{"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":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"},{"sourceId":244955,"sourceType":"modelInstanceVersion","isSourceIdPinned":true,"modelInstanceId":209276,"modelId":230963}],"dockerImageVersionId":30840,"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":"2025-02-03T01:41:59.279862Z","iopub.execute_input":"2025-02-03T01:41:59.280079Z","iopub.status.idle":"2025-02-03T01:41:59.582498Z","shell.execute_reply.started":"2025-02-03T01:41:59.280058Z","shell.execute_reply":"2025-02-03T01:41:59.581785Z"},"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":"2025-02-03T01:41:59.583579Z","iopub.execute_input":"2025-02-03T01:41:59.583913Z","iopub.status.idle":"2025-02-03T01:42:13.169992Z","shell.execute_reply.started":"2025-02-03T01:41:59.583892Z","shell.execute_reply":"2025-02-03T01:42:13.169311Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import psutil\nprint(f\"Available Memory: {psutil.virtual_memory().available / 1e9:.2f} GB\")\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:13.171355Z","iopub.execute_input":"2025-02-03T01:42:13.171623Z","iopub.status.idle":"2025-02-03T01:42:13.176143Z","shell.execute_reply.started":"2025-02-03T01:42:13.171591Z","shell.execute_reply":"2025-02-03T01:42:13.175318Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!fallocate -l 4G /swapfile\n!chmod 600 /swapfile\n!mkswap /swapfile\n!swapon /swapfile\n!free -h  # ตรวจสอบ Swap ที่เพิ่ม\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:13.177516Z","iopub.execute_input":"2025-02-03T01:42:13.177800Z","iopub.status.idle":"2025-02-03T01:42:13.822900Z","shell.execute_reply.started":"2025-02-03T01:42:13.177772Z","shell.execute_reply":"2025-02-03T01:42:13.821817Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"!ls train","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":"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":"2025-02-03T01:42:13.824012Z","iopub.execute_input":"2025-02-03T01:42:13.824338Z","iopub.status.idle":"2025-02-03T01:42:14.769560Z","shell.execute_reply.started":"2025-02-03T01:42:13.824301Z","shell.execute_reply":"2025-02-03T01:42:14.768627Z"},"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":"2025-02-03T01:42:14.770450Z","iopub.execute_input":"2025-02-03T01:42:14.770736Z","iopub.status.idle":"2025-02-03T01:42:15.618517Z","shell.execute_reply.started":"2025-02-03T01:42:14.770713Z","shell.execute_reply":"2025-02-03T01:42:15.617571Z"},"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","metadata":{"execution":{"iopub.status.busy":"2025-02-03T01:42:15.619357Z","iopub.execute_input":"2025-02-03T01:42:15.619597Z","iopub.status.idle":"2025-02-03T01:42:27.129721Z","shell.execute_reply.started":"2025-02-03T01:42:15.619576Z","shell.execute_reply":"2025-02-03T01:42:27.128812Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from os import listdir\nfrom numpy import asarray, save\nfrom keras.preprocessing.image import load_img, img_to_array\nimport random\n\n# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n\n# สุ่มเลือกแค่ 50% ของไฟล์ทั้งหมด\nfiles = listdir(folder)\nrandom.shuffle(files)  # สุ่มลำดับไฟล์\nfiles = files[:len(files) // 2]  # เอาแค่ครึ่งเดียว\n\n# enumerate files in the directory\nfor file in files:\n    # determine class\n    output = 1.0 if file.startswith('dog') else 0.0\n\n    # load image\n    photo = load_img(folder + file, target_size=(100, 100))  # ลดขนาดรูปภาพ\n    photo = img_to_array(photo)\n\n    # store\n    photos.append(photo)\n    labels.append(output)\n\n# convert to a numpy arrays\nphotos = asarray(photos, dtype='float16')  # ใช้ float16 เพื่อลดขนาด\nlabels = asarray(labels, dtype='uint8')    # uint8 ใช้พื้นที่น้อยกว่า float\n\nprint(photos.shape, labels.shape)\n\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:27.131946Z","iopub.execute_input":"2025-02-03T01:42:27.132443Z","iopub.status.idle":"2025-02-03T01:42:43.090862Z","shell.execute_reply.started":"2025-02-03T01:42:27.132420Z","shell.execute_reply":"2025-02-03T01:42:43.089929Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n# # load dogs vs cats dataset, reshape and save to a new file\n# from os import listdir\n# from numpy import asarray\n# from numpy import save\n# from keras.preprocessing.image import load_img\n# from keras.preprocessing.image import img_to_array\n# # define location of dataset\n# folder = 'train/'\n# photos, labels = list(), list()\n# # enumerate files in the directory\n# for 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=(200, 200))\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\n# photos = asarray(photos)\n# labels = asarray(labels)\n# print(photos.shape, labels.shape)\n# # save the reshaped photos\n# save('dogs_vs_cats_photos.npy', photos)\n# save('dogs_vs_cats_labels.npy', labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:43.092330Z","iopub.execute_input":"2025-02-03T01:42:43.092642Z","iopub.status.idle":"2025-02-03T01:42:43.096296Z","shell.execute_reply.started":"2025-02-03T01:42:43.092619Z","shell.execute_reply":"2025-02-03T01:42:43.095448Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import psutil\nprint(f\"Available Memory: {psutil.virtual_memory().available / 1e9:.2f} GB\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:43.097254Z","iopub.execute_input":"2025-02-03T01:42:43.097553Z","iopub.status.idle":"2025-02-03T01:42:43.115759Z","shell.execute_reply.started":"2025-02-03T01:42:43.097524Z","shell.execute_reply":"2025-02-03T01:42:43.115150Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n# 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":"2025-02-03T01:42:43.116468Z","iopub.execute_input":"2025-02-03T01:42:43.116649Z","iopub.status.idle":"2025-02-03T01:42:43.318066Z","shell.execute_reply.started":"2025-02-03T01:42:43.116633Z","shell.execute_reply":"2025-02-03T01:42:43.317301Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Pre-Process Photos into Standard Directories**","metadata":{}},{"cell_type":"code","source":"\n# 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","metadata":{"execution":{"iopub.status.busy":"2025-02-03T01:42:43.319025Z","iopub.execute_input":"2025-02-03T01:42:43.319370Z","iopub.status.idle":"2025-02-03T01:42:43.323249Z","shell.execute_reply.started":"2025-02-03T01:42:43.319338Z","shell.execute_reply":"2025-02-03T01:42:43.322444Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Create directories\nimport os\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\nfor subdir in subdirs:\n    # Create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = os.path.join(dataset_home, subdir, labldir)\n        os.makedirs(newdir, exist_ok=True)\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:43.324134Z","iopub.execute_input":"2025-02-03T01:42:43.324423Z","iopub.status.idle":"2025-02-03T01:42:43.340127Z","shell.execute_reply.started":"2025-02-03T01:42:43.324391Z","shell.execute_reply":"2025-02-03T01:42:43.339342Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 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":"2025-02-03T01:42:43.341027Z","iopub.execute_input":"2025-02-03T01:42:43.341391Z","iopub.status.idle":"2025-02-03T01:42:45.603314Z","shell.execute_reply.started":"2025-02-03T01:42:43.341357Z","shell.execute_reply":"2025-02-03T01:42:45.602591Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"    !ls -l dataset_dogs_vs_cats/train/dogs | wc -l","metadata":{"execution":{"iopub.status.busy":"2025-02-03T01:42:45.604081Z","iopub.execute_input":"2025-02-03T01:42:45.604310Z","iopub.status.idle":"2025-02-03T01:42:45.860700Z","shell.execute_reply.started":"2025-02-03T01:42:45.604267Z","shell.execute_reply":"2025-02-03T01:42:45.859839Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2025-02-03T01:42:45.861695Z","iopub.execute_input":"2025-02-03T01:42:45.861920Z","iopub.status.idle":"2025-02-03T01:42:46.108225Z","shell.execute_reply.started":"2025-02-03T01:42:45.861902Z","shell.execute_reply":"2025-02-03T01:42:46.107208Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip install livelossplot","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:46.109174Z","iopub.execute_input":"2025-02-03T01:42:46.109432Z","iopub.status.idle":"2025-02-03T01:42:50.614953Z","shell.execute_reply.started":"2025-02-03T01:42:46.109411Z","shell.execute_reply":"2025-02-03T01:42:50.614084Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2025-02-03T01:42:50.615966Z","iopub.execute_input":"2025-02-03T01:42:50.616221Z","iopub.status.idle":"2025-02-03T01:42:50.630209Z","shell.execute_reply.started":"2025-02-03T01:42:50.616199Z","shell.execute_reply":"2025-02-03T01:42:50.629375Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"markdown","source":"# **Develop a Baseline CNN Model**","metadata":{}},{"cell_type":"code","source":"# นำเข้า Keras และ TensorFlow\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D\n\n# สร้างโมเดล Sequential\nmodel = Sequential()\n\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# แสดงโมเดล\nmodel.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:50.631170Z","iopub.execute_input":"2025-02-03T01:42:50.631463Z","iopub.status.idle":"2025-02-03T01:42:53.120170Z","shell.execute_reply.started":"2025-02-03T01:42:50.631432Z","shell.execute_reply":"2025-02-03T01:42:53.119344Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\nfrom tensorflow.keras.optimizers import SGD\n\n# define cnn model\ndef define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(224, 224, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(1, activation='sigmoid'))\n    # compile model\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\n# เรียกใช้ฟังก์ชันเพื่อสร้างโมเดล\nmodel = define_model()\n\n# แสดง summary ของโมเดล\nmodel.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:53.121022Z","iopub.execute_input":"2025-02-03T01:42:53.121264Z","iopub.status.idle":"2025-02-03T01:42:53.203236Z","shell.execute_reply.started":"2025-02-03T01:42:53.121244Z","shell.execute_reply":"2025-02-03T01:42:53.202575Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# create data generator\ndatagen = ImageDataGenerator(\n    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)\n\n# prepare iterator\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(224, 224))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(224, 224))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:53.204053Z","iopub.execute_input":"2025-02-03T01:42:53.204260Z","iopub.status.idle":"2025-02-03T01:42:54.075884Z","shell.execute_reply.started":"2025-02-03T01:42:53.204242Z","shell.execute_reply":"2025-02-03T01:42:54.075096Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras\n\n# fit model\nhistory = model.fit(train_it, \n                    steps_per_epoch=len(train_it), \n                    epochs=10, verbose=0, \n                    validation_data=test_it, \n                    validation_steps=len(test_it), \n                    callbacks=[PlotLossesKeras()]\n                   )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T01:42:54.076632Z","iopub.execute_input":"2025-02-03T01:42:54.077055Z","iopub.status.idle":"2025-02-03T02:05:38.750810Z","shell.execute_reply.started":"2025-02-03T01:42:54.077029Z","shell.execute_reply":"2025-02-03T02:05:38.750024Z"}},"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))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:05:38.754868Z","iopub.execute_input":"2025-02-03T02:05:38.755360Z","iopub.status.idle":"2025-02-03T02:06:47.956411Z","shell.execute_reply.started":"2025-02-03T02:05:38.755338Z","shell.execute_reply":"2025-02-03T02:06:47.955471Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# save model\nmodel.save('final_model.h5')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:06:47.958408Z","iopub.execute_input":"2025-02-03T02:06:47.958645Z","iopub.status.idle":"2025-02-03T02:06:48.611050Z","shell.execute_reply.started":"2025-02-03T02:06:47.958624Z","shell.execute_reply":"2025-02-03T02:06:48.610371Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.models import load_model\n\n# โหลดโมเดลจากไฟล์\nmodel = load_model('final_model.h5')\n\n# ใช้งานโมเดลที่โหลดมา\nmodel.summary()  # แสดงรายละเอียดของโมเดลที่โหลดมา\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:06:48.611815Z","iopub.execute_input":"2025-02-03T02:06:48.612045Z","iopub.status.idle":"2025-02-03T02:06:48.952994Z","shell.execute_reply.started":"2025-02-03T02:06:48.612025Z","shell.execute_reply":"2025-02-03T02:06:48.952362Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":">  **Load Model**","metadata":{}},{"cell_type":"code","source":"# Defining the model with a correct input shape (200, 200, 3)\ndef define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(200, 200, 3)))  # Adjust the input shape here\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu'))\n    model.add(Dense(1, activation='sigmoid'))  # Output layer for binary classification\n    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:06:48.953754Z","iopub.execute_input":"2025-02-03T02:06:48.954058Z","iopub.status.idle":"2025-02-03T02:06:48.958742Z","shell.execute_reply.started":"2025-02-03T02:06:48.954029Z","shell.execute_reply":"2025-02-03T02:06:48.957980Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from matplotlib import pyplot\ndef summarize_diagnostics(history):\n    pyplot.figure(figsize=(8, 6), dpi=150)\n    # plot loss\n    pyplot.subplot(211)\n    pyplot.title('Cross Entropy Loss')\n    pyplot.plot(history.history['loss'], color='blue', label='train')\n    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n    pyplot.show()\n    # plot accuracy\n    pyplot.subplot(212)\n    pyplot.title('Classification Accuracy')\n    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n    # save plot to file\n    #filename = sys.argv[0].split('/')[-1]\n    #pyplot.savefig(filename + '_plot.png')\n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:06:48.959421Z","iopub.execute_input":"2025-02-03T02:06:48.959723Z","iopub.status.idle":"2025-02-03T02:06:48.974869Z","shell.execute_reply.started":"2025-02-03T02:06:48.959690Z","shell.execute_reply":"2025-02-03T02:06:48.974071Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as pyplot\n\n\n# run the test harness for evaluating a model\ndef run_test_harness():\n    # define model\n    model = define_model()\n    # create data generator with validation split\n    datagen = ImageDataGenerator(rescale=1.0/255.0, validation_split=0.2)  # 20% สำหรับ validation\n    \n    # prepare iterators\n    train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n        class_mode='binary', batch_size=64, target_size=(200, 200), subset='training')  # ใช้ข้อมูล train\n    \n    validation_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n        class_mode='binary', batch_size=64, target_size=(200, 200), subset='validation')  # ใช้ข้อมูล validation จาก train\n    \n    # fit model\n    history = model.fit(train_it, \n                    steps_per_epoch=len(train_it), \n                    epochs=20, \n                    verbose=0, \n                    validation_data=validation_it, \n                    validation_steps=len(validation_it), \n                    callbacks=[PlotLossesKeras()]\n                   )\n    \n    # evaluate model on test data\n    test_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n        class_mode='binary', batch_size=64, target_size=(200, 200))\n    \n    _, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\n    print('> %.3f' % (acc * 100.0))\n\n    # learning curves\n    summarize_diagnostics(history)\n\n# entry point, run the test harness\nrun_test_harness()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:06:48.975738Z","iopub.execute_input":"2025-02-03T02:06:48.976007Z","iopub.status.idle":"2025-02-03T02:11:48.528102Z","shell.execute_reply.started":"2025-02-03T02:06:48.975981Z","shell.execute_reply":"2025-02-03T02:11:48.527321Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# save model\nmodel.save('final_model.h5')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:11:48.529043Z","iopub.execute_input":"2025-02-03T02:11:48.529465Z","iopub.status.idle":"2025-02-03T02:11:49.098209Z","shell.execute_reply.started":"2025-02-03T02:11:48.529441Z","shell.execute_reply":"2025-02-03T02:11:49.097215Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\ndataset_path = \"/kaggle/input/\"\n\nfor root, dirs, files in os.walk(dataset_path):\n    for file in files:\n        print(os.path.join(root, file))  # แสดงที่อยู่ไฟล์ทั้งหมด\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:11:49.098939Z","iopub.execute_input":"2025-02-03T02:11:49.099151Z","iopub.status.idle":"2025-02-03T02:11:49.116332Z","shell.execute_reply.started":"2025-02-03T02:11:49.099133Z","shell.execute_reply":"2025-02-03T02:11:49.115482Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.models import load_model\n\nmodel_path = \"/kaggle/input/modelsdogandcat/keras/default/1/final_model.h5\"\nmodel = load_model(model_path)\n\nmodel.summary()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:11:49.117159Z","iopub.execute_input":"2025-02-03T02:11:49.117437Z","iopub.status.idle":"2025-02-03T02:11:51.670940Z","shell.execute_reply.started":"2025-02-03T02:11:49.117415Z","shell.execute_reply":"2025-02-03T02:11:51.670257Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **One Block VGG Model**","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\nfrom tensorflow.keras.optimizers import SGD\n\n# define cnn model\ndef define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(1, activation='sigmoid'))\n    \n    # compile model\n    opt = SGD(learning_rate=0.001, momentum=0.9)  # ใช้ learning_rate แทน lr\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model\n\n# 🔥 ทดสอบสร้างโมเดล\nmodel = define_model()\nprint(model.summary())  # แสดงโครงสร้างของโมเดล\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:11:51.671836Z","iopub.execute_input":"2025-02-03T02:11:51.672065Z","iopub.status.idle":"2025-02-03T02:11:51.727684Z","shell.execute_reply.started":"2025-02-03T02:11:51.672046Z","shell.execute_reply":"2025-02-03T02:11:51.727002Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as pyplot\n\n\n# run the test harness for evaluating a model\ndef run_test_harness():\n    # define model\n    model = define_model()\n    # create data generator with validation split\n    datagen = ImageDataGenerator(rescale=1.0/255.0, validation_split=0.2)  # 20% สำหรับ validation\n    \n    # prepare iterators\n    train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n        class_mode='binary', batch_size=64, target_size=(200, 200), subset='training')  # ใช้ข้อมูล train\n    \n    validation_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n        class_mode='binary', batch_size=64, target_size=(200, 200), subset='validation')  # ใช้ข้อมูล validation จาก train\n    \n    # fit model\n    history = model.fit(train_it, \n                    steps_per_epoch=len(train_it), \n                    epochs=20, \n                    verbose=0, \n                    validation_data=validation_it, \n                    validation_steps=len(validation_it), \n                    callbacks=[PlotLossesKeras()]\n                   )\n    \n    # evaluate model on test data\n    test_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n        class_mode='binary', batch_size=64, target_size=(200, 200))\n    \n    _, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\n    print('> %.3f' % (acc * 100.0))\n\n# entry point, run the test harness\nrun_test_harness()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:11:51.728417Z","iopub.execute_input":"2025-02-03T02:11:51.728630Z","iopub.status.idle":"2025-02-03T02:16:48.107110Z","shell.execute_reply.started":"2025-02-03T02:11:51.728605Z","shell.execute_reply":"2025-02-03T02:16:48.106143Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from matplotlib import pyplot\ndef summarize_diagnostics(history):\n    pyplot.figure(figsize=(8, 6), dpi=150)\n    # plot loss\n    pyplot.subplot(211)\n    pyplot.title('Cross Entropy Loss')\n    pyplot.plot(history.history['loss'], color='blue', label='train')\n    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n    pyplot.show()\n    # plot accuracy\n    pyplot.subplot(212)\n    pyplot.title('Classification Accuracy')\n    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n    # save plot to file\n    #filename = sys.argv[0].split('/')[-1]\n    #pyplot.savefig(filename + '_plot.png')\n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:16:48.108382Z","iopub.execute_input":"2025-02-03T02:16:48.108721Z","iopub.status.idle":"2025-02-03T02:16:48.114017Z","shell.execute_reply.started":"2025-02-03T02:16:48.108690Z","shell.execute_reply":"2025-02-03T02:16:48.113049Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\nfrom tensorflow.keras.optimizers import SGD\n\n# define cnn model\ndef define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(1, activation='sigmoid'))\n    \n    # compile model with correct parameter name\n    opt = SGD(learning_rate=0.001, momentum=0.9)  # ใช้ learning_rate แทน lr\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:16:48.121132Z","iopub.execute_input":"2025-02-03T02:16:48.121346Z","iopub.status.idle":"2025-02-03T02:16:48.135884Z","shell.execute_reply.started":"2025-02-03T02:16:48.121327Z","shell.execute_reply":"2025-02-03T02:16:48.135065Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as pyplot\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# define model\nmodel = define_model()\n# create data generator with validation split\ndatagen = ImageDataGenerator(rescale=1.0/255.0, validation_split=0.2)  # 20% สำหรับ validation\n\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(200, 200), subset='training')  # ใช้ข้อมูล train\n\nvalidation_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(200, 200), subset='validation')  # ใช้ข้อมูล validation จาก train\n\n# fit model\nhistory = model.fit(train_it, \n                steps_per_epoch=len(train_it), \n                epochs=20, \n                verbose=0, \n                validation_data=validation_it, \n                validation_steps=len(validation_it), \n                callbacks=[PlotLossesKeras()]\n               )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:16:48.136718Z","iopub.execute_input":"2025-02-03T02:16:48.136932Z","iopub.status.idle":"2025-02-03T02:21:28.115811Z","shell.execute_reply.started":"2025-02-03T02:16:48.136913Z","shell.execute_reply":"2025-02-03T02:21:28.115041Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model on test data\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))\n\n_, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:21:28.116746Z","iopub.execute_input":"2025-02-03T02:21:28.116980Z","iopub.status.idle":"2025-02-03T02:21:37.375813Z","shell.execute_reply.started":"2025-02-03T02:21:28.116960Z","shell.execute_reply":"2025-02-03T02:21:37.375031Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(1, activation='sigmoid'))\n    # compile model\n    opt = SGD(learning_rate=0.001, momentum=0.9)  # ใช้ learning_rate แทน lr\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:21:37.376694Z","iopub.execute_input":"2025-02-03T02:21:37.376918Z","iopub.status.idle":"2025-02-03T02:21:37.382871Z","shell.execute_reply.started":"2025-02-03T02:21:37.376899Z","shell.execute_reply":"2025-02-03T02:21:37.381979Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as pyplot\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# define model\nmodel = define_model()\n# create data generator with validation split\ndatagen = ImageDataGenerator(rescale=1.0/255.0, validation_split=0.2)  # 20% สำหรับ validation\n\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(200, 200), subset='training')  # ใช้ข้อมูล train\n\nvalidation_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(200, 200), subset='validation')  # ใช้ข้อมูล validation จาก train\n\n# fit model\nhistory = model.fit(train_it, \n                steps_per_epoch=len(train_it), \n                epochs=20, \n                verbose=0, \n                validation_data=validation_it, \n                validation_steps=len(validation_it), \n                callbacks=[PlotLossesKeras()]\n               )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:21:37.383743Z","iopub.execute_input":"2025-02-03T02:21:37.384047Z","iopub.status.idle":"2025-02-03T02:26:27.693662Z","shell.execute_reply.started":"2025-02-03T02:21:37.384016Z","shell.execute_reply":"2025-02-03T02:26:27.692760Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model on test data\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))\n\n_, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:26:27.694587Z","iopub.execute_input":"2025-02-03T02:26:27.694889Z","iopub.status.idle":"2025-02-03T02:26:37.386178Z","shell.execute_reply.started":"2025-02-03T02:26:27.694859Z","shell.execute_reply":"2025-02-03T02:26:37.385423Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Dropout Regularization**","metadata":{}},{"cell_type":"code","source":"from keras.layers import Dropout\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout\nfrom keras.optimizers import SGD\n\n# 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(Dropout(0.2))\n\tmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Dropout(0.2))\n\tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Dropout(0.2))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dropout(0.5))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(learning_rate=0.001, momentum=0.9)  # ใช้ learning_rate แทน lr\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model\n\nmodel = define_model()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:26:37.387161Z","iopub.execute_input":"2025-02-03T02:26:37.387506Z","iopub.status.idle":"2025-02-03T02:26:37.497323Z","shell.execute_reply.started":"2025-02-03T02:26:37.387475Z","shell.execute_reply":"2025-02-03T02:26:37.496688Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nhistory = model.fit(train_it, \n                steps_per_epoch=len(train_it), \n                epochs=20, \n                verbose=0, \n                validation_data=validation_it, \n                validation_steps=len(validation_it), \n                callbacks=[PlotLossesKeras()]\n               )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:26:37.498013Z","iopub.execute_input":"2025-02-03T02:26:37.498218Z","iopub.status.idle":"2025-02-03T02:31:24.392725Z","shell.execute_reply.started":"2025-02-03T02:26:37.498200Z","shell.execute_reply":"2025-02-03T02:31:24.391754Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model on test data\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))\n\n_, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:31:24.393911Z","iopub.execute_input":"2025-02-03T02:31:24.394259Z","iopub.status.idle":"2025-02-03T02:31:33.687205Z","shell.execute_reply.started":"2025-02-03T02:31:24.394225Z","shell.execute_reply":"2025-02-03T02:31:33.686391Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Image Data Augmentation**","metadata":{}},{"cell_type":"code","source":"import sys\nfrom matplotlib import pyplot\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\nfrom keras.optimizers import SGD\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# define cnn model\ndef define_model():\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(1, activation='sigmoid'))\n    # compile model\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:31:33.688008Z","iopub.execute_input":"2025-02-03T02:31:33.688322Z","iopub.status.idle":"2025-02-03T02:31:33.694690Z","shell.execute_reply.started":"2025-02-03T02:31:33.688266Z","shell.execute_reply":"2025-02-03T02:31:33.693934Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# run the test harness for evaluating a model\ndef run_test_harness():\n    # define model\n    model = define_model()\n    # create data generators\n    train_datagen = ImageDataGenerator(rescale=1.0/255.0,\n                                      width_shift_range=0.1, height_shift_range=0.1, horizontal_flip=True)\n    test_datagen = ImageDataGenerator(rescale=1.0/255.0)\n    # prepare iterators\n    train_it = train_datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n                                                 class_mode='binary', batch_size=64, target_size=(200, 200))\n    test_it = test_datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n                                               class_mode='binary', batch_size=64, target_size=(200, 200))\n\n        # fit model\n    history = model.fit(train_it, \n                    steps_per_epoch=len(train_it), \n                    epochs=50, \n                    verbose=1, \n                    validation_data=test_it, \n                    validation_steps=len(test_it), \n                    callbacks=[PlotLossesKeras()]\n                   )\n    \n    # evaluate model\n    _, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\n    print('> %.3f' % (acc * 100.0))\n    # learning curves\n    summarize_diagnostics(history)\n\n# entry point, run the test harness\nrun_test_harness()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2025-02-03T02:31:33.695740Z","iopub.execute_input":"2025-02-03T02:31:33.696049Z","execution_failed":"2025-02-03T03:52:31.339Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Explore Transfer Learning**","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.applications.vgg16 import VGG16\nfrom tensorflow.keras.applications.xception import Xception\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, Flatten\nfrom tensorflow.keras.optimizers import SGD\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.401Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\nmodel = VGG16(\n    include_top=False,\n    input_shape=(224, 224, 3)\n    )\nprint(model.summary())\n#model = Xception(include_top=False, input_shape=(299, 299, 3))","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.402Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# mark loaded layers as not trainable\nfor index, layer in enumerate(model.layers[1:15]):  # ข้าม InputLayer\n    print(index, layer.name, layer.output.shape)\n    layer.trainable = False\n    \nfor index, layer in enumerate(model.layers[15:]):\n    print(index, layer.name, layer.output.shape)\n    layer.trainable = True\n","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.403Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model.layers[-1].output","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.404Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# add new classifier layers\nflat1 = Flatten()(model.layers[-1].output)\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n# define new model\nmy_model = Model(inputs=model.inputs, outputs=output)\n# compile model\nopt = SGD(learning_rate=0.0001, momentum=0.9)\nmy_model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\nmy_model.summary()\n","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.405Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications import VGG16\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Flatten, Dense\nfrom tensorflow.keras.optimizers import SGD\n\n# โหลดโมเดล VGG16 โดยไม่รวมเลเยอร์ fully connected\nbase_model = VGG16(weights='imagenet', include_top=False, input_shape=(200, 200, 3))\n\n# เอาต์พุตจากโมเดล VGG16\nvgg16_output = base_model.output\n\n# เพิ่มเลเยอร์การจำแนกใหม่\nflat1 = Flatten()(vgg16_output)  # แฟลตเอาต์พุต\nclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\noutput = Dense(1, activation='sigmoid')(class1)\n\n# สร้างโมเดลใหม่โดยเชื่อมต่ออินพุตจาก base_model และเอาต์พุตที่เราเพิ่ม\nmy_model = Model(inputs=base_model.input, outputs=output)\n\n# คอมไพล์โมเดล\nopt = SGD(learning_rate=0.0001, momentum=0.9)\nmy_model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\n# สรุปโครงสร้างของโมเดล\nmy_model.summary()\n","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.405Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nhistory = my_model.fit(train_it, \n                       validation_data=test_it, \n                       epochs=2, verbose=1,\n                       callbacks=[PlotLossesKeras()])\n\n# evaluate model\n_, acc = my_model.evaluate(test_it, verbose=1)\nprint('> %.3f' % (acc * 100.0))\n\n# learning curves\nsummarize_diagnostics(history)\n\n# Save the best model\nbest_model = 'vgg16_model.hdf5'\nmy_model.save(best_model)\n","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.406Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **How to Finalize the Model and Make Predictions**","metadata":{}},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\n# create directories\ndataset_home = 'finalize_dogs_vs_cats/'\n# create label subdirectories\nlabeldirs = ['dogs/', 'cats/']\nfor labldir in labeldirs:\n\tnewdir = dataset_home + labldir\n\tmakedirs(newdir, exist_ok=True)\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.407Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Save Final Model**","metadata":{}},{"cell_type":"code","source":"# prepare iterator\ntrain_it = datagen.flow_from_directory('finalize_dogs_vs_cats/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.410Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmy_model.fit(train_it, steps_per_epoch=len(train_it), epochs=10, verbose=2)","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.410Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# save model\nmy_model.save('final_model.h5')","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.412Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# **Make Prediction**","metadata":{}},{"cell_type":"code","source":"import os\n\n# ระบุโฟลเดอร์ที่มีรูปภาพ\nfolder = 'train/'  # เปลี่ยนเป็น path ของ dataset จริง\n\n# ดึงรายชื่อไฟล์ทั้งหมดในโฟลเดอร์\nimage_files = [f for f in os.listdir(folder) if f.lower().endswith(('.png', '.jpg', '.jpeg'))]\n\nif len(image_files) == 0:\n    print(\"ไม่มีไฟล์ภาพในโฟลเดอร์ที่กำหนด\")\nelse:\n    # ใช้ภาพแรกในลิสต์ (หรือจะสุ่มก็ได้)\n    first_image = image_files[0]\n    print(f'ชื่อไฟล์ภาพแรก: {first_image}')\n\n    # ถ้าต้องการสุ่มเลือกภาพใดก็ได้\n    import random\n    random_image = random.choice(image_files)\n    print(f'ชื่อไฟล์ที่เลือกแบบสุ่ม: {random_image}')\n","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.414Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# make a prediction for a new image.\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array\nfrom keras.models import load_model\n \n# load and prepare the image\ndef load_image(filename):\n\t# load the image\n\timg = load_img(filename, target_size=(200, 200))\n\t# convert to array\n\timg = img_to_array(img)\n\t# reshape into a single sample with 3 channels\n\timg = img.reshape(1, 200, 200, 3)\n\t# center pixel data\n\timg = img.astype('float32')\n\timg = img - [123.68, 116.779, 103.939]\n\treturn img\n \n# load an image and predict the class\ndef run_example():\n\t# load the image\n\timg = load_image('train/dog.2168.jpg')\n\t# load model\n\tmodel = load_model('final_model.h5')\n\t# predict the class\n\tresult = model.predict(img)\n\tprint(result[0])\n \n# entry point, run the example\nrun_example()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.416Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# make a prediction for a new image.\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array\nfrom keras.models import load_model\n \n# load and prepare the image\ndef load_image(filename):\n\t# load the image\n\timg = load_img(filename, target_size=(200, 200))\n\t# convert to array\n\timg = img_to_array(img)\n\t# reshape into a single sample with 3 channels\n\timg = img.reshape(1, 200, 200, 3)\n\t# center pixel data\n\timg = img.astype('float32')\n\timg = img - [123.68, 116.779, 103.939]\n\treturn img\n \n# load an image and predict the class\ndef run_example():\n\t# load the image\n\timg = load_image('train/cat.3599.jpg')\n\t# load model\n\tmodel = load_model('final_model.h5')\n\t# predict the class\n\tresult = model.predict(img)\n\tprint(result[0])\n \n# entry point, run the example\nrun_example()","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.417Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom keras.preprocessing.image import load_img, img_to_array\nfrom keras.models import load_model\n\n# โหลดและเตรียมภาพ\ndef load_image(filename):\n    img = load_img(filename, target_size=(200, 200))  # โหลดภาพและปรับขนาด\n    img_array = img_to_array(img)  # แปลงเป็น array\n    img_array = img_array.reshape(1, 200, 200, 3)  # ปรับ shape ให้ตรงกับโมเดล\n    img_array = img_array.astype('float32')  # แปลงเป็น float\n    img_array = img_array - [123.68, 116.779, 103.939]  # Normalize (VGG16)\n    return img, img_array\n\n# โหลดภาพและพยากรณ์คลาส\ndef run_example():\n    filename = 'train/cat.11451.jpg'  # เปลี่ยนเป็นภาพที่ต้องการ\n    true_label = \"Cat\" if \"cat\" in filename else \"Dog\"  # หาคำตอบที่แท้จริงจากชื่อไฟล์\n\n    # โหลดภาพ\n    img, img_array = load_image(filename)\n    \n    # โหลดโมเดล\n    model = load_model('final_model.h5')\n\n    # ทำนายคลาส\n    result = model.predict(img_array)[0][0]\n    predicted_label = \"Cat\" if result < 0.5 else \"Dog\"  # ตั้งค่าขีดจำกัด (0.5)\n\n    # แสดงภาพและผลลัพธ์\n    plt.imshow(img)\n    plt.axis(\"off\")\n    plt.title(f\"Predicted: {predicted_label}\\nActual: {true_label}\\nConfidence: {result:.4f}\")\n    plt.show()\n\n# รันตัวอย่าง\nrun_example()\n","metadata":{"trusted":true,"execution":{"execution_failed":"2025-02-03T03:52:31.419Z"}},"outputs":[],"execution_count":null}]}