final_trained_model.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "c:\\Users\\hp\\Desktop\\car_parking_slot_occupancy_detection_using_yolov8\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "HOME = os.getcwd()\n",
    "print(HOME)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 14342,
     "status": "ok",
     "timestamp": 1686418381621,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "4iBLRGzxgzpI",
    "outputId": "be255dad-3436-4bb6-a9a3-afdc367a953e"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Ultralytics YOLOv8.0.115 🚀 Python-3.11.4 torch-2.0.1+cpu CPU\n",
      "Setup complete ✅ (8 CPUs, 15.8 GB RAM, 172.0/236.2 GB disk)\n"
     ]
    }
   ],
   "source": [
    "# Pip install method (recommended)\n",
    "\n",
    "\n",
    "!pip install ultralytics==8.0.20\n",
    "\n",
    "from IPython import display\n",
    "display.clear_output()\n",
    "\n",
    "import ultralytics\n",
    "ultralytics.checks()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "executionInfo": {
     "elapsed": 8,
     "status": "ok",
     "timestamp": 1686418381622,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "YVd9wkhmg2mT"
   },
   "outputs": [],
   "source": [
    "from ultralytics import YOLO\n",
    "\n",
    "from IPython.display import display, Image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[WinError 2] The system cannot find the file specified: 'c:\\\\Users\\\\hp\\\\Desktop\\\\car_parking_slot_occupancy_detection_using_yolov8/datasets'\n",
      "c:\\Users\\hp\\Desktop\\car_parking_slot_occupancy_detection_using_yolov8\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "The syntax of the command is incorrect.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: roboflow in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (1.0.9)\n",
      "Requirement already satisfied: certifi==2022.12.7 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (2022.12.7)\n",
      "Requirement already satisfied: chardet==4.0.0 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (4.0.0)\n",
      "Requirement already satisfied: cycler==0.10.0 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (0.10.0)\n",
      "Requirement already satisfied: idna==2.10 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (2.10)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (1.4.4)\n",
      "Requirement already satisfied: matplotlib in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (3.7.1)\n",
      "Requirement already satisfied: numpy>=1.18.5 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (1.24.3)\n",
      "Requirement already satisfied: opencv-python>=4.1.2 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (4.7.0.72)\n",
      "Requirement already satisfied: Pillow>=7.1.2 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (9.5.0)\n",
      "Requirement already satisfied: pyparsing==2.4.7 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (2.4.7)\n",
      "Requirement already satisfied: python-dateutil in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (2.8.2)\n",
      "Requirement already satisfied: python-dotenv in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (1.0.0)\n",
      "Requirement already satisfied: requests in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (2.31.0)\n",
      "Requirement already satisfied: six in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (1.16.0)\n",
      "Requirement already satisfied: urllib3>=1.26.6 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (2.0.3)\n",
      "Requirement already satisfied: wget in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (3.2)\n",
      "Requirement already satisfied: tqdm>=4.41.0 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (4.65.0)\n",
      "Requirement already satisfied: PyYAML>=5.3.1 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (6.0)\n",
      "Requirement already satisfied: requests-toolbelt in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from roboflow) (1.0.0)\n",
      "Requirement already satisfied: colorama in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from tqdm>=4.41.0->roboflow) (0.4.6)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from matplotlib->roboflow) (1.0.7)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from matplotlib->roboflow) (4.39.4)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from matplotlib->roboflow) (23.1)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\hp\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from requests->roboflow) (3.1.0)\n",
      "loading Roboflow workspace...\n",
      "loading Roboflow project...\n",
      "Dependency ultralytics<=8.0.20 is required but found version=8.0.115, to fix: `pip install ultralytics<=8.0.20`\n",
      "Downloading Dataset Version Zip in Real-time-parking-lot-vehicle-detection-1 to yolov8: 100% [153501374 / 153501374] bytes\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Extracting Dataset Version Zip to Real-time-parking-lot-vehicle-detection-1 in yolov8:: 100%|██████████| 3846/3846 [00:05<00:00, 703.91it/s]\n"
     ]
    }
   ],
   "source": [
    "\n",
    "!mkdir {HOME}/datasets\n",
    "%cd {HOME}/datasets\n",
    "\n",
    "!pip install roboflow\n",
    "\n",
    "from roboflow import Roboflow\n",
    "rf = Roboflow(api_key=\"tUZCeeGNLljUnpXXsngy\")\n",
    "project = rf.workspace(\"swastik-abhijit-patra-zlamm\").project(\"real-time-parking-lot-vehicle-detection\")\n",
    "dataset = project.version(1).download(\"yolov8\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 876968,
     "status": "ok",
     "timestamp": 1686420272757,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "4gCWQxZ7hyZU",
    "outputId": "367e7277-e909-449f-c445-f26dc3907811"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "c:\\Users\\hp\\Desktop\\car_parking_slot_occupancy_detection_using_yolov8\n",
      "^C\n"
     ]
    },
    {
     "ename": "",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31mThe Kernel crashed while executing code in the the current cell or a previous cell. Please review the code in the cell(s) to identify a possible cause of the failure. Click <a href='https://aka.ms/vscodeJupyterKernelCrash'>here</a> for more info. View Jupyter <a href='command:jupyter.viewOutput'>log</a> for further details."
     ]
    }
   ],
   "source": [
    "%cd {HOME}\n",
    "!yolo task=detect mode=train model=yolov8m.pt data=r'C:\\Users\\hp\\Desktop\\car_parking_slot_occupancy_detection_using_yolov8\\Real-time-parking-lot-vehicle-detection-1\\data.yaml' epochs=30 imgsz=640 plots=True"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 531,
     "status": "ok",
     "timestamp": 1686421077957,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "MlGr1B4emrk4",
    "outputId": "cd7cebb8-3e3c-45be-fa3f-cf625f8e8a68"
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "'ls' is not recognized as an internal or external command,\n",
      "operable program or batch file.\n"
     ]
    }
   ],
   "source": [
    "!ls {HOME}/runs/detect/train/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 485
    },
    "executionInfo": {
     "elapsed": 1231,
     "status": "ok",
     "timestamp": 1686421101901,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "XkDbtZtQmwPO",
    "outputId": "c6e850d3-d2cd-4a1d-f404-e13b74dd5d3b"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/content\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 12,
     "metadata": {
      "image/png": {
       "width": 600
      }
     },
     "output_type": "execute_result"
    }
   ],
   "source": [
    "%cd {HOME}\n",
    "Image(filename=f'/content/runs/detect/train2/confusion_matrix.png', width=600)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 33199,
     "status": "ok",
     "timestamp": 1686421209237,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "ifIldj0_mxfA",
    "outputId": "8589e86d-98f5-47f7-ef73-93eac9bfb406"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "C:\\Users\\hp\\Desktop\\smart_parking_system\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Traceback (most recent call last):\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\runpy.py\", line 197, in _run_module_as_main\n",
      "    return _run_code(code, main_globals, None,\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\runpy.py\", line 87, in _run_code\n",
      "    exec(code, run_globals)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\Scripts\\yolo.exe\\__main__.py\", line 7, in <module>\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\yolo\\cfg\\__init__.py\", line 367, in entrypoint\n",
      "    model = YOLO(model, task=task)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\yolo\\engine\\model.py\", line 107, in __init__\n",
      "    self._load(model, task)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\yolo\\engine\\model.py\", line 156, in _load\n",
      "    self.model, self.ckpt = attempt_load_one_weight(weights)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\nn\\tasks.py\", line 441, in attempt_load_one_weight\n",
      "    ckpt, weight = torch_safe_load(weight)  # load ckpt\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\nn\\tasks.py\", line 381, in torch_safe_load\n",
      "    return torch.load(file, map_location='cpu'), file  # load\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\torch\\serialization.py\", line 791, in load\n",
      "    with _open_file_like(f, 'rb') as opened_file:\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\torch\\serialization.py\", line 271, in _open_file_like\n",
      "    return _open_file(name_or_buffer, mode)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\torch\\serialization.py\", line 252, in __init__\n",
      "    super().__init__(open(name, mode))\n",
      "FileNotFoundError: [Errno 2] No such file or directory: 'C:\\\\Users\\\\hp\\\\Desktop\\\\smart_parking_system\\\\runs\\\\detect\\\\train\\\\weights\\\\best.pt'\n"
     ]
    }
   ],
   "source": [
    "%cd {HOME}\n",
    "\n",
    "!yolo task=detect mode=val model={HOME}/runs/detect/train/weights/best.pt data={dataset.location}/data.yaml"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 18130,
     "status": "ok",
     "timestamp": 1686421441669,
     "user": {
      "displayName": "Arpit Patel",
      "userId": "03496994636738147779"
     },
     "user_tz": -330
    },
    "id": "ZddCp1S8nv_T",
    "outputId": "3deb3b48-eb78-45dd-db08-ab79c33dac3f"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "C:\\Users\\hp\\Desktop\\smart_parking_system\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Traceback (most recent call last):\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\runpy.py\", line 197, in _run_module_as_main\n",
      "    return _run_code(code, main_globals, None,\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\runpy.py\", line 87, in _run_code\n",
      "    exec(code, run_globals)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\Scripts\\yolo.exe\\__main__.py\", line 7, in <module>\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\yolo\\cfg\\__init__.py\", line 367, in entrypoint\n",
      "    model = YOLO(model, task=task)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\yolo\\engine\\model.py\", line 107, in __init__\n",
      "    self._load(model, task)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\yolo\\engine\\model.py\", line 156, in _load\n",
      "    self.model, self.ckpt = attempt_load_one_weight(weights)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\nn\\tasks.py\", line 441, in attempt_load_one_weight\n",
      "    ckpt, weight = torch_safe_load(weight)  # load ckpt\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\ultralytics\\nn\\tasks.py\", line 381, in torch_safe_load\n",
      "    return torch.load(file, map_location='cpu'), file  # load\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\torch\\serialization.py\", line 791, in load\n",
      "    with _open_file_like(f, 'rb') as opened_file:\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\torch\\serialization.py\", line 271, in _open_file_like\n",
      "    return _open_file(name_or_buffer, mode)\n",
      "  File \"C:\\Users\\hp\\anaconda3\\lib\\site-packages\\torch\\serialization.py\", line 252, in __init__\n",
      "    super().__init__(open(name, mode))\n",
      "FileNotFoundError: [Errno 2] No such file or directory: 'C:\\\\Users\\\\hp\\\\Desktop\\\\smart_parking_system\\\\runs\\\\detect\\\\train\\\\weights\\\\best.pt'\n"
     ]
    }
   ],
   "source": [
    "%cd {HOME}\n",
    "!yolo task=detect mode=predict model={HOME}/runs/detect/train/weights/best.pt conf=0.25 source=/content/drive/MyDrive/smart_parking_system/parking1.mp4 save=True"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "authorship_tag": "ABX9TyOCiLn7Vpw19gdC06a/Gv05",
   "gpuType": "T4",
   "mount_file_id": "1-ljJgBw6CLoHb0CvcwmYX7DLf-3fDZ5S",
   "provenance": []
  },
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}