skin cancer detection

Skin_cancer_Detection.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "NvgOAuTNHnFv",
+    "outputId": "9af20872-9b69-4105-c9b0-a5189e93f11f"
+   },
+   "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": null,
+   "metadata": {
+    "id": "e5VoXOheOrbn"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import os\n",
+    "import shutil\n",
+    "import random\n",
+    "metadata = pd.read_csv('/content/drive/MyDrive/Dataset_skin/HAM10000_metadata.csv')\n",
+    "\n",
+    "# Define source and destination directories\n",
+    "src_dir  = '/content/drive/MyDrive/Dataset_skin/HAM10000_images_part_1/'\n",
+    "dst_dir = '/content/newData'\n",
+    "\n",
+    "# Create destination directories for each class\n",
+    "for class_name in metadata['dx'].unique():\n",
+    "    os.makedirs(os.path.join(dst_dir, class_name), exist_ok=True)\n",
+    "\n",
+    "# Copy images to their respective class directories\n",
+    "for index, row in metadata.iterrows():\n",
+    "    img_name = row['image_id'] + '.jpg'\n",
+    "    src_path = os.path.join(src_dir, img_name)\n",
+    "    dst_path = os.path.join(dst_dir, row['dx'], img_name)\n",
+    "    shutil.copy(src_path, dst_path)\n",
+    "    \n",
+    "print('Dataset splitting complete.')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "wuoNOi_-B0mN"
+   },
+   "outputs": [],
+   "source": [
+    "!zip -r newData.zip newData/\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ekUMBoOJB9FL"
+   },
+   "outputs": [],
+   "source": [
+    "!mv newData.zip /content/drive/MyDrive\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "MNEtNMmmQK6n"
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "data_dir  = '/content/newData'\n",
+    "train_dir = '/content/train_dir'\n",
+    "test_dir = '/content/test_dir'\n",
+    "\n",
+    "\n",
+    "# Define list of class names\n",
+    "class_names = [\"akiec\", \"bcc\", \"bkl\", \"df\", \"mel\", \"nv\", \"vasc\"]\n",
+    "\n",
+    "# Create train and test directories if they don't exist\n",
+    "if not os.path.exists(train_dir):\n",
+    "    os.makedirs(train_dir)\n",
+    "if not os.path.exists(test_dir):\n",
+    "    os.makedirs(test_dir)\n",
+    "\n",
+    "# Split data into train and test sets\n",
+    "for class_name in class_names:\n",
+    "    class_dir = os.path.join(data_dir, class_name)\n",
+    "    train_class_dir = os.path.join(train_dir, class_name)\n",
+    "    test_class_dir = os.path.join(test_dir, class_name)\n",
+    "    if not os.path.exists(train_class_dir):\n",
+    "        os.makedirs(train_class_dir)\n",
+    "    if not os.path.exists(test_class_dir):\n",
+    "        os.makedirs(test_class_dir)\n",
+    "    files = os.listdir(class_dir)\n",
+    "    random.shuffle(files)\n",
+    "    train_files = files[:int(len(files)*0.8)]\n",
+    "    test_files = files[int(len(files)*0.8):]\n",
+    "    for file in train_files:\n",
+    "        src_path = os.path.join(class_dir, file)\n",
+    "        dst_path = os.path.join(train_class_dir, file)\n",
+    "        shutil.copy(src_path, dst_path)\n",
+    "    for file in test_files:\n",
+    "        src_path = os.path.join(class_dir, file)\n",
+    "        dst_path = os.path.join(test_class_dir, file)\n",
+    "        shutil.copy(src_path, dst_path)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "35cL5WbTA_Cr",
+    "outputId": "fff6d9c7-767d-40bb-da34-ee32b4ba51ec"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Found 8010 images belonging to 7 classes.\n",
+      "Found 2005 images belonging to 7 classes.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "import numpy as np\n",
+    "import tensorflow as tf\n",
+    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+    "from tensorflow.keras.models import Sequential\n",
+    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\n",
+    "\n",
+    "# Define data paths and parameters\n",
+    "train_dir = '/content/train_dir/'\n",
+    "test_dir = '/content/test_dir/'\n",
+    "input_shape = (224, 224, 3)\n",
+    "batch_size = 32\n",
+    "epochs = 50\n",
+    "num_classes = 7\n",
+    "\n",
+    "# Create data generators with data augmentation\n",
+    "train_datagen = ImageDataGenerator(rescale=1./255,\n",
+    "                                   rotation_range=40,\n",
+    "                                   width_shift_range=0.2,\n",
+    "                                   height_shift_range=0.2,\n",
+    "                                   shear_range=0.2,\n",
+    "                                   zoom_range=0.2,\n",
+    "                                   horizontal_flip=True,\n",
+    "                                   fill_mode='nearest')\n",
+    "test_datagen = ImageDataGenerator(rescale=1./255)\n",
+    "\n",
+    "train_generator = train_datagen.flow_from_directory(train_dir,\n",
+    "                                                    target_size=input_shape[:2],\n",
+    "                                                    batch_size=batch_size,\n",
+    "                                                    class_mode='categorical')\n",
+    "\n",
+    "test_generator = test_datagen.flow_from_directory(test_dir,\n",
+    "                                                  target_size=input_shape[:2],\n",
+    "                                                  batch_size=batch_size,\n",
+    "                                                  class_mode='categorical')\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "UTqAmayWFPCF"
+   },
+   "outputs": [],
+   "source": [
+    "# Define the model architecture\n",
+    "model = Sequential()\n",
+    "model.add(Conv2D(32, (3, 3), activation='relu', input_shape=input_shape))\n",
+    "model.add(MaxPooling2D((2, 2)))\n",
+    "model.add(Conv2D(64, (3, 3), activation='relu'))\n",
+    "model.add(MaxPooling2D((2, 2)))\n",
+    "model.add(Conv2D(128, (3, 3), activation='relu'))\n",
+    "model.add(MaxPooling2D((2, 2)))\n",
+    "model.add(Conv2D(128, (3, 3), activation='relu'))\n",
+    "model.add(MaxPooling2D((2, 2)))\n",
+    "model.add(Flatten())\n",
+    "model.add(Dense(512, activation='relu'))\n",
+    "model.add(Dropout(0.5))\n",
+    "model.add(Dense(num_classes, activation='softmax'))\n",
+    "\n",
+    "# Compile the model\n",
+    "model.compile(loss='categorical_crossentropy',\n",
+    "              optimizer='rmsprop',\n",
+    "              metrics=['accuracy'])\n",
+    "\n",
+    "# Train the model\n",
+    "history = model.fit(train_generator,\n",
+    "                    steps_per_epoch=train_generator.samples//batch_size,\n",
+    "                    epochs=epochs,\n",
+    "                    validation_data=test_generator,\n",
+    "                    validation_steps=test_generator.samples//batch_size)\n",
+    "\n",
+    "# Save the model\n",
+    "model.save('skin_cancer_model.h5')\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}