Cassava Leaf Disease Classification

Cassava Leaf Disease Classification/Dataset/LInk.txt

@@ -0,0 +1,3 @@
+https://drive.google.com/drive/folders/1KLfnDtRlBaVWG_5xMfst-d9M9GhYTLno
+
+Uploaded due to GITHUB limit.

Cassava Leaf Disease Classification/Model/CNN.ipynb

@@ -0,0 +1,294 @@
+{
+ "nbformat": 4,
+ "nbformat_minor": 0,
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "name": "python3",
+ "display_name": "Python 3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "accelerator": "TPU"
+ },
+ "cells": [
+ {
+ "cell_type": "code",
+ "source": [
+ "from google.colab import drive\n",
+ "drive.mount('/content/drive')"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 0
+ },
+ "id": "ZgKNAgwylDkM",
+ "outputId": "a33dd5ae-ad9a-4939-e18a-506f5215b336"
+ },
+ "execution_count": 1,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import numpy as np\n",
+ "import pandas as pd\n",
+ "import tensorflow as tf\n",
+ "import re\n",
+ "from tensorflow.keras.preprocessing.text import one_hot\n",
+ "import matplotlib.pyplot as py\n",
+ "from tensorflow.keras.models import Sequential,load_model\n",
+ "from sklearn.model_selection import train_test_split\n"
+ ],
+ "metadata": {
+ "id": "zq1juT-2nfgA"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "\n",
+ "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+ "\n",
+ "main_directory = '/content/drive/MyDrive/data'\n",
+ "# Define image dimensions and batch size\n",
+ "img_height, img_width = 224, 224\n",
+ "batch_size = 32\n",
+ "\n",
+ "# Use ImageDataGenerator for data augmentation and normalization\n",
+ "datagen = ImageDataGenerator(\n",
+ " rescale=1./255,\n",
+ " shear_range=0.2,\n",
+ " zoom_range=0.2,\n",
+ " horizontal_flip=True,\n",
+ " validation_split=0.2 # Set the validation split\n",
+ ")\n",
+ "\n",
+ "# Create training data generator\n",
+ "train_generator = datagen.flow_from_directory(\n",
+ " main_directory,\n",
+ " target_size=(img_height, img_width),\n",
+ " batch_size=batch_size,\n",
+ " class_mode='categorical',\n",
+ " subset='training' # Specify 'training' for training data\n",
+ ")\n",
+ "\n",
+ "# Create validation data generator\n",
+ "validation_generator = datagen.flow_from_directory(\n",
+ " main_directory,\n",
+ " target_size=(img_height, img_width),\n",
+ " batch_size=batch_size,\n",
+ " class_mode='categorical',\n",
+ " subset='validation' # Specify 'validation' for validation data\n",
+ ")\n",
+ "\n",
+ "# Define your CNN model using TensorFlow's Keras API\n",
+ "model = tf.keras.models.Sequential([\n",
+ " tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(img_height, img_width, 3)),\n",
+ " tf.keras.layers.MaxPooling2D(2, 2),\n",
+ " tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),\n",
+ " tf.keras.layers.MaxPooling2D(2, 2),\n",
+ " tf.keras.layers.Flatten(),\n",
+ " tf.keras.layers.Dense(128, activation='relu'),\n",
+ " tf.keras.layers.Dense(5, activation='softmax') # 4 classes for diseases\n",
+ "])\n",
+ "\n",
+ "# Compile the model\n",
+ "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+ "\n",
+ "# Train the model\n",
+ "model.fit(\n",
+ " train_generator,\n",
+ " steps_per_epoch=train_generator.samples // batch_size,\n",
+ " validation_data=validation_generator,\n",
+ " validation_steps=validation_generator.samples // batch_size,\n",
+ " epochs=10 # Set the number of epochs\n",
+ ")\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "ohjGWycknjcT",
+ "outputId": "26181de4-4136-45e4-b697-0a5b423cf7d2"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Found 17120 images belonging to 5 classes.\n",
+ "Found 4277 images belonging to 5 classes.\n",
+ "Epoch 1/10\n",
+ "535/535 [==============================] - 445s 826ms/step - loss: 1.1809 - accuracy: 0.6193 - val_loss: 1.0219 - val_accuracy: 0.6262\n",
+ "Epoch 2/10\n",
+ "535/535 [==============================] - 481s 899ms/step - loss: 0.9930 - accuracy: 0.6361 - val_loss: 0.9264 - val_accuracy: 0.6527\n",
+ "Epoch 3/10\n",
+ "535/535 [==============================] - 425s 795ms/step - loss: 0.9094 - accuracy: 0.6527 - val_loss: 0.8733 - val_accuracy: 0.6624\n",
+ "Epoch 4/10\n",
+ "535/535 [==============================] - 423s 791ms/step - loss: 0.8665 - accuracy: 0.6751 - val_loss: 0.8820 - val_accuracy: 0.6703\n",
+ "Epoch 5/10\n",
+ "535/535 [==============================] - 419s 784ms/step - loss: 0.8286 - accuracy: 0.6883 - val_loss: 0.8381 - val_accuracy: 0.6805\n",
+ "Epoch 6/10\n",
+ "535/535 [==============================] - 477s 892ms/step - loss: 0.8065 - accuracy: 0.6976 - val_loss: 0.8142 - val_accuracy: 0.6823\n",
+ "Epoch 7/10\n",
+ "535/535 [==============================] - 408s 763ms/step - loss: 0.7731 - accuracy: 0.7116 - val_loss: 0.8000 - val_accuracy: 0.6969\n",
+ "Epoch 8/10\n",
+ "535/535 [==============================] - 411s 769ms/step - loss: 0.7556 - accuracy: 0.7154 - val_loss: 0.8063 - val_accuracy: 0.6969\n",
+ "Epoch 9/10\n",
+ "535/535 [==============================] - 403s 753ms/step - loss: 0.7326 - accuracy: 0.7245 - val_loss: 0.8010 - val_accuracy: 0.6924\n",
+ "Epoch 10/10\n",
+ "535/535 [==============================] - 406s 759ms/step - loss: 0.7127 - accuracy: 0.7324 - val_loss: 0.7961 - val_accuracy: 0.7023\n"
+ ]
+ },
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ "<keras.src.callbacks.History at 0x7e6f006ac1f0>"
+ ]
+ },
+ "metadata": {},
+ "execution_count": 17
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "model.save(\"/content/drive/MyDrive\")\n"
+ ],
+ "metadata": {
+ "id": "Tv3WJTGC9Dt1"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "evaluation_result = model.evaluate(validation_generator, steps=validation_generator.samples // batch_size)\n",
+ "print(\"Validation Loss:\", evaluation_result[0])\n",
+ "print(\"Validation Accuracy:\", evaluation_result[1])"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "tGE3OAL4_YWp",
+ "outputId": "66ee96e8-5664-49bf-b9b8-71ec6b9f62b9"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "133/133 [==============================] - 84s 630ms/step - loss: 0.8085 - accuracy: 0.7002\n",
+ "Validation Loss: 0.8085159063339233\n",
+ "Validation Accuracy: 0.7001879811286926\n"
+ ]
+ }
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import tensorflow as tf\n",
+ "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
+ "from tensorflow.keras.applications import VGG16\n",
+ "from tensorflow.keras.models import Sequential\n",
+ "from tensorflow.keras.layers import Dense, Flatten, Dropout\n",
+ "\n",
+ "\n",
+ "# Load pre-trained VGG16 model\n",
+ "base_model = VGG16(weights='imagenet', include_top=False, input_shape=(img_height, img_width, 3))\n",
+ "\n",
+ "# Freeze the layers of the pre-trained model\n",
+ "for layer in base_model.layers:\n",
+ " layer.trainable = False\n",
+ "\n",
+ "# Create a new model on top of the pre-trained model\n",
+ "model = Sequential()\n",
+ "model.add(base_model)\n",
+ "model.add(Flatten())\n",
+ "model.add(Dense(128, activation='relu'))\n",
+ "model.add(Dropout(0.5))\n",
+ "model.add(Dense(5, activation='softmax')) # 5 classes for your task\n",
+ "\n",
+ "# Compile the model\n",
+ "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
+ "\n",
+ "# Train the model\n",
+ "model.fit(\n",
+ " train_generator,\n",
+ " steps_per_epoch=train_generator.samples // batch_size,\n",
+ " validation_data=validation_generator,\n",
+ " validation_steps=validation_generator.samples // batch_size,\n",
+ " epochs=10 # Set the number of epochs\n",
+ ")\n",
+ "\n",
+ "# Evaluate the model on the validation set\n",
+ "evaluation_result = model.evaluate(validation_generator, steps=validation_generator.samples // batch_size)\n",
+ "print(\"Validation Loss:\", evaluation_result[0])\n",
+ "print(\"Validation Accuracy:\", evaluation_result[1])\n"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "LUKlFJfZ-66C",
+ "outputId": "74a256ac-9a0a-411e-f58c-8158927c5d72"
+ },
+ "execution_count": null,
+ "outputs": [
+ {
+ "output_type": "stream",
+ "name": "stdout",
+ "text": [
+ "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
+ "58889256/58889256 [==============================] - 2s 0us/step\n",
+ "Epoch 1/10\n",
+ "535/535 [==============================] - 442s 809ms/step - loss: 1.1297 - accuracy: 0.6065 - val_loss: 0.9465 - val_accuracy: 0.6147\n",
+ "Epoch 2/10\n",
+ "535/535 [==============================] - 488s 913ms/step - loss: 1.0326 - accuracy: 0.6147 - val_loss: 0.9351 - val_accuracy: 0.6163\n",
+ "Epoch 3/10\n",
+ "535/535 [==============================] - 434s 812ms/step - loss: 1.0177 - accuracy: 0.6149 - val_loss: 0.9210 - val_accuracy: 0.6161\n",
+ "Epoch 4/10\n",
+ "535/535 [==============================] - 432s 807ms/step - loss: 1.0118 - accuracy: 0.6149 - val_loss: 0.9234 - val_accuracy: 0.6147\n",
+ "Epoch 5/10\n",
+ "535/535 [==============================] - 480s 898ms/step - loss: 1.0028 - accuracy: 0.6149 - val_loss: 0.9272 - val_accuracy: 0.6151\n",
+ "Epoch 6/10\n",
+ "535/535 [==============================] - 415s 776ms/step - loss: 0.9988 - accuracy: 0.6149 - val_loss: 0.9163 - val_accuracy: 0.6158\n",
+ "Epoch 7/10\n",
+ "535/535 [==============================] - 479s 896ms/step - loss: 0.9945 - accuracy: 0.6149 - val_loss: 0.9155 - val_accuracy: 0.6147\n",
+ "Epoch 8/10\n",
+ "535/535 [==============================] - 420s 784ms/step - loss: 0.9990 - accuracy: 0.6149 - val_loss: 0.9119 - val_accuracy: 0.6163\n",
+ "Epoch 9/10\n",
+ "535/535 [==============================] - 472s 883ms/step - loss: 0.9939 - accuracy: 0.6149 - val_loss: 0.9141 - val_accuracy: 0.6156\n",
+ "Epoch 10/10\n",
+ "535/535 [==============================] - 415s 776ms/step - loss: 0.9950 - accuracy: 0.6147 - val_loss: 0.9141 - val_accuracy: 0.6140\n",
+ "133/133 [==============================] - 84s 629ms/step - loss: 0.9111 - accuracy: 0.6151\n",
+ "Validation Loss: 0.9110695123672485\n",
+ "Validation Accuracy: 0.6151315569877625\n"
+ ]
+ }
+ ]
+ }
+ ]
+}