{metric_name}: {trend} (Initial: {initial:.4f}, Final: {final:.4f})\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cd2fb43f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\n",
+    "\n",
+    "img = mpimg.imread(f\"{file_path}/confusion_matrix_normalized.png\") \n",
+    "plt.imshow(img)\n",
+    "plt.axis('off') \n",
+    "plt.show()\n",
+    "\n",
+    "img = mpimg.imread(f\"{file_path}/F1_curve.png\") \n",
+    "plt.imshow(img)\n",
+    "plt.axis('off') \n",
+    "plt.show()\n",
+    "\n",
+    "img = mpimg.imread(f\"{file_path}/P_curve.png\") \n",
+    "plt.imshow(img)\n",
+    "plt.axis('off') \n",
+    "plt.show()\n",
+    "\n",
+    "img = mpimg.imread(f\"{file_path}/R_curve.png\") \n",
+    "plt.imshow(img)\n",
+    "plt.axis('off') \n",
+    "plt.show()\n",
+    "\n",
+    "img = mpimg.imread(f\"{file_path}/PR_curve.png\") \n",
+    "plt.imshow(img)\n",
+    "plt.axis('off') \n",
+    "plt.show()\n",
+    "\n",
+    "img = mpimg.imread(f\"{file_path}/results.png\") \n",
+    "plt.imshow(img)\n",
+    "plt.axis('off') \n",
+    "plt.show()\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}