{
  "cells": [
    {
      "attachments": {},
      "cell_type": "markdown",
      "metadata": {
        "id": "FjDGwlCJYO2m"
      },
      "source": [
        "### Model Inferences"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "DUXRPvLRxpJe"
      },
      "outputs": [],
      "source": [
        "import pandas as pd \n",
        "import numpy as np\n",
        "from tensorflow import keras\n",
        "import tensorflow as tf\n",
        "import pickle\n",
        "from keras.models import load_model\n",
        "from tensorflow.keras.preprocessing import image \n",
        "import matplotlib.pyplot as plt"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "WOLLnPnAuzKm",
        "outputId": "644f852b-b695-40d8-db1c-3a8e502ca316"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9nTgKQUKu61s",
        "outputId": "3105e278-99eb-468d-8890-4079916391b2"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "/content/drive/MyDrive/cnn_model\n"
          ]
        }
      ],
      "source": [
        "%cd /content/drive/MyDrive/cnn_model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "ij3PCeoCyU23"
      },
      "outputs": [],
      "source": [
        "def prediction(file):\n",
        "    img = tf.keras.utils.load_img(file, target_size=(224, 224))\n",
        "    x = tf.keras.utils.img_to_array(img)\n",
        "    x = np.expand_dims(x, axis=0)\n",
        "\n",
        "    # Load the saved model\n",
        "    loaded_model = load_model('cnn_model.h5')\n",
        "\n",
        "    # Predict the class probabilities\n",
        "    classes = loaded_model.predict(x)\n",
        "\n",
        "    # Get the predicted class label\n",
        "    classes = np.ravel(classes) # convert to 1D array\n",
        "    idx = np.argmax(classes)\n",
        "    clas = ['adenocarcinoma', 'large.cell.carcinoma', 'normal', 'squamous.cell.carcinoma']\n",
        "\n",
        "    # Print the predicted class label\n",
        "    print('Prediction is a {}'.format(clas[idx]))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "h4xpRFtUw-OR",
        "outputId": "6af2e2d1-3f78-4a9a-a7b2-b8e83db72e6b"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "1/1 [==============================] - 2s 2s/step\n",
            "Prediction is a normal\n"
          ]
        }
      ],
      "source": [
        "prediction('Adenocarcinoma-in-situ-Axial-contrast-enhanced-chest-CT-scan-with-lung-window.png')"
      ]
    },
    {
      "attachments": {},
      "cell_type": "markdown",
      "metadata": {
        "id": "VG4syGUcYjSK"
      },
      "source": [
        "Prediction wrong, the model should maintained for next utilization"
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python",
      "version": "3.7.16"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}