{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceType":"competition","sourceId":3362,"databundleVersionId":31148}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2026-02-20T06:47:40.970901Z","iopub.execute_input":"2026-02-20T06:47:40.971227Z","iopub.status.idle":"2026-02-20T06:47:40.979186Z","shell.execute_reply.started":"2026-02-20T06:47:40.971202Z","shell.execute_reply":"2026-02-20T06:47:40.978559Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"execution":{"iopub.status.busy":"2026-02-20T06:47:42.402414Z","iopub.execute_input":"2026-02-20T06:47:42.402736Z","iopub.status.idle":"2026-02-20T06:47:52.845791Z","shell.execute_reply.started":"2026-02-20T06:47:42.402712Z","shell.execute_reply":"2026-02-20T06:47:52.845059Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Dogs vs. Cats Dataset Preparation","metadata":{"execution":{"iopub.status.busy":"2024-01-08T06:57:18.293035Z","iopub.execute_input":"2024-01-08T06:57:18.293457Z","iopub.status.idle":"2024-01-08T06:57:19.311078Z","shell.execute_reply.started":"2024-01-08T06:57:18.293422Z","shell.execute_reply":"2024-01-08T06:57:19.309969Z"}}},{"cell_type":"markdown","source":"## Plot Dog and Cat Photos","metadata":{}},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'dog.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-02-20T06:47:59.316676Z","iopub.execute_input":"2026-02-20T06:47:59.317614Z","iopub.status.idle":"2026-02-20T06:48:00.294116Z","shell.execute_reply.started":"2026-02-20T06:47:59.317572Z","shell.execute_reply":"2026-02-20T06:48:00.293226Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot cat photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'cat.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-02-20T06:48:02.315616Z","iopub.execute_input":"2026-02-20T06:48:02.316539Z","iopub.status.idle":"2026-02-20T06:48:03.217134Z","shell.execute_reply.started":"2026-02-20T06:48:02.316507Z","shell.execute_reply":"2026-02-20T06:48:03.216322Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load dogs vs cats dataset, reshape and save to a new file\nfrom os import listdir\nfrom numpy import asarray\nfrom numpy import save\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array\n# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n\t# determine class\n\toutput = 0.0\n\tif file.startswith('dog'):\n\t\toutput = 1.0\n\t# load image\n\tphoto = load_img(folder + file, target_size=(128, 128))\n\t# convert to numpy array\n\tphoto = img_to_array(photo)\n\t# store\n\tphotos.append(photo)\n\tlabels.append(output)\n# convert to a numpy arrays\nphotos = asarray(photos)\nlabels = asarray(labels)\nprint(photos.shape, labels.shape)\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T06:48:05.163622Z","iopub.execute_input":"2026-02-20T06:48:05.163954Z","iopub.status.idle":"2026-02-20T06:48:38.406146Z","shell.execute_reply.started":"2026-02-20T06:48:05.163928Z","shell.execute_reply":"2026-02-20T06:48:38.405169Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')\nprint(photos.shape, labels.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T06:48:38.462961Z","iopub.execute_input":"2026-02-20T06:48:38.463750Z","iopub.status.idle":"2026-02-20T06:48:40.065587Z","shell.execute_reply.started":"2026-02-20T06:48:38.463705Z","shell.execute_reply":"2026-02-20T06:48:40.064684Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Pre-Process Photos into Standard Directories","metadata":{}},{"cell_type":"code","source":"from os import makedirs\n# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\nfor subdir in subdirs:\n\t# create label subdirectories\n\tlabeldirs = ['dogs/', 'cats/']\n\tfor labldir in labeldirs:\n\t\tnewdir = dataset_home + subdir + labldir\n\t\tmakedirs(newdir, exist_ok=True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T06:48:41.819718Z","iopub.execute_input":"2026-02-20T06:48:41.820053Z","iopub.status.idle":"2026-02-20T06:48:42.055481Z","shell.execute_reply.started":"2026-02-20T06:48:41.820027Z","shell.execute_reply":"2026-02-20T06:48:42.054508Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from random import seed\nfrom random import random\nfrom shutil import copyfile\nfrom os import listdir\n# seed random number generator\nseed(1)\n# define ratio of pictures to use for validation\nval_ratio = 0.25\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T06:48:43.734957Z","iopub.execute_input":"2026-02-20T06:48:43.735594Z","iopub.status.idle":"2026-02-20T06:48:46.038012Z","shell.execute_reply.started":"2026-02-20T06:48:43.735567Z","shell.execute_reply":"2026-02-20T06:48:46.037250Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random\n# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\nfor subdir in subdirs:\n\t# create label subdirectories\n\tlabeldirs = ['dogs/', 'cats/']\n\tfor labldir in labeldirs:\n\t\tnewdir = dataset_home + subdir + labldir\n\t\tmakedirs(newdir, exist_ok=True)\n# seed random number generator\nseed(1)\n# define ratio of pictures to use for validation\nval_ratio = 0.25\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T06:48:50.687128Z","iopub.execute_input":"2026-02-20T06:48:50.687954Z","iopub.status.idle":"2026-02-20T06:48:53.646787Z","shell.execute_reply.started":"2026-02-20T06:48:50.687917Z","shell.execute_reply":"2026-02-20T06:48:53.646022Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Develop a Baseline CNN Model","metadata":{}},{"cell_type":"code","source":"import sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T06:48:55.290836Z","iopub.execute_input":"2026-02-20T06:48:55.291537Z","iopub.status.idle":"2026-02-20T06:48:59.643277Z","shell.execute_reply.started":"2026-02-20T06:48:55.291507Z","shell.execute_reply":"2026-02-20T06:48:59.642269Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n# block 1\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\nmodel.add(MaxPooling2D((2, 2)))\n# block 2\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\n# block 3\nmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T07:59:12.868995Z","iopub.execute_input":"2026-02-20T07:59:12.869318Z","iopub.status.idle":"2026-02-20T07:59:12.916319Z","shell.execute_reply.started":"2026-02-20T07:59:12.869292Z","shell.execute_reply":"2026-02-20T07:59:12.915629Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model():\n\tmodel = Sequential()\n\tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T07:59:14.684130Z","iopub.execute_input":"2026-02-20T07:59:14.684480Z","iopub.status.idle":"2026-02-20T07:59:14.690262Z","shell.execute_reply.started":"2026-02-20T07:59:14.684451Z","shell.execute_reply":"2026-02-20T07:59:14.689414Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define model\nmodel = define_model()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T07:59:16.358025Z","iopub.execute_input":"2026-02-20T07:59:16.358621Z","iopub.status.idle":"2026-02-20T07:59:16.403843Z","shell.execute_reply.started":"2026-02-20T07:59:16.358593Z","shell.execute_reply":"2026-02-20T07:59:16.403056Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create data generator\ndatagen = ImageDataGenerator(rescale=1.0/255.0)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T07:59:18.251766Z","iopub.execute_input":"2026-02-20T07:59:18.252480Z","iopub.status.idle":"2026-02-20T07:59:18.256340Z","shell.execute_reply.started":"2026-02-20T07:59:18.252451Z","shell.execute_reply":"2026-02-20T07:59:18.255454Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# prepare iterators\ndatagen = ImageDataGenerator(rescale=1.0/255.0)\n\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T07:59:20.231672Z","iopub.execute_input":"2026-02-20T07:59:20.232694Z","iopub.status.idle":"2026-02-20T07:59:20.946299Z","shell.execute_reply.started":"2026-02-20T07:59:20.232663Z","shell.execute_reply":"2026-02-20T07:59:20.945474Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## One Block VGG Model","metadata":{}},{"cell_type":"code","source":"# fit model\nhistory = model.fit(train_it, \n                    steps_per_epoch=len(train_it),\n                \tvalidation_data=test_it,\n                    validation_steps=len(test_it), \n                    epochs=20, \n                    verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T07:59:23.043919Z","iopub.execute_input":"2026-02-20T07:59:23.044529Z","iopub.status.idle":"2026-02-20T08:13:11.576549Z","shell.execute_reply.started":"2026-02-20T07:59:23.044497Z","shell.execute_reply":"2026-02-20T08:13:11.575857Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T08:14:20.903811Z","iopub.execute_input":"2026-02-20T08:14:20.904157Z","iopub.status.idle":"2026-02-20T08:14:32.029700Z","shell.execute_reply.started":"2026-02-20T08:14:20.904131Z","shell.execute_reply":"2026-02-20T08:14:32.028899Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. วาดกราฟ Loss\npyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\npyplot.legend()\n\n# 2. วาดกราฟ Accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\npyplot.legend()\n\n# 3. show\npyplot.tight_layout()\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T08:14:35.970786Z","iopub.execute_input":"2026-02-20T08:14:35.971461Z","iopub.status.idle":"2026-02-20T08:14:36.451006Z","shell.execute_reply.started":"2026-02-20T08:14:35.971433Z","shell.execute_reply":"2026-02-20T08:14:36.450115Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Two Block VGG Model","metadata":{}},{"cell_type":"code","source":"# baseline model for the dogs vs cats dataset\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T08:14:41.166234Z","iopub.execute_input":"2026-02-20T08:14:41.166581Z","iopub.status.idle":"2026-02-20T08:14:41.171317Z","shell.execute_reply.started":"2026-02-20T08:14:41.166554Z","shell.execute_reply":"2026-02-20T08:14:41.170321Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\nmodel = Sequential()\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\nmodel.add(Dense(1, activation='sigmoid'))\n# compile model\nopt = SGD(lr=0.001, momentum=0.9)\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T08:14:42.690175Z","iopub.execute_input":"2026-02-20T08:14:42.690831Z","iopub.status.idle":"2026-02-20T08:14:42.737051Z","shell.execute_reply.started":"2026-02-20T08:14:42.690802Z","shell.execute_reply":"2026-02-20T08:14:42.736399Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# run the test harness for evaluating a model\n# define model\nmodel = define_model()\n# create data generator\ndatagen = ImageDataGenerator(rescale=1.0/255.0)\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n# fit model\nhistory = model.fit_generator(train_it, steps_per_epoch=len(train_it),\n\tvalidation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T08:14:44.470126Z","iopub.execute_input":"2026-02-20T08:14:44.470434Z","iopub.status.idle":"2026-02-20T08:28:33.085560Z","shell.execute_reply.started":"2026-02-20T08:14:44.470412Z","shell.execute_reply":"2026-02-20T08:28:33.084808Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T08:29:53.108978Z","iopub.execute_input":"2026-02-20T08:29:53.109435Z","iopub.status.idle":"2026-02-20T08:30:03.381543Z","shell.execute_reply.started":"2026-02-20T08:29:53.109405Z","shell.execute_reply":"2026-02-20T08:30:03.380638Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. วาดกราฟ Loss\npyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\npyplot.legend()\n\n# 2. วาดกราฟ Accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\npyplot.legend()\n\n# 3. show\npyplot.tight_layout()\npyplot.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Three Block VGG Model","metadata":{}},{"cell_type":"code","source":"# เตรียมข้อมูล\ndatagen = ImageDataGenerator(rescale=1.0/255.0)\n\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T09:40:01.312774Z","iopub.execute_input":"2026-02-20T09:40:01.313660Z","iopub.status.idle":"2026-02-20T09:40:02.027008Z","shell.execute_reply.started":"2026-02-20T09:40:01.313614Z","shell.execute_reply":"2026-02-20T09:40:02.026339Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\nmodel = Sequential()\n# Block 1\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Block 2\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Block 3\nmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\n\n\n# Flatten & Dense\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\nmodel.add(Dense(1, activation='sigmoid'))\n\n# Compile Model\nopt = SGD(learning_rate=0.001, momentum=0.9)\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T09:40:03.628266Z","iopub.execute_input":"2026-02-20T09:40:03.629052Z","iopub.status.idle":"2026-02-20T09:40:03.700655Z","shell.execute_reply.started":"2026-02-20T09:40:03.629026Z","shell.execute_reply":"2026-02-20T09:40:03.699923Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = model.fit(train_it, \n                    steps_per_epoch=len(train_it),\n                \tvalidation_data=test_it,\n                    validation_steps=len(test_it), \n                    epochs=20, \n                    verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T09:40:05.392724Z","iopub.execute_input":"2026-02-20T09:40:05.393072Z","iopub.status.idle":"2026-02-20T09:54:13.658048Z","shell.execute_reply.started":"2026-02-20T09:40:05.393045Z","shell.execute_reply":"2026-02-20T09:54:13.657282Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T09:54:32.798408Z","iopub.execute_input":"2026-02-20T09:54:32.799188Z","iopub.status.idle":"2026-02-20T09:54:43.410208Z","shell.execute_reply.started":"2026-02-20T09:54:32.799156Z","shell.execute_reply":"2026-02-20T09:54:43.409302Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. วาดกราฟ Loss\npyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\npyplot.legend()\n\n# 2. วาดกราฟ Accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\npyplot.legend()\n\n# 3. show\npyplot.tight_layout()\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T09:54:50.215379Z","iopub.execute_input":"2026-02-20T09:54:50.216126Z","iopub.status.idle":"2026-02-20T09:54:50.710407Z","shell.execute_reply.started":"2026-02-20T09:54:50.216095Z","shell.execute_reply":"2026-02-20T09:54:50.709545Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Dropout Regularization","metadata":{}},{"cell_type":"code","source":"# เตรียมข้อมูล\ndatagen = ImageDataGenerator(rescale=1.0/255.0)\n\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T12:39:10.723288Z","iopub.execute_input":"2026-02-20T12:39:10.724119Z","iopub.status.idle":"2026-02-20T12:39:11.377144Z","shell.execute_reply.started":"2026-02-20T12:39:10.724091Z","shell.execute_reply":"2026-02-20T12:39:11.376402Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.layers import Dropout\n\n# สร้าง model\nmodel = Sequential()\n# Block 1\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\nmodel.add(MaxPooling2D((2, 2)))\nmodel.add(Dropout(0.2))\n\n# Block 2\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\nmodel.add(Dropout(0.2))\n\n# Block 3\nmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\nmodel.add(Dropout(0.2))\n\n\n# Flatten & Dense\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))\n\n# Compile Model\nopt = SGD(learning_rate=0.001, momentum=0.9)\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T12:39:15.399184Z","iopub.execute_input":"2026-02-20T12:39:15.399907Z","iopub.status.idle":"2026-02-20T12:39:15.492512Z","shell.execute_reply.started":"2026-02-20T12:39:15.399876Z","shell.execute_reply":"2026-02-20T12:39:15.491756Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = model.fit(train_it, \n                    steps_per_epoch=len(train_it),\n                \tvalidation_data=test_it,\n                    validation_steps=len(test_it), \n                    epochs=50, \n                    verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T12:39:17.767185Z","iopub.execute_input":"2026-02-20T12:39:17.767798Z","iopub.status.idle":"2026-02-20T13:14:16.129047Z","shell.execute_reply.started":"2026-02-20T12:39:17.767751Z","shell.execute_reply":"2026-02-20T13:14:16.128281Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\npyplot.legend()\n\n# plot accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\npyplot.legend()\n# save plot to file\npyplot.tight_layout()\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T13:15:40.122574Z","iopub.execute_input":"2026-02-20T13:15:40.123172Z","iopub.status.idle":"2026-02-20T13:15:40.594559Z","shell.execute_reply.started":"2026-02-20T13:15:40.123140Z","shell.execute_reply":"2026-02-20T13:15:40.593685Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Image Data Augmentation","metadata":{}},{"cell_type":"code","source":"# create data generators\ntrain_datagen = ImageDataGenerator(rescale=1.0/255.0,\n\twidth_shift_range=0.1, \n    height_shift_range=0.1,\n    horizontal_flip=True\n)\ntest_datagen = ImageDataGenerator(rescale=1.0/255.0)\n\n# prepare iterators\ntrain_it = train_datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\ntest_it = test_datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T13:16:14.645973Z","iopub.execute_input":"2026-02-20T13:16:14.646317Z","iopub.status.idle":"2026-02-20T13:16:15.398035Z","shell.execute_reply.started":"2026-02-20T13:16:14.646290Z","shell.execute_reply":"2026-02-20T13:16:15.397407Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# สร้าง model\nmodel = Sequential()\n# Block 1\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Block 2\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Block 3\nmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\n\n# Flatten & Dense\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\nmodel.add(Dense(1, activation='sigmoid'))\n\n# Compile Model\nopt = SGD(learning_rate=0.001, momentum=0.9)\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T13:16:17.278050Z","iopub.execute_input":"2026-02-20T13:16:17.278755Z","iopub.status.idle":"2026-02-20T13:16:17.352254Z","shell.execute_reply.started":"2026-02-20T13:16:17.278727Z","shell.execute_reply":"2026-02-20T13:16:17.351416Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = model.fit(train_it, \n                    steps_per_epoch=len(train_it),\n                    validation_data=test_it, \n                    validation_steps=len(test_it), \n                    epochs=50,\n                    verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T13:16:19.857392Z","iopub.execute_input":"2026-02-20T13:16:19.857724Z","iopub.status.idle":"2026-02-20T15:36:56.875109Z","shell.execute_reply.started":"2026-02-20T13:16:19.857697Z","shell.execute_reply":"2026-02-20T15:36:56.874108Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. วาดกราฟ Loss\npyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\npyplot.legend()\n\n# 2. วาดกราฟ Accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\npyplot.legend()\n\n# 3. show\npyplot.tight_layout()\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T15:37:00.266547Z","iopub.execute_input":"2026-02-20T15:37:00.266884Z","iopub.status.idle":"2026-02-20T15:37:00.714599Z","shell.execute_reply.started":"2026-02-20T15:37:00.266859Z","shell.execute_reply":"2026-02-20T15:37:00.713771Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Explore Transfer Learning","metadata":{}},{"cell_type":"code","source":"import sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.optimizers import Adam\n\n# load model\nbase_model = VGG16(include_top=False, input_shape=(224, 224, 3))\n# mark loaded layers as not trainable\nfor layer in base_model.layers:\n    layer.trainable = False\n    \n# add new classifier layers\nflat1 = Flatten()(base_model.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\nmodel = Model(inputs=base_model.input, outputs=output)\n\n# compile model\nopt = Adam(learning_rate=0.00001) \n\nmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T15:44:38.666646Z","iopub.execute_input":"2026-02-20T15:44:38.667308Z","iopub.status.idle":"2026-02-20T15:44:38.992576Z","shell.execute_reply.started":"2026-02-20T15:44:38.667279Z","shell.execute_reply":"2026-02-20T15:44:38.991619Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(224, 224))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(224, 224))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T15:44:41.885669Z","iopub.execute_input":"2026-02-20T15:44:41.886318Z","iopub.status.idle":"2026-02-20T15:44:42.485499Z","shell.execute_reply.started":"2026-02-20T15:44:41.886288Z","shell.execute_reply":"2026-02-20T15:44:42.484797Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nhistory = model.fit(train_it, \n                    validation_data=test_it, \n                    epochs=5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T15:44:44.069152Z","iopub.execute_input":"2026-02-20T15:44:44.069997Z","iopub.status.idle":"2026-02-20T15:50:10.205128Z","shell.execute_reply.started":"2026-02-20T15:44:44.069952Z","shell.execute_reply":"2026-02-20T15:50:10.204374Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot loss\npyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\n\n# plot accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n\n# save plot to file\nfilename = sys.argv[0].split('/')[-1]\npyplot.savefig(filename + '_plot.png')\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T15:51:31.616255Z","iopub.execute_input":"2026-02-20T15:51:31.616603Z","iopub.status.idle":"2026-02-20T15:51:32.129134Z","shell.execute_reply.started":"2026-02-20T15:51:31.616578Z","shell.execute_reply":"2026-02-20T15:51:32.128231Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"base_model = VGG16(\n    weights='imagenet', \n    include_top=False, \n    input_shape=(224, 224, 3)\n)\n\n\nfor layer in base_model.layers:\n    layer.trainable = False\n\n\nx = Flatten()(base_model.output)\nx = Dense(128, activation='relu', kernel_initializer='he_uniform')(x)\noutput = Dense(1, activation='sigmoid')(x) \n\nmodel = Model(inputs=base_model.input, outputs=output)\n\nmodel.compile(optimizer=Adam(learning_rate=0.0001), \n              loss='binary_crossentropy', \n              metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T16:46:20.519641Z","iopub.execute_input":"2026-02-20T16:46:20.519987Z","iopub.status.idle":"2026-02-20T16:46:20.849616Z","shell.execute_reply.started":"2026-02-20T16:46:20.519960Z","shell.execute_reply":"2026-02-20T16:46:20.848882Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history = model.fit(train_it, \n                    validation_data=test_it, \n                    epochs=10)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T16:56:59.995459Z","iopub.execute_input":"2026-02-20T16:56:59.995759Z","iopub.status.idle":"2026-02-20T17:07:08.251234Z","shell.execute_reply.started":"2026-02-20T16:56:59.995737Z","shell.execute_reply":"2026-02-20T17:07:08.250526Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pyplot.subplot(211)\npyplot.title('Cross Entropy Loss')\npyplot.plot(history.history['loss'], color='blue', label='train')\npyplot.plot(history.history['val_loss'], color='orange', label='test')\n\t# plot accuracy\npyplot.subplot(212)\npyplot.title('Classification Accuracy')\npyplot.plot(history.history['accuracy'], color='blue', label='train')\npyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n\t# save plot to file\nfilename = sys.argv[0].split('/')[-1]\npyplot.savefig(filename + '_plot.png')\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T17:10:25.170039Z","iopub.execute_input":"2026-02-20T17:10:25.170934Z","iopub.status.idle":"2026-02-20T17:10:25.506437Z","shell.execute_reply.started":"2026-02-20T17:10:25.170902Z","shell.execute_reply":"2026-02-20T17:10:25.505740Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nprint(\"\\nRandom Inference (5 Cats and 5 Dogs):\")\n\nplt.figure(figsize=(15, 6))\n\ncat_images, dog_images = [], []\ncat_labels, dog_labels = [], []\n\nfor imgs, labels in test_it:\n    for i in range(len(imgs)):\n        if labels[i] == 0 and len(cat_images) < 5:\n            cat_images.append(imgs[i])\n            cat_labels.append(labels[i])\n        elif labels[i] == 1 and len(dog_images) < 5:\n            dog_images.append(imgs[i])\n            dog_labels.append(labels[i])\n            \n    if len(cat_images) == 5 and len(dog_images) == 5:\n        break\n\nall_imgs = cat_images + dog_images\nall_labels = cat_labels + dog_labels\n\nfor i in range(10):\n    ax = plt.subplot(2, 5, i + 1)\n    \n    img = all_imgs[i]\n    img_display = ((img - img.min()) * (255 / (img.max() - img.min()))).astype(\"uint8\")\n    plt.imshow(img_display)\n    \n    img_input = tf.expand_dims(img, 0)\n    prediction = model.predict(img_input, verbose=0)[0][0]\n    \n    pred_label = \"Dog\" if prediction > 0.5 else \"Cat\"\n    true_label = \"Dog\" if all_labels[i] == 1 else \"Cat\"\n    color = \"green\" if pred_label == true_label else \"red\"\n    score = prediction if prediction > 0.5 else 1 - prediction\n    \n    plt.title(f\"True: {true_label}\\nPred: {pred_label}\\n({score:.2%})\", color=color, fontsize=10)\n    plt.axis(\"off\")\n    print(prediction)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-20T17:10:28.114412Z","iopub.execute_input":"2026-02-20T17:10:28.115188Z","iopub.status.idle":"2026-02-20T17:10:30.961889Z","shell.execute_reply.started":"2026-02-20T17:10:28.115159Z","shell.execute_reply":"2026-02-20T17:10:30.960982Z"}},"outputs":[],"execution_count":null}]}