{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "dc7ab4859abf4fdaa598729ec421129a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_5441781ef8f046dd979a8c389a8e7587",
              "IPY_MODEL_999c37c9cce448a792df58915545135f",
              "IPY_MODEL_db66afed001a4324bdd44f51efeaafa1"
            ],
            "layout": "IPY_MODEL_11cb47a0455044af83969ae1994af22f"
          }
        },
        "5441781ef8f046dd979a8c389a8e7587": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f884e42910e14b5aa9dc9919558cf75f",
            "placeholder": "​",
            "style": "IPY_MODEL_53cc94f964d54d71923bc295d2882216",
            "value": "config.json: 100%"
          }
        },
        "999c37c9cce448a792df58915545135f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_b0a3d7e1d2ea4e3bb7e3264c8089b26d",
            "max": 71813,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_279f9349c7334713bb760bbc4bff3d3c",
            "value": 71813
          }
        },
        "db66afed001a4324bdd44f51efeaafa1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_865cd86f5627433e9d92c1de46917f08",
            "placeholder": "​",
            "style": "IPY_MODEL_73db46b258794cfe922424d06689e44e",
            "value": " 71.8k/71.8k [00:00<00:00, 3.22MB/s]"
          }
        },
        "11cb47a0455044af83969ae1994af22f": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f884e42910e14b5aa9dc9919558cf75f": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "53cc94f964d54d71923bc295d2882216": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "b0a3d7e1d2ea4e3bb7e3264c8089b26d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "279f9349c7334713bb760bbc4bff3d3c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "865cd86f5627433e9d92c1de46917f08": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "73db46b258794cfe922424d06689e44e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "cd77cd0c2d1741c39b9ca6f36ec562c3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_4f28a143f3cd438b87a74a62d9c5bea4",
              "IPY_MODEL_256dc2937cb2449f84ec14b9dae2e51f",
              "IPY_MODEL_a60bc29c8c1044f690a6cd4f74ed7c2c"
            ],
            "layout": "IPY_MODEL_a33d503834a741a9a23a26c03c1c3aaf"
          }
        },
        "4f28a143f3cd438b87a74a62d9c5bea4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_a2f0b441f346498faabf97d5d8eabd3a",
            "placeholder": "​",
            "style": "IPY_MODEL_3243191638d14067a1565ae2f03f48de",
            "value": "model.safetensors: 100%"
          }
        },
        "256dc2937cb2449f84ec14b9dae2e51f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f0b74718119e4f3a9bb6295bc7567f6d",
            "max": 113412768,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_fd6d8576cbc444e1b22111ddf4fa1dc2",
            "value": 113412768
          }
        },
        "a60bc29c8c1044f690a6cd4f74ed7c2c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c469ed61c6b946b78bb0308f36cb915b",
            "placeholder": "​",
            "style": "IPY_MODEL_e0db11f2d42744e982e2206a1640344a",
            "value": " 113M/113M [00:01<00:00, 130MB/s]"
          }
        },
        "a33d503834a741a9a23a26c03c1c3aaf": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "a2f0b441f346498faabf97d5d8eabd3a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3243191638d14067a1565ae2f03f48de": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "f0b74718119e4f3a9bb6295bc7567f6d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fd6d8576cbc444e1b22111ddf4fa1dc2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "c469ed61c6b946b78bb0308f36cb915b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e0db11f2d42744e982e2206a1640344a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "## using pre-trained swin transformer to train the model"
      ],
      "metadata": {
        "id": "kuFuGmlMnSSF"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "from torchvision import datasets, transforms\n",
        "from torch.utils.data import DataLoader\n",
        "\n",
        "# Define transformation pipeline\n",
        "transform = transforms.Compose([\n",
        "    transforms.Resize((224, 224)),  # Resize to 224x224 for Swin Transformer\n",
        "    transforms.ToTensor(),\n",
        "])\n",
        "\n",
        "# Load dataset\n",
        "train_dataset = datasets.ImageFolder(root='/content/drive/MyDrive/data/brain_tumor_dataset/train', transform=transform)\n",
        "val_dataset = datasets.ImageFolder(root='/content/drive/MyDrive/data/brain_tumor_dataset/test', transform=transform)\n",
        "\n",
        "# Create dataloaders\n",
        "train_loader = DataLoader(train_dataset, batch_size=32, shuffle=True)\n",
        "val_loader = DataLoader(val_dataset, batch_size=32, shuffle=False)\n"
      ],
      "metadata": {
        "id": "dacVmRJWSB-7"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from transformers import SwinForImageClassification\n",
        "\n",
        "# Load the pre-trained Swin Transformer model with 4 output classes\n",
        "model = SwinForImageClassification.from_pretrained(\n",
        "    'microsoft/swin-tiny-patch4-window7-224',\n",
        "    num_labels=2,  # Number of tumor types\n",
        "    ignore_mismatched_sizes=True  # Ignore size mismatch for the classifier layer\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170,
          "referenced_widgets": [
            "dc7ab4859abf4fdaa598729ec421129a",
            "5441781ef8f046dd979a8c389a8e7587",
            "999c37c9cce448a792df58915545135f",
            "db66afed001a4324bdd44f51efeaafa1",
            "11cb47a0455044af83969ae1994af22f",
            "f884e42910e14b5aa9dc9919558cf75f",
            "53cc94f964d54d71923bc295d2882216",
            "b0a3d7e1d2ea4e3bb7e3264c8089b26d",
            "279f9349c7334713bb760bbc4bff3d3c",
            "865cd86f5627433e9d92c1de46917f08",
            "73db46b258794cfe922424d06689e44e",
            "cd77cd0c2d1741c39b9ca6f36ec562c3",
            "4f28a143f3cd438b87a74a62d9c5bea4",
            "256dc2937cb2449f84ec14b9dae2e51f",
            "a60bc29c8c1044f690a6cd4f74ed7c2c",
            "a33d503834a741a9a23a26c03c1c3aaf",
            "a2f0b441f346498faabf97d5d8eabd3a",
            "3243191638d14067a1565ae2f03f48de",
            "f0b74718119e4f3a9bb6295bc7567f6d",
            "fd6d8576cbc444e1b22111ddf4fa1dc2",
            "c469ed61c6b946b78bb0308f36cb915b",
            "e0db11f2d42744e982e2206a1640344a"
          ]
        },
        "id": "WQb3MZ2oSTLr",
        "outputId": "f159d174-0444-44de-dfe0-b77a20694146"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "config.json:   0%|          | 0.00/71.8k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "dc7ab4859abf4fdaa598729ec421129a"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "model.safetensors:   0%|          | 0.00/113M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "cd77cd0c2d1741c39b9ca6f36ec562c3"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of SwinForImageClassification were not initialized from the model checkpoint at microsoft/swin-tiny-patch4-window7-224 and are newly initialized because the shapes did not match:\n",
            "- classifier.bias: found shape torch.Size([1000]) in the checkpoint and torch.Size([2]) in the model instantiated\n",
            "- classifier.weight: found shape torch.Size([1000, 768]) in the checkpoint and torch.Size([2, 768]) in the model instantiated\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Freeze all layers except the final classification head\n",
        "for param in model.parameters():\n",
        "    param.requires_grad = False\n",
        "\n",
        "# Unfreeze the classification layer\n",
        "for param in model.classifier.parameters():\n",
        "    param.requires_grad = True\n"
      ],
      "metadata": {
        "id": "_oCiVhFbSbBQ"
      },
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import torch.optim as optim\n",
        "from torch.optim.lr_scheduler import StepLR\n",
        "import torch.nn as nn\n",
        "\n",
        "# Set up optimizer and loss function\n",
        "optimizer = optim.Adam(model.parameters(), lr=1e-4)\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "\n",
        "# Move model to GPU if available\n",
        "device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n",
        "model.to(device)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sfu4me_OTSJx",
        "outputId": "55f7ff18-72c3-45b2-a97c-587b81c122b5"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "SwinForImageClassification(\n",
              "  (swin): SwinModel(\n",
              "    (embeddings): SwinEmbeddings(\n",
              "      (patch_embeddings): SwinPatchEmbeddings(\n",
              "        (projection): Conv2d(3, 96, kernel_size=(4, 4), stride=(4, 4))\n",
              "      )\n",
              "      (norm): LayerNorm((96,), eps=1e-05, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.0, inplace=False)\n",
              "    )\n",
              "    (encoder): SwinEncoder(\n",
              "      (layers): ModuleList(\n",
              "        (0): SwinStage(\n",
              "          (blocks): ModuleList(\n",
              "            (0-1): 2 x SwinLayer(\n",
              "              (layernorm_before): LayerNorm((96,), eps=1e-05, elementwise_affine=True)\n",
              "              (attention): SwinAttention(\n",
              "                (self): SwinSelfAttention(\n",
              "                  (query): Linear(in_features=96, out_features=96, bias=True)\n",
              "                  (key): Linear(in_features=96, out_features=96, bias=True)\n",
              "                  (value): Linear(in_features=96, out_features=96, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "                (output): SwinSelfOutput(\n",
              "                  (dense): Linear(in_features=96, out_features=96, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "              )\n",
              "              (drop_path): SwinDropPath(p=0.1)\n",
              "              (layernorm_after): LayerNorm((96,), eps=1e-05, elementwise_affine=True)\n",
              "              (intermediate): SwinIntermediate(\n",
              "                (dense): Linear(in_features=96, out_features=384, bias=True)\n",
              "                (intermediate_act_fn): GELUActivation()\n",
              "              )\n",
              "              (output): SwinOutput(\n",
              "                (dense): Linear(in_features=384, out_features=96, bias=True)\n",
              "                (dropout): Dropout(p=0.0, inplace=False)\n",
              "              )\n",
              "            )\n",
              "          )\n",
              "          (downsample): SwinPatchMerging(\n",
              "            (reduction): Linear(in_features=384, out_features=192, bias=False)\n",
              "            (norm): LayerNorm((384,), eps=1e-05, elementwise_affine=True)\n",
              "          )\n",
              "        )\n",
              "        (1): SwinStage(\n",
              "          (blocks): ModuleList(\n",
              "            (0-1): 2 x SwinLayer(\n",
              "              (layernorm_before): LayerNorm((192,), eps=1e-05, elementwise_affine=True)\n",
              "              (attention): SwinAttention(\n",
              "                (self): SwinSelfAttention(\n",
              "                  (query): Linear(in_features=192, out_features=192, bias=True)\n",
              "                  (key): Linear(in_features=192, out_features=192, bias=True)\n",
              "                  (value): Linear(in_features=192, out_features=192, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "                (output): SwinSelfOutput(\n",
              "                  (dense): Linear(in_features=192, out_features=192, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "              )\n",
              "              (drop_path): SwinDropPath(p=0.1)\n",
              "              (layernorm_after): LayerNorm((192,), eps=1e-05, elementwise_affine=True)\n",
              "              (intermediate): SwinIntermediate(\n",
              "                (dense): Linear(in_features=192, out_features=768, bias=True)\n",
              "                (intermediate_act_fn): GELUActivation()\n",
              "              )\n",
              "              (output): SwinOutput(\n",
              "                (dense): Linear(in_features=768, out_features=192, bias=True)\n",
              "                (dropout): Dropout(p=0.0, inplace=False)\n",
              "              )\n",
              "            )\n",
              "          )\n",
              "          (downsample): SwinPatchMerging(\n",
              "            (reduction): Linear(in_features=768, out_features=384, bias=False)\n",
              "            (norm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "          )\n",
              "        )\n",
              "        (2): SwinStage(\n",
              "          (blocks): ModuleList(\n",
              "            (0-5): 6 x SwinLayer(\n",
              "              (layernorm_before): LayerNorm((384,), eps=1e-05, elementwise_affine=True)\n",
              "              (attention): SwinAttention(\n",
              "                (self): SwinSelfAttention(\n",
              "                  (query): Linear(in_features=384, out_features=384, bias=True)\n",
              "                  (key): Linear(in_features=384, out_features=384, bias=True)\n",
              "                  (value): Linear(in_features=384, out_features=384, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "                (output): SwinSelfOutput(\n",
              "                  (dense): Linear(in_features=384, out_features=384, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "              )\n",
              "              (drop_path): SwinDropPath(p=0.1)\n",
              "              (layernorm_after): LayerNorm((384,), eps=1e-05, elementwise_affine=True)\n",
              "              (intermediate): SwinIntermediate(\n",
              "                (dense): Linear(in_features=384, out_features=1536, bias=True)\n",
              "                (intermediate_act_fn): GELUActivation()\n",
              "              )\n",
              "              (output): SwinOutput(\n",
              "                (dense): Linear(in_features=1536, out_features=384, bias=True)\n",
              "                (dropout): Dropout(p=0.0, inplace=False)\n",
              "              )\n",
              "            )\n",
              "          )\n",
              "          (downsample): SwinPatchMerging(\n",
              "            (reduction): Linear(in_features=1536, out_features=768, bias=False)\n",
              "            (norm): LayerNorm((1536,), eps=1e-05, elementwise_affine=True)\n",
              "          )\n",
              "        )\n",
              "        (3): SwinStage(\n",
              "          (blocks): ModuleList(\n",
              "            (0-1): 2 x SwinLayer(\n",
              "              (layernorm_before): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (attention): SwinAttention(\n",
              "                (self): SwinSelfAttention(\n",
              "                  (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "                  (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "                  (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "                (output): SwinSelfOutput(\n",
              "                  (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "                  (dropout): Dropout(p=0.0, inplace=False)\n",
              "                )\n",
              "              )\n",
              "              (drop_path): SwinDropPath(p=0.1)\n",
              "              (layernorm_after): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (intermediate): SwinIntermediate(\n",
              "                (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "                (intermediate_act_fn): GELUActivation()\n",
              "              )\n",
              "              (output): SwinOutput(\n",
              "                (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "                (dropout): Dropout(p=0.0, inplace=False)\n",
              "              )\n",
              "            )\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "    (layernorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "    (pooler): AdaptiveAvgPool1d(output_size=1)\n",
              "  )\n",
              "  (classifier): Linear(in_features=768, out_features=2, bias=True)\n",
              ")"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Training loop\n",
        "for epoch in range(10):  # Train for 10 epochs (adjust as needed)\n",
        "    model.train()\n",
        "    running_loss = 0.0\n",
        "    correct = 0\n",
        "    total = 0\n",
        "\n",
        "    for inputs, labels in train_loader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "\n",
        "        # Zero the parameter gradients\n",
        "        optimizer.zero_grad()\n",
        "\n",
        "        # Forward pass\n",
        "        outputs = model(inputs).logits\n",
        "        loss = criterion(outputs, labels)\n",
        "\n",
        "        # Backward pass and optimization\n",
        "        loss.backward()\n",
        "        optimizer.step()\n",
        "\n",
        "        # Calculate accuracy\n",
        "        _, predicted = torch.max(outputs, 1)\n",
        "        total += labels.size(0)\n",
        "        correct += (predicted == labels).sum().item()\n",
        "        running_loss += loss.item()\n",
        "\n",
        "    # Print training stats\n",
        "    print(f'Epoch [{epoch+1}/10], Loss: {running_loss/len(train_loader)}, Accuracy: {100 * correct / total}%')\n",
        "\n",
        "    # Validation\n",
        "    model.eval()\n",
        "    val_correct = 0\n",
        "    val_total = 0\n",
        "    with torch.no_grad():\n",
        "        for inputs, labels in val_loader:\n",
        "            inputs, labels = inputs.to(device), labels.to(device)\n",
        "            outputs = model(inputs).logits\n",
        "            _, predicted = torch.max(outputs, 1)\n",
        "            val_total += labels.size(0)\n",
        "            val_correct += (predicted == labels).sum().item()\n",
        "\n",
        "    print(f'Validation Accuracy: {100 * val_correct / val_total}%')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2Q3sxrxtTXzX",
        "outputId": "c5a6b813-c5a4-43b8-cad5-48a146034ece"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch [1/10], Loss: 0.6803878396749496, Accuracy: 58.13692480359147%\n",
            "Validation Accuracy: 59.060402684563755%\n",
            "Epoch [2/10], Loss: 0.6379124437059674, Accuracy: 72.61503928170595%\n",
            "Validation Accuracy: 69.12751677852349%\n",
            "Epoch [3/10], Loss: 0.6045689774411065, Accuracy: 77.32884399551067%\n",
            "Validation Accuracy: 74.49664429530202%\n",
            "Epoch [4/10], Loss: 0.5734582436936242, Accuracy: 79.12457912457913%\n",
            "Validation Accuracy: 78.52348993288591%\n",
            "Epoch [5/10], Loss: 0.5508207274334771, Accuracy: 80.13468013468014%\n",
            "Validation Accuracy: 80.53691275167785%\n",
            "Epoch [6/10], Loss: 0.5296014377049038, Accuracy: 80.69584736251403%\n",
            "Validation Accuracy: 78.52348993288591%\n",
            "Epoch [7/10], Loss: 0.5103116855025291, Accuracy: 82.37934904601572%\n",
            "Validation Accuracy: 79.86577181208054%\n",
            "Epoch [8/10], Loss: 0.48474655938999994, Accuracy: 83.72615039281706%\n",
            "Validation Accuracy: 77.85234899328859%\n",
            "Epoch [9/10], Loss: 0.48020742727177484, Accuracy: 83.16498316498317%\n",
            "Validation Accuracy: 79.19463087248322%\n",
            "Epoch [10/10], Loss: 0.458157547882625, Accuracy: 84.51178451178451%\n",
            "Validation Accuracy: 79.86577181208054%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Test the model\n",
        "model.eval()\n",
        "test_correct = 0\n",
        "test_total = 0\n",
        "\n",
        "with torch.no_grad():\n",
        "    for inputs, labels in val_loader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        outputs = model(inputs).logits\n",
        "        _, predicted = torch.max(outputs, 1)\n",
        "        test_total += labels.size(0)\n",
        "        test_correct += (predicted == labels).sum().item()\n",
        "\n",
        "print(f'Test Accuracy: {100 * test_correct / test_total}%')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "la_3QpX9TfiP",
        "outputId": "3a1f21ca-81a9-4cd8-9d66-ec899d4e0dea"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Accuracy: 79.86577181208054%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "torch.save(model.state_dict(), 'swin_brain_tumor_classifier.pth')"
      ],
      "metadata": {
        "id": "RYS7IhD2T1-a"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from PIL import Image"
      ],
      "metadata": {
        "id": "f-mJ9OWQUYdB"
      },
      "execution_count": 8,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Load the saved model\n",
        "model.load_state_dict(torch.load('swin_brain_tumor_classifier.pth'))\n",
        "model.eval()\n",
        "\n",
        "# Make predictions on new data\n",
        "img = Image.open('/content/drive/MyDrive/data/brain_tumor_dataset/test/healthy/0566.jpg')\n",
        "img = transform(img).unsqueeze(0).to(device)\n",
        "\n",
        "# Predict\n",
        "output = model(img).logits\n",
        "_, predicted = torch.max(output, 1)\n",
        "print(f'Predicted class: {predicted.item()}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Eq0_X__wT3RV",
        "outputId": "6bdfa0ef-cba7-448b-8a5f-ef46f93b8677"
      },
      "execution_count": 20,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-20-c22c92cd5d87>:2: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature.\n",
            "  model.load_state_dict(torch.load('swin_brain_tumor_classifier.pth'))\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Predicted class: 0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#healthy tumor\n",
        "path = '/content/drive/MyDrive/data/brain_tumor_dataset/test/healthy'\n"
      ],
      "metadata": {
        "id": "gzK2C_4-k8F1"
      },
      "execution_count": 21,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "import os"
      ],
      "metadata": {
        "id": "6EDJd38AxZFv"
      },
      "execution_count": 22,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "files = os.listdir(path)\n",
        "\n",
        "for f in files:\n",
        "  try:\n",
        "    img = Image.open(os.path.join(path,f))\n",
        "    img = transform(img).unsqueeze(0).to(device)\n",
        "    output = model(img).logits\n",
        "    _, predicted = torch.max(output, 1)\n",
        "    print(f'predicted class: {predicted.item()} filename: {f} actual class: 0')\n",
        "  except Exception as e:\n",
        "    print(e)\n",
        "    continue"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1jTDGblkxdAn",
        "outputId": "5610b6fc-ac47-4a6b-9314-f5398ea2787d"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "predicted class: 0 filename: 0796.jpg actual class: 0\n",
            "predicted class: 0 filename: 0676.jpg actual class: 0\n",
            "predicted class: 1 filename: 0698.jpg actual class: 0\n",
            "predicted class: 1 filename: 0601.jpg actual class: 0\n",
            "predicted class: 0 filename: 0861.jpg actual class: 0\n",
            "predicted class: 1 filename: 0615.jpg actual class: 0\n",
            "predicted class: 0 filename: 0874.jpg actual class: 0\n",
            "predicted class: 0 filename: 0820.jpg actual class: 0\n",
            "predicted class: 0 filename: 0785.jpg actual class: 0\n",
            "predicted class: 0 filename: 0792.jpg actual class: 0\n",
            "predicted class: 0 filename: 0731.jpg actual class: 0\n",
            "predicted class: 0 filename: 0762.jpg actual class: 0\n",
            "predicted class: 1 filename: 0710.jpg actual class: 0\n",
            "predicted class: 0 filename: 0858.jpg actual class: 0\n",
            "predicted class: 0 filename: 0691.jpg actual class: 0\n",
            "predicted class: 0 filename: 0791.jpg actual class: 0\n",
            "predicted class: 1 filename: 0639.jpg actual class: 0\n",
            "predicted class: 1 filename: 0596.jpg actual class: 0\n",
            "predicted class: 1 filename: 0591.jpg actual class: 0\n",
            "predicted class: 0 filename: 0730.jpg actual class: 0\n",
            "predicted class: 0 filename: 0638.jpg actual class: 0\n",
            "predicted class: 0 filename: 0566.jpg actual class: 0\n",
            "predicted class: 1 filename: 0645.jpg actual class: 0\n",
            "predicted class: 0 filename: 0565.jpg actual class: 0\n",
            "predicted class: 1 filename: 0778.jpg actual class: 0\n",
            "predicted class: 0 filename: 0697.jpg actual class: 0\n",
            "predicted class: 1 filename: 0800.jpg actual class: 0\n",
            "predicted class: 0 filename: 0857.jpg actual class: 0\n",
            "predicted class: 0 filename: 0879.jpg actual class: 0\n",
            "predicted class: 0 filename: 0765.jpg actual class: 0\n",
            "predicted class: 0 filename: 0562.jpg actual class: 0\n",
            "predicted class: 0 filename: 0719.jpg actual class: 0\n",
            "predicted class: 0 filename: 0740.jpg actual class: 0\n",
            "predicted class: 0 filename: 0607.jpg actual class: 0\n",
            "predicted class: 0 filename: 0580.jpg actual class: 0\n",
            "predicted class: 1 filename: 0839.jpg actual class: 0\n",
            "predicted class: 0 filename: 0860.jpg actual class: 0\n",
            "predicted class: 0 filename: 0718.jpg actual class: 0\n",
            "predicted class: 0 filename: 0793.jpg actual class: 0\n",
            "predicted class: 0 filename: 0881.jpg actual class: 0\n",
            "predicted class: 0 filename: 0864.jpg actual class: 0\n",
            "predicted class: 0 filename: 0696.jpg actual class: 0\n",
            "predicted class: 0 filename: 0724.jpg actual class: 0\n",
            "predicted class: 0 filename: 0703.jpg actual class: 0\n",
            "predicted class: 0 filename: 0721.jpg actual class: 0\n",
            "predicted class: 1 filename: 0652.jpg actual class: 0\n",
            "predicted class: 0 filename: 0551.jpg actual class: 0\n",
            "predicted class: 0 filename: 0720.jpg actual class: 0\n",
            "predicted class: 0 filename: 0689.jpg actual class: 0\n",
            "predicted class: 0 filename: 0795.jpg actual class: 0\n",
            "predicted class: 1 filename: 0571.jpg actual class: 0\n",
            "predicted class: 0 filename: 0640.jpg actual class: 0\n",
            "predicted class: 0 filename: 0806.jpg actual class: 0\n",
            "predicted class: 0 filename: 0761.jpg actual class: 0\n",
            "predicted class: 1 filename: 0715.jpg actual class: 0\n",
            "predicted class: 0 filename: 0884.jpg actual class: 0\n",
            "predicted class: 1 filename: 0684.jpg actual class: 0\n",
            "predicted class: 0 filename: 0846.jpg actual class: 0\n",
            "predicted class: 0 filename: 0805.jpg actual class: 0\n",
            "predicted class: 0 filename: 0872.jpg actual class: 0\n",
            "predicted class: 1 filename: 0707.jpg actual class: 0\n",
            "predicted class: 0 filename: 0868.jpg actual class: 0\n",
            "predicted class: 1 filename: 0863.jpg actual class: 0\n",
            "predicted class: 1 filename: 0871.jpg actual class: 0\n",
            "predicted class: 0 filename: 0859.jpg actual class: 0\n",
            "predicted class: 1 filename: 0769.jpg actual class: 0\n",
            "predicted class: 0 filename: 0888.jpg actual class: 0\n",
            "predicted class: 0 filename: 0733.jpg actual class: 0\n",
            "predicted class: 0 filename: 0835.jpg actual class: 0\n",
            "predicted class: 1 filename: 0841.jpg actual class: 0\n",
            "predicted class: 0 filename: 0768.jpg actual class: 0\n",
            "predicted class: 1 filename: 0878.jpg actual class: 0\n",
            "[Errno 21] Is a directory: '/content/drive/MyDrive/data/brain_tumor_dataset/test/healthy/.ipynb_checkpoints'\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#calculating the accuracy\n",
        "def calculate_accuracy(model, img_path, img_files, actual_class):\n",
        "  total_images = len(img_files)\n",
        "  predicted_ones = 0\n",
        "  for i in img_files:\n",
        "    try:\n",
        "      img = Image.open(os.path.join(img_path,i))\n",
        "      img = transform(img).unsqueeze(0).to(device)\n",
        "      output = model(img).logits\n",
        "      _, predicted = torch.max(output, 1)\n",
        "      if int(predicted.item()) == int(actual_class):\n",
        "        predicted_ones += 1\n",
        "    except Exception as e:\n",
        "      continue\n",
        "  accuracy_score = (predicted_ones/total_images)*100\n",
        "  return accuracy_score"
      ],
      "metadata": {
        "id": "j92hyOmB15e0"
      },
      "execution_count": 39,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "img_path = '/content/drive/MyDrive/data/brain_tumor_dataset/train/healthy'\n",
        "img_files = os.listdir(img_path)\n",
        "print(\"Accuracy score:\",calculate_accuracy(model, img_path, img_files, 0))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mAMy1XYG5DCw",
        "outputId": "5ff76b58-7972-4b05-ea88-5758e0c17483"
      },
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy score: 62.02830188679245\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "img_path = '/content/drive/MyDrive/data/brain_tumor_dataset/train/tumor'\n",
        "img_files = os.listdir(img_path)\n",
        "print(\"Accuracy score:\",calculate_accuracy(model, img_path, img_files, 1))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "I4y62G1K5lXF",
        "outputId": "fb1f6ebe-0862-4f62-e268-8bc42fd803f7"
      },
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy score: 85.65310492505354\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### For healthy class model accuracy score is 62%\n",
        "### For tumor images model accuracy score is 85%"
      ],
      "metadata": {
        "id": "oLFI0ASV7YKJ"
      }
    }
  ]
}