{"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":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"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\n# import os\n# for 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":"2026-10-03T18:13:56.683338Z","iopub.execute_input":"2026-10-03T18:13:56.683621Z","iopub.status.idle":"2026-10-03T18:13:57.029207Z","shell.execute_reply.started":"2026-10-03T18:13:56.683589Z","shell.execute_reply":"2026-10-03T18:13:57.028471Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:13:57.031276Z","iopub.execute_input":"2026-10-03T18:13:57.032126Z","iopub.status.idle":"2026-10-03T18:13:58.161053Z","shell.execute_reply.started":"2026-10-03T18:13:57.032099Z","shell.execute_reply":"2026-10-03T18:13:58.159909Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:13:58.162668Z","iopub.execute_input":"2026-10-03T18:13:58.162968Z","iopub.status.idle":"2026-10-03T18:13:59.276234Z","shell.execute_reply.started":"2026-10-03T18:13:58.162941Z","shell.execute_reply":"2026-10-03T18:13:59.275003Z"}},"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":"2026-10-03T18:13:59.277671Z","iopub.execute_input":"2026-10-03T18:13:59.278046Z","iopub.status.idle":"2026-10-03T18:14:09.565032Z","shell.execute_reply.started":"2026-10-03T18:13:59.278021Z","shell.execute_reply":"2026-10-03T18:14:09.563863Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:09.566378Z","iopub.execute_input":"2026-10-03T18:14:09.567302Z","iopub.status.idle":"2026-10-03T18:14:10.588994Z","shell.execute_reply.started":"2026-10-03T18:14:09.567275Z","shell.execute_reply":"2026-10-03T18:14:10.58806Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:10.590549Z","iopub.execute_input":"2026-10-03T18:14:10.590894Z","iopub.status.idle":"2026-10-03T18:14:11.571864Z","shell.execute_reply.started":"2026-10-03T18:14:10.59086Z","shell.execute_reply":"2026-10-03T18:14:11.570929Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:11.574691Z","iopub.execute_input":"2026-10-03T18:14:11.575056Z","iopub.status.idle":"2026-10-03T18:14:12.648629Z","shell.execute_reply.started":"2026-10-03T18:14:11.57503Z","shell.execute_reply":"2026-10-03T18:14:12.647389Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:12.650128Z","iopub.execute_input":"2026-10-03T18:14:12.650553Z","iopub.status.idle":"2026-10-03T18:14:13.736551Z","shell.execute_reply.started":"2026-10-03T18:14:12.650527Z","shell.execute_reply":"2026-10-03T18:14:13.735608Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:13.737866Z","iopub.execute_input":"2026-10-03T18:14:13.738307Z","iopub.status.idle":"2026-10-03T18:14:13.742501Z","shell.execute_reply.started":"2026-10-03T18:14:13.738281Z","shell.execute_reply":"2026-10-03T18:14:13.741632Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:13.743636Z","iopub.execute_input":"2026-10-03T18:14:13.743906Z","iopub.status.idle":"2026-10-03T18:14:14.834069Z","shell.execute_reply.started":"2026-10-03T18:14:13.743883Z","shell.execute_reply":"2026-10-03T18:14:14.832759Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:14.835713Z","iopub.execute_input":"2026-10-03T18:14:14.836143Z","iopub.status.idle":"2026-10-03T18:14:15.939585Z","shell.execute_reply.started":"2026-10-03T18:14:14.836115Z","shell.execute_reply":"2026-10-03T18:14:15.938253Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\n# from matplotlib import pyplot as plt\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":"2026-10-03T18:14:15.941393Z","iopub.execute_input":"2026-10-03T18:14:15.941732Z","iopub.status.idle":"2026-10-03T18:14:18.407373Z","shell.execute_reply.started":"2026-10-03T18:14:15.941703Z","shell.execute_reply":"2026-10-03T18:14:18.406455Z"},"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":"2026-10-03T18:14:18.408658Z","iopub.execute_input":"2026-10-03T18:14:18.408898Z","iopub.status.idle":"2026-10-03T18:14:19.377871Z","shell.execute_reply.started":"2026-10-03T18:14:18.408876Z","shell.execute_reply":"2026-10-03T18:14:19.377014Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:19.379306Z","iopub.execute_input":"2026-10-03T18:14:19.380032Z","iopub.status.idle":"2026-10-03T18:14:20.374749Z","shell.execute_reply.started":"2026-10-03T18:14:19.379997Z","shell.execute_reply":"2026-10-03T18:14:20.37346Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow\nprint(f\"{tensorflow.__version__=}\")\n\nimport keras\nprint(f\"{keras.__version__=}\")\n\nimport tensorflow.keras\nprint(f\"{tensorflow.__version__=}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:20.376339Z","iopub.execute_input":"2026-10-03T18:14:20.376887Z","iopub.status.idle":"2026-10-03T18:14:32.439211Z","shell.execute_reply.started":"2026-10-03T18:14:20.376856Z","shell.execute_reply":"2026-10-03T18:14:32.438159Z"}},"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":"2026-10-03T18:14:32.440442Z","iopub.execute_input":"2026-10-03T18:14:32.441087Z","iopub.status.idle":"2026-10-03T18:14:32.447363Z","shell.execute_reply.started":"2026-10-03T18:14:32.441052Z","shell.execute_reply":"2026-10-03T18:14:32.445945Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# 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=(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\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":{"execution":{"iopub.status.busy":"2024-01-27T03:36:15.416611Z","iopub.execute_input":"2024-01-27T03:36:15.417128Z","iopub.status.idle":"2024-01-27T03:36:38.886396Z","shell.execute_reply.started":"2024-01-27T03:36:15.417101Z","shell.execute_reply":"2024-01-27T03:36:38.883149Z"}}},{"cell_type":"markdown","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:38.88711Z","iopub.status.idle":"2024-01-27T03:36:38.887458Z","shell.execute_reply.started":"2024-01-27T03:36:38.887281Z","shell.execute_reply":"2024-01-27T03:36:38.887296Z"}}},{"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","metadata":{"execution":{"iopub.status.busy":"2026-10-03T18:14:32.448414Z","iopub.execute_input":"2026-10-03T18:14:32.448727Z","iopub.status.idle":"2026-10-03T18:14:32.473257Z","shell.execute_reply.started":"2026-10-03T18:14:32.448703Z","shell.execute_reply":"2026-10-03T18:14:32.472433Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/'] #test==>validation\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir       \n        makedirs(newdir, exist_ok=True)\n        print(newdir)","metadata":{"execution":{"iopub.status.busy":"2026-10-03T18:14:32.474556Z","iopub.execute_input":"2026-10-03T18:14:32.47482Z","iopub.status.idle":"2026-10-03T18:14:32.487296Z","shell.execute_reply.started":"2026-10-03T18:14:32.474797Z","shell.execute_reply":"2026-10-03T18:14:32.486255Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:32.488361Z","iopub.execute_input":"2026-10-03T18:14:32.489456Z","iopub.status.idle":"2026-10-03T18:14:33.49103Z","shell.execute_reply.started":"2026-10-03T18:14:32.489433Z","shell.execute_reply":"2026-10-03T18:14:33.490095Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:33.492508Z","iopub.execute_input":"2026-10-03T18:14:33.493169Z","iopub.status.idle":"2026-10-03T18:14:34.525642Z","shell.execute_reply.started":"2026-10-03T18:14:33.493144Z","shell.execute_reply":"2026-10-03T18:14:34.52473Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:34.52704Z","iopub.execute_input":"2026-10-03T18:14:34.527359Z","iopub.status.idle":"2026-10-03T18:14:35.53854Z","shell.execute_reply.started":"2026-10-03T18:14:34.527332Z","shell.execute_reply":"2026-10-03T18:14:35.537608Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1337)\n# define ratio of pictures to use for validation\nval_ratio = 0.25 #changable\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\n\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":{"execution":{"iopub.status.busy":"2026-10-03T18:14:35.54431Z","iopub.execute_input":"2026-10-03T18:14:35.544672Z","iopub.status.idle":"2026-10-03T18:14:37.437475Z","shell.execute_reply.started":"2026-10-03T18:14:35.544645Z","shell.execute_reply":"2026-10-03T18:14:37.436605Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:37.438535Z","iopub.execute_input":"2026-10-03T18:14:37.43885Z","iopub.status.idle":"2026-10-03T18:14:37.443359Z","shell.execute_reply.started":"2026-10-03T18:14:37.43881Z","shell.execute_reply":"2026-10-03T18:14:37.442483Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-10-03T18:14:37.444559Z","iopub.execute_input":"2026-10-03T18:14:37.444963Z","iopub.status.idle":"2026-10-03T18:14:39.635822Z","shell.execute_reply.started":"2026-10-03T18:14:37.444939Z","shell.execute_reply":"2026-10-03T18:14:39.63463Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#validation set\n!ls -l dataset_dogs_vs_cats/test/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/test/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-10-03T18:14:39.637534Z","iopub.execute_input":"2026-10-03T18:14:39.63852Z","iopub.status.idle":"2026-10-03T18:14:41.676478Z","shell.execute_reply.started":"2026-10-03T18:14:39.638492Z","shell.execute_reply":"2026-10-03T18:14:41.675238Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-10-03T18:14:41.677901Z","iopub.execute_input":"2026-10-03T18:14:41.678339Z","iopub.status.idle":"2026-10-03T18:14:51.704613Z","shell.execute_reply.started":"2026-10-03T18:14:41.678312Z","shell.execute_reply":"2026-10-03T18:14:51.703535Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-10-03T18:14:51.705968Z","iopub.execute_input":"2026-10-03T18:14:51.706373Z","iopub.status.idle":"2026-10-03T18:14:51.723631Z","shell.execute_reply.started":"2026-10-03T18:14:51.706347Z","shell.execute_reply":"2026-10-03T18:14:51.722641Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:51.724747Z","iopub.execute_input":"2026-10-03T18:14:51.725068Z","iopub.status.idle":"2026-10-03T18:14:51.728952Z","shell.execute_reply.started":"2026-10-03T18:14:51.725039Z","shell.execute_reply":"2026-10-03T18:14:51.728243Z"}},"outputs":[],"execution_count":null},{"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":"2026-10-03T18:14:51.730303Z","iopub.execute_input":"2026-10-03T18:14:51.730629Z","iopub.status.idle":"2026-10-03T18:14:51.740702Z","shell.execute_reply.started":"2026-10-03T18:14:51.730596Z","shell.execute_reply":"2026-10-03T18:14:51.739644Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\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":"2026-10-03T18:14:51.741893Z","iopub.execute_input":"2026-10-03T18:14:51.742867Z","iopub.status.idle":"2026-10-03T18:14:51.751368Z","shell.execute_reply.started":"2026-10-03T18:14:51.74282Z","shell.execute_reply":"2026-10-03T18:14:51.75059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:51.752355Z","iopub.execute_input":"2026-10-03T18:14:51.752654Z","iopub.status.idle":"2026-10-03T18:14:53.835923Z","shell.execute_reply.started":"2026-10-03T18:14:51.752622Z","shell.execute_reply":"2026-10-03T18:14:53.835124Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot diagnostic learning curves\ndef summarize_diagnostics(history):\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    # 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    \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":"2026-10-03T18:14:53.838704Z","iopub.execute_input":"2026-10-03T18:14:53.839369Z","iopub.status.idle":"2026-10-03T18:14:53.845Z","shell.execute_reply.started":"2026-10-03T18:14:53.839344Z","shell.execute_reply":"2026-10-03T18:14:53.844006Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(2, activation='softmax'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:53.846169Z","iopub.execute_input":"2026-10-03T18:14:53.846505Z","iopub.status.idle":"2026-10-03T18:14:53.93395Z","shell.execute_reply.started":"2026-10-03T18:14:53.846475Z","shell.execute_reply":"2026-10-03T18:14:53.93299Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:53.935021Z","iopub.execute_input":"2026-10-03T18:14:53.93541Z","iopub.status.idle":"2026-10-03T18:14:54.032299Z","shell.execute_reply.started":"2026-10-03T18:14:53.935383Z","shell.execute_reply":"2026-10-03T18:14:54.030646Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx1 = Conv2D(64, (3, 3), activation='relu')(x1)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:54.033591Z","iopub.execute_input":"2026-10-03T18:14:54.034026Z","iopub.status.idle":"2026-10-03T18:14:54.138875Z","shell.execute_reply.started":"2026-10-03T18:14:54.033987Z","shell.execute_reply":"2026-10-03T18:14:54.135275Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:54.139907Z","iopub.execute_input":"2026-10-03T18:14:54.140128Z","iopub.status.idle":"2026-10-03T18:14:54.146659Z","shell.execute_reply.started":"2026-10-03T18:14:54.140108Z","shell.execute_reply":"2026-10-03T18:14:54.145817Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:54.147908Z","iopub.execute_input":"2026-10-03T18:14:54.148386Z","iopub.status.idle":"2026-10-03T18:14:55.223131Z","shell.execute_reply.started":"2026-10-03T18:14:54.148362Z","shell.execute_reply":"2026-10-03T18:14:55.221822Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = 224\nBATCH_SIZE = 64\nEPOCHS = 30","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:55.224656Z","iopub.execute_input":"2026-10-03T18:14:55.225078Z","iopub.status.idle":"2026-10-03T18:14:55.22988Z","shell.execute_reply.started":"2026-10-03T18:14:55.22505Z","shell.execute_reply":"2026-10-03T18:14:55.228931Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True,\n    validation_split=0.2  # Defined here at initialization\n)\n\ntrain_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/train'\n\n# 2. Extract the training subset (80% of data)\ntrain_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='training',     # Explicitly request the training partition\n    shuffle=True           # Stochastic sampling is standard for training\n)\n\n# 3. Extract the validation subset (20% of data)\nval_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='validation',   # Explicitly request the validation partition\n    shuffle=False          # Disable shuffle to maintain index alignment for metrics\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:14:55.230966Z","iopub.execute_input":"2026-10-03T18:14:55.231222Z","iopub.status.idle":"2026-10-03T18:15:28.151392Z","shell.execute_reply.started":"2026-10-03T18:14:55.231155Z","shell.execute_reply":"2026-10-03T18:15:28.1504Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_it), len(train_it.classes), train_it.classes[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:28.152628Z","iopub.execute_input":"2026-10-03T18:15:28.153045Z","iopub.status.idle":"2026-10-03T18:15:28.160221Z","shell.execute_reply.started":"2026-10-03T18:15:28.153008Z","shell.execute_reply":"2026-10-03T18:15:28.15942Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(val_it), len(val_it.classes), val_it.classes[-10:]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:28.161881Z","iopub.execute_input":"2026-10-03T18:15:28.162227Z","iopub.status.idle":"2026-10-03T18:15:28.183683Z","shell.execute_reply.started":"2026-10-03T18:15:28.16216Z","shell.execute_reply":"2026-10-03T18:15:28.182873Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\n# model_1.reset_states()\n# history_1 = model_1.fit(\n#     train_it,\n#     steps_per_epoch=len(train_it),\n#     validation_data=val_it,\n#     validation_steps=len(val_it),\n#     epochs=EPOCHS,\n#     verbose=2,\n#     callbacks = [PlotLossesKeras()]\n#     )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:28.184871Z","iopub.execute_input":"2026-10-03T18:15:28.185078Z","iopub.status.idle":"2026-10-03T18:15:28.191342Z","shell.execute_reply.started":"2026-10-03T18:15:28.185058Z","shell.execute_reply":"2026-10-03T18:15:28.190446Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:28.192338Z","iopub.execute_input":"2026-10-03T18:15:28.19264Z","iopub.status.idle":"2026-10-03T18:15:28.204125Z","shell.execute_reply.started":"2026-10-03T18:15:28.192618Z","shell.execute_reply":"2026-10-03T18:15:28.203246Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n# _, acc = model_1.evaluate(val_it, steps=len(val_it), verbose=1)\n# print('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:28.205378Z","iopub.execute_input":"2026-10-03T18:15:28.205688Z","iopub.status.idle":"2026-10-03T18:15:28.216654Z","shell.execute_reply.started":"2026-10-03T18:15:28.205651Z","shell.execute_reply":"2026-10-03T18:15:28.215537Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Create test datagenerator from 308-456 Dogs vs Cats ","metadata":{}},{"cell_type":"code","source":"ls /kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:28.217987Z","iopub.execute_input":"2026-10-03T18:15:28.218647Z","iopub.status.idle":"2026-10-03T18:15:29.240822Z","shell.execute_reply.started":"2026-10-03T18:15:28.218621Z","shell.execute_reply":"2026-10-03T18:15:29.239607Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport pandas as pd\nfrom glob import glob\n\n# Define the image folder path\ntest_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test'\n\nprint(test_path)\n# # List all .jpg files in the directory (adjust the pattern if needed)\n# image_files = glob(os.path.join(image_folder, '*.jpg'))\n\n# # Check if images were found\n# if not image_files:\n#     print(\"No images found. Please verify the directory and file extensions.\")\n    \n# # Create a DataFrame with the file paths\n# test_df = pd.DataFrame({'filename': image_files})\n\n# If your use-case doesn't require labels (for example, during testing), you can leave out the label column.\n# Otherwise, if you need a dummy label, you can add one:\n# df['class'] = 'dummy_label'\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.242422Z","iopub.execute_input":"2026-10-03T18:15:29.242848Z","iopub.status.idle":"2026-10-03T18:15:29.248653Z","shell.execute_reply.started":"2026-10-03T18:15:29.242814Z","shell.execute_reply":"2026-10-03T18:15:29.24759Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.249699Z","iopub.execute_input":"2026-10-03T18:15:29.250016Z","iopub.status.idle":"2026-10-03T18:15:29.269051Z","shell.execute_reply.started":"2026-10-03T18:15:29.249995Z","shell.execute_reply":"2026-10-03T18:15:29.268039Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.270309Z","iopub.execute_input":"2026-10-03T18:15:29.270854Z","iopub.status.idle":"2026-10-03T18:15:29.27714Z","shell.execute_reply.started":"2026-10-03T18:15:29.270826Z","shell.execute_reply":"2026-10-03T18:15:29.276421Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.278263Z","iopub.execute_input":"2026-10-03T18:15:29.278622Z","iopub.status.idle":"2026-10-03T18:15:29.288584Z","shell.execute_reply.started":"2026-10-03T18:15:29.278598Z","shell.execute_reply":"2026-10-03T18:15:29.287745Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.289417Z","iopub.execute_input":"2026-10-03T18:15:29.289613Z","iopub.status.idle":"2026-10-03T18:15:29.3008Z","shell.execute_reply.started":"2026-10-03T18:15:29.289595Z","shell.execute_reply":"2026-10-03T18:15:29.299871Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.302051Z","iopub.execute_input":"2026-10-03T18:15:29.302878Z","iopub.status.idle":"2026-10-03T18:15:29.311919Z","shell.execute_reply.started":"2026-10-03T18:15:29.302853Z","shell.execute_reply":"2026-10-03T18:15:29.311065Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # Create test data generator\n# from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# # Initialize your ImageDataGenerator (modify parameters as needed)\n# datagen_test = ImageDataGenerator(rescale=1./255,\n#                                  vertical_flip=True)\n\n# # Create the data generator using the DataFrame\n# test_it = datagen_test.flow_from_dataframe(\n#     dataframe=test_df,\n#     x_col='filename',\n#     y_col=None,            # No labels for testing, so set to None\n#     target_size=IMAGE_SIZE,\n#     batch_size=BATCH_SIZE,\n#     class_mode=None,       # Since there are no labels\n#     # shuffle=True,         # Usually testing data should not be shuffled\n#     shuffle=False,\n# )\n\n# type(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.313242Z","iopub.execute_input":"2026-10-03T18:15:29.313556Z","iopub.status.idle":"2026-10-03T18:15:29.320622Z","shell.execute_reply.started":"2026-10-03T18:15:29.313526Z","shell.execute_reply":"2026-10-03T18:15:29.319925Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.321992Z","iopub.execute_input":"2026-10-03T18:15:29.322317Z","iopub.status.idle":"2026-10-03T18:15:29.336336Z","shell.execute_reply.started":"2026-10-03T18:15:29.322286Z","shell.execute_reply":"2026-10-03T18:15:29.335509Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True\n)\ntest_it = test_datagen.flow_from_directory(\n    test_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:29.337599Z","iopub.execute_input":"2026-10-03T18:15:29.337955Z","iopub.status.idle":"2026-10-03T18:15:38.836808Z","shell.execute_reply.started":"2026-10-03T18:15:29.337924Z","shell.execute_reply":"2026-10-03T18:15:38.835815Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_exmaple(images, labels):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(labels[i]))  # Fixed: set_title instead of title\n            # ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n            ax.axis(\"on\")\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:38.838128Z","iopub.execute_input":"2026-10-03T18:15:38.838488Z","iopub.status.idle":"2026-10-03T18:15:38.844917Z","shell.execute_reply.started":"2026-10-03T18:15:38.838456Z","shell.execute_reply":"2026-10-03T18:15:38.843917Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_images, train_labels = train_it.__next__()\nprint(train_images.shape, len(train_labels))\nplot_exmaple(train_images, train_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:38.845954Z","iopub.execute_input":"2026-10-03T18:15:38.846517Z","iopub.status.idle":"2026-10-03T18:15:48.191869Z","shell.execute_reply.started":"2026-10-03T18:15:38.846493Z","shell.execute_reply":"2026-10-03T18:15:48.190574Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_images, val_labels = val_it.__next__()\nval_images.shape\nplot_exmaple(val_images, val_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:48.193337Z","iopub.execute_input":"2026-10-03T18:15:48.193634Z","iopub.status.idle":"2026-10-03T18:15:57.570219Z","shell.execute_reply.started":"2026-10-03T18:15:48.193609Z","shell.execute_reply":"2026-10-03T18:15:57.569057Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_exmaple_test(images, indices):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(indices[i]))  # ตั้งค่า title ด้วย index จาก list/array indices\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:57.571996Z","iopub.execute_input":"2026-10-03T18:15:57.572441Z","iopub.status.idle":"2026-10-03T18:15:57.579812Z","shell.execute_reply.started":"2026-10-03T18:15:57.572396Z","shell.execute_reply":"2026-10-03T18:15:57.578776Z"},"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images, test_labels = test_it.__next__()  # หรือ next(test_it)\nprint(f\"{test_images.shape=}, {test_labels.shape}\")\n\n# สร้าง list เลขดัชนีตามจำนวนภาพที่มี\nindices = list(range(len(test_images)))\n\nplot_exmaple(test_images, test_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:15:57.580986Z","iopub.execute_input":"2026-10-03T18:15:57.581299Z","iopub.status.idle":"2026-10-03T18:16:06.851329Z","shell.execute_reply.started":"2026-10-03T18:15:57.581271Z","shell.execute_reply":"2026-10-03T18:16:06.849748Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import numpy as np\n\n\n# # 1. สุ่ม index มา 10 ตัวจากชุดข้อมูล\n# sample_indices = np.random.choice(len(test_images), size=10, replace=False)\n# sample_images = test_images[sample_indices]\n\n# # 2. Predict \n# predictions = model_1.predict(sample_images)\n# predicted_classes = np.argmax(predictions, axis=1)  # ดึง class ที่ได้คะแนนสูงสุด\n\n# # 3. แสดงผล 10 ภาพ (ปรับเป็น grid 2x5)\n# fig, axes = plt.subplots(2, 5, figsize=(15, 6))\n# axes = axes.flatten()\n\n# for i, ax in enumerate(axes):\n#     ax.imshow(sample_images[i])\n#     # แสดง Index เดิม และ Class ที่ทายได้\n#     ax.set_title(f\"Idx: {sample_indices[i]}\\nPred: {predicted_classes[i]}\")\n#     ax.axis(\"off\")\n\n# plt.tight_layout()\n# plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:06.85306Z","iopub.execute_input":"2026-10-03T18:16:06.853436Z","iopub.status.idle":"2026-10-03T18:16:06.858417Z","shell.execute_reply.started":"2026-10-03T18:16:06.853403Z","shell.execute_reply":"2026-10-03T18:16:06.857551Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 2026-09-13\n# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:06.859562Z","iopub.execute_input":"2026-10-03T18:16:06.859882Z","iopub.status.idle":"2026-10-03T18:16:06.879327Z","shell.execute_reply.started":"2026-10-03T18:16:06.859853Z","shell.execute_reply":"2026-10-03T18:16:06.878088Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#เพื่อให้มันฝึก     เพื่อวัดผลการทำการ  เพื่อทดสอบจริง\nid(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:06.880642Z","iopub.execute_input":"2026-10-03T18:16:06.881028Z","iopub.status.idle":"2026-10-03T18:16:06.892877Z","shell.execute_reply.started":"2026-10-03T18:16:06.880993Z","shell.execute_reply":"2026-10-03T18:16:06.89217Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Create transfer learning model for VGG16\nimport 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\n\n# Hyperparameter => changable\nIMAGE_SIZE = 224\nBATCH_SIE = 64\nEPOCHS = 20\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\n\t# mark loaded layers as not trainable\n\tfor layer in model.layers:\n\t\tlayer.trainable = False\n\t# add new classifier layers\n\tflat1 = Flatten()(model.layers[-1].output)\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\toutput = Dense(1, activation='sigmoid')(class1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\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\n\nvgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:06.894262Z","iopub.execute_input":"2026-10-03T18:16:06.895007Z","iopub.status.idle":"2026-10-03T18:16:07.663756Z","shell.execute_reply.started":"2026-10-03T18:16:06.894983Z","shell.execute_reply":"2026-10-03T18:16:07.662604Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_vgg16_top = VGG16(include_top=True, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\nmodel_vgg16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:07.665236Z","iopub.execute_input":"2026-10-03T18:16:07.666019Z","iopub.status.idle":"2026-10-03T18:16:12.730232Z","shell.execute_reply.started":"2026-10-03T18:16:07.665982Z","shell.execute_reply":"2026-10-03T18:16:12.728334Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_16_feature_extractor = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\nmodel_16_feature_extractor.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:12.731656Z","iopub.execute_input":"2026-10-03T18:16:12.731889Z","iopub.status.idle":"2026-10-03T18:16:13.10461Z","shell.execute_reply.started":"2026-10-03T18:16:12.731869Z","shell.execute_reply":"2026-10-03T18:16:13.103325Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n\t\tprint(index, layer.trainable, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.10576Z","iopub.execute_input":"2026-10-03T18:16:13.10612Z","iopub.status.idle":"2026-10-03T18:16:13.113244Z","shell.execute_reply.started":"2026-10-03T18:16:13.106087Z","shell.execute_reply":"2026-10-03T18:16:13.112211Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n    if index <= 15:\n        layer.trainable = False\n\nfor index, layer in enumerate(model_16_feature_extractor.layers):\n    print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.121145Z","iopub.execute_input":"2026-10-03T18:16:13.121438Z","iopub.status.idle":"2026-10-03T18:16:13.127225Z","shell.execute_reply.started":"2026-10-03T18:16:13.121415Z","shell.execute_reply":"2026-10-03T18:16:13.12626Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.128923Z","iopub.execute_input":"2026-10-03T18:16:13.129323Z","iopub.status.idle":"2026-10-03T18:16:13.141952Z","shell.execute_reply.started":"2026-10-03T18:16:13.129286Z","shell.execute_reply":"2026-10-03T18:16:13.14111Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# use functional API\nflat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\nprint(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.143239Z","iopub.execute_input":"2026-10-03T18:16:13.143582Z","iopub.status.idle":"2026-10-03T18:16:13.159325Z","shell.execute_reply.started":"2026-10-03T18:16:13.143559Z","shell.execute_reply":"2026-10-03T18:16:13.158073Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\nprint(class1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.160616Z","iopub.execute_input":"2026-10-03T18:16:13.161597Z","iopub.status.idle":"2026-10-03T18:16:13.177544Z","shell.execute_reply.started":"2026-10-03T18:16:13.161566Z","shell.execute_reply":"2026-10-03T18:16:13.176635Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.178744Z","iopub.execute_input":"2026-10-03T18:16:13.179332Z","iopub.status.idle":"2026-10-03T18:16:13.197474Z","shell.execute_reply.started":"2026-10-03T18:16:13.179305Z","shell.execute_reply":"2026-10-03T18:16:13.196486Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define new model to be trained\nmodel_vgg16 = Model(inputs=model_16_feature_extractor.inputs, outputs=output)\n# compile model\nopt = SGD(lr=0.001, momentum=0.9)\n\nmodel_vgg16.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.19867Z","iopub.execute_input":"2026-10-03T18:16:13.199077Z","iopub.status.idle":"2026-10-03T18:16:13.214496Z","shell.execute_reply.started":"2026-10-03T18:16:13.19905Z","shell.execute_reply":"2026-10-03T18:16:13.213703Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.215731Z","iopub.execute_input":"2026-10-03T18:16:13.21638Z","iopub.status.idle":"2026-10-03T18:16:13.268234Z","shell.execute_reply.started":"2026-10-03T18:16:13.216348Z","shell.execute_reply":"2026-10-03T18:16:13.267231Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.269374Z","iopub.execute_input":"2026-10-03T18:16:13.270648Z","iopub.status.idle":"2026-10-03T18:16:13.276088Z","shell.execute_reply.started":"2026-10-03T18:16:13.270622Z","shell.execute_reply":"2026-10-03T18:16:13.275138Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_vgg16 = define_model_vgg16()\nprint(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.277324Z","iopub.execute_input":"2026-10-03T18:16:13.277585Z","iopub.status.idle":"2026-10-03T18:16:13.631568Z","shell.execute_reply.started":"2026-10-03T18:16:13.277563Z","shell.execute_reply":"2026-10-03T18:16:13.630736Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nimport tensorflow as tf\n\n# 1. Verify that TensorFlow can communicate with the GPU hardware\nphysical_devices = tf.config.list_physical_devices('GPU')\nprint(f\"Hardware status: {len(physical_devices)} GPU(s) detected.\")\n\nif len(physical_devices) > 0:\n    # Optional but highly recommended: Prevent TF from pre-allocating 100% of VRAM\n    try:\n        tf.config.experimental.set_memory_growth(physical_devices[0], True)\n    except Exception as e:\n        print(f\"Memory growth configuration failed: {e}\")\n\n    # 2. Explicitly bind the execution to the primary GPU\n    with tf.device('/GPU:0'):\n        \n        print(f\"Model ID: {id(model_vgg16)}\")\n        \n        # Note: reset_states() is strictly for stateful RNNs (LSTMs/GRUs). \n        # For a feed-forward CNN like VGG16, this method has no effect and can be removed.\n        # model_vgg16.reset_states() \n        \n        model_vgg16_history = model_vgg16.fit(\n            train_it, \n            steps_per_epoch=len(train_it),\n            validation_data=val_it,\n            validation_steps=len(val_it),\n            epochs=15, \n            verbose=1,\n            callbacks=[PlotLossesKeras()]\n        )\nelse:\n    print(\"WARNING: No GPU detected. Execution will proceed on the CPU, which will be significantly slower.\")\n    # Fallback to standard execution\n    model_vgg16_history = model_vgg16.fit(\n        train_it, \n        steps_per_epoch=len(train_it),\n        validation_data=val_it,\n        validation_steps=len(val_it),\n        epochs=15, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:16:13.632563Z","iopub.execute_input":"2026-10-03T18:16:13.633092Z","iopub.status.idle":"2026-10-03T18:41:07.319729Z","shell.execute_reply.started":"2026-10-03T18:16:13.633064Z","shell.execute_reply":"2026-10-03T18:41:07.318981Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"%who","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:47:33.374453Z","iopub.execute_input":"2026-10-03T18:47:33.374764Z","iopub.status.idle":"2026-10-03T18:47:33.380628Z","shell.execute_reply.started":"2026-10-03T18:47:33.374742Z","shell.execute_reply":"2026-10-03T18:47:33.379636Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ==========================================\n# ส่วนที่เพิ่มใหม่สำหรับการทำ Fine-Tuning (ปรับชื่อตัวแปรให้ตรงกับโค้ดของคุณ)\n# ==========================================\n\n# สมมติว่าโมเดลคุณชื่อ model ถ้าตอนแรกรันไม่ผ่านให้เปลี่ยนบรรทัดนี้เป็น model = model_vgg16\nactive_model = model_vgg16 if 'model_vgg16' in globals() else model\n\n# 1. ตั้งค่าให้ทุกเลเยอร์แก้ไขได้ก่อน\nactive_model.trainable = True\n\n# 2. ไล่ล็อค (Freeze) เฉพาะเลเยอร์ส่วนแรกๆ ของ VGG16 (Block 1 ถึง 4) \nfor layer in active_model.layers:\n    if layer.name.startswith(('block1', 'block2', 'block3', 'block4')):\n        layer.trainable = False\n    else:\n        layer.trainable = True\n\nprint(\"ตั้งค่า Fine-Tuning สำเร็จ! เตรียมคอมไพล์โมเดล...\")\n\n# 3. คอมไพล์โมเดลใหม่ ***ต้องใช้ Learning Rate ต่ำๆ เช่น 1e-5***\nfrom tensorflow.keras.optimizers import Adam\n    \nactive_model.compile(\n    optimizer=Adam(learning_rate=1e-5), \n    loss='binary_crossentropy', # ถ้า Error ตรงนี้ ให้แก้เป็น 'categorical_crossentropy'\n    metrics=['accuracy']\n)\n    \n# 4. สั่งเทรนต่อจากเดิม (Fine-Tune)\nfine_tune_epochs = 10 # จำนวนรอบที่อยากเทรนเพิ่ม\n    \nprint(\"\\nเริ่มการทำ Fine-tuning...\")\nhistory_fine = active_model.fit(\n    train_it, # แก้เป็น train_it ตามรายชื่อตัวแปรของคุณ\n    epochs=fine_tune_epochs, \n    validation_data=val_it # แก้เป็น val_it ตามรายชื่อตัวแปรของคุณ\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T18:48:28.531864Z","iopub.execute_input":"2026-10-03T18:48:28.532199Z","iopub.status.idle":"2026-10-03T19:06:07.112546Z","shell.execute_reply.started":"2026-10-03T18:48:28.532158Z","shell.execute_reply":"2026-10-03T19:06:07.111518Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:06:52.706858Z","iopub.execute_input":"2026-10-03T19:06:52.707831Z","iopub.status.idle":"2026-10-03T19:06:52.987946Z","shell.execute_reply.started":"2026-10-03T19:06:52.707797Z","shell.execute_reply":"2026-10-03T19:06:52.987238Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_vgg16.evaluate(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:06:54.31471Z","iopub.execute_input":"2026-10-03T19:06:54.315633Z","iopub.status.idle":"2026-10-03T19:07:13.876527Z","shell.execute_reply.started":"2026-10-03T19:06:54.315591Z","shell.execute_reply":"2026-10-03T19:07:13.875694Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model for the test set\n_, test_acc = model_vgg16.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (test_acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:07:13.877967Z","iopub.execute_input":"2026-10-03T19:07:13.878342Z","iopub.status.idle":"2026-10-03T19:11:29.406729Z","shell.execute_reply.started":"2026-10-03T19:07:13.878318Z","shell.execute_reply":"2026-10-03T19:11:29.405848Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\n# 1. Reset the generator state to ensure alignment from index 0\ntest_it.reset()\n\n# 2. Extract the ordered ground truth labels from the generator\ny_true = test_it.classes\nprint(y_true.shape)\n\n# 3. Execute the forward pass over the entire test dataset\n# Calculate exact steps to prevent infinite looping or partial evaluation\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobabilities = model_vgg16.predict(test_it, steps=steps, verbose=1).squeeze()\nprint(probabilities.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:11:29.409345Z","iopub.execute_input":"2026-10-03T19:11:29.409858Z","iopub.status.idle":"2026-10-03T19:12:02.218064Z","shell.execute_reply.started":"2026-10-03T19:11:29.409831Z","shell.execute_reply":"2026-10-03T19:12:02.217096Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 4. Discretize continuous logistic probabilities into binary class predictions\ny_pred = (probabilities > 0.5).astype(int)\nprint(y_pred.shape)\n\n# 5. Extract dynamic class labels mapping (e.g., {'cats': 0, 'dogs': 1})\n# This ensures the report correctly maps index 0 and 1 to your string labels\ntarget_names = list(test_it.class_indices.keys())\n\n# 6. Compute and output the classification report\nreport = classification_report(y_true, y_pred, target_names=target_names)\nprint(report)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:12:02.219826Z","iopub.execute_input":"2026-10-03T19:12:02.220417Z","iopub.status.idle":"2026-10-03T19:12:02.25598Z","shell.execute_reply.started":"2026-10-03T19:12:02.220389Z","shell.execute_reply":"2026-10-03T19:12:02.25522Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Predict\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# 1. Aggregate sufficient samples from the iterator\nimages_list = []\nlabels_list = []\n\n# Fetch 2 batches (2 * 64 = 128 samples) to ensure we have pool > 100\nfor _ in range(2):\n    batch_images, batch_labels = next(test_it)\n    images_list.append(batch_images)\n    labels_list.append(batch_labels)\n\n# Concatenate into a single tensor\nall_images = np.concatenate(images_list, axis=0)\nall_labels = np.concatenate(labels_list, axis=0)\n\n# 2. Stochastically sample 100 unique indices\nnp.random.seed(42) # For reproducibility\nrandom_indices = np.random.choice(all_images.shape[0], size=100, replace=False)\n\nsample_images = all_images[random_indices]\nsample_labels = all_labels[random_indices]\n\n# 3. Execute the forward pass\n# Squeeze is used to convert shape (100, 1) to (100,)\nprobabilities = model_vgg16.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:12:02.257119Z","iopub.execute_input":"2026-10-03T19:12:02.257793Z","iopub.status.idle":"2026-10-03T19:12:09.720267Z","shell.execute_reply.started":"2026-10-03T19:12:02.25775Z","shell.execute_reply":"2026-10-03T19:12:09.719238Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Initialize a 10x10 matrix visualization\nfig, axes = plt.subplots(10, 10, figsize=(20, 22))\naxes = axes.flatten()\n\nfor i in range(100):\n    ax = axes[i]\n    \n    # Isolate image tensor. \n    # NOTE: If your VGG16 preprocessor applies mean-centering (caffe style) \n    # instead of standard [0,1] scaling, you must reverse it here for correct plt.imshow() rendering.\n    # We assume standard [0, 1] or [0, 255] spatial tensors below.\n    img = sample_images[i]\n    if img.max() > 1.0 or img.min() < 0:\n        # Simple normalization for display purposes\n        img = (img - img.min()) / (img.max() - img.min())\n        \n    ax.imshow(img)\n    ax.axis('off')\n    \n    # Extract structural labels\n    gt_class = class_mapping[int(sample_labels[i])]\n    pred_class = class_mapping[predictions[i]]\n    prob = probabilities[i]\n    \n    # Apply conditional color coding (Green for True Positives/Negatives, Red for False Positives/Negatives)\n    text_color = 'darkgreen' if gt_class == pred_class else 'darkred'\n    \n    title_str = f\"GT: {gt_class}\\nPred: {pred_class}\\nProb: {prob:.3f}\"\n    ax.set_title(title_str, color=text_color, fontsize=9, pad=4)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T19:12:09.721536Z","iopub.execute_input":"2026-10-03T19:12:09.722168Z","iopub.status.idle":"2026-10-03T19:12:17.883734Z","shell.execute_reply.started":"2026-10-03T19:12:09.722133Z","shell.execute_reply":"2026-10-03T19:12:17.881918Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.980765Z","iopub.status.idle":"2026-09-12T14:09:21.981271Z","shell.execute_reply.started":"2026-09-12T14:09:21.981026Z","shell.execute_reply":"2026-09-12T14:09:21.98105Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\nfrom keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom keras.models import Model\nfrom keras.optimizers import Adam\n\ndef define_model_inceptionv3():\n    base_model = InceptionV3(include_top=False, input_shape=(299, 299, 3))\n    \n    # Freeze เลเยอร์ช่วงแรก Unfreeze ช่วงท้าย (เลเยอร์ 249 เป็นต้นไป)\n    for layer in base_model.layers[:249]:\n        layer.trainable = False\n    for layer in base_model.layers[249:]:\n        layer.trainable = True\n        \n    x = base_model.output\n    x = GlobalAveragePooling2D()(x)\n    x = Dense(256, activation='relu', kernel_initializer='he_uniform')(x)\n    x = Dropout(0.4)(x)\n    \n    # แก้ไขจุดนี้: ปรับเป็น 1 Node (Sigmoid) เพื่อรองรับ Shape (None, 1)\n    output = Dense(1, activation='sigmoid')(x)\n    \n    model = Model(inputs=base_model.inputs, outputs=output)\n    \n    # แก้ไขจุดนี้: ปรับเป็น binary_crossentropy\n    opt = Adam(learning_rate=1e-4)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model\n\nmodel_inceptionv3 = define_model_inceptionv3()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T14:54:52.7555Z","iopub.execute_input":"2026-09-19T14:54:52.756298Z","iopub.status.idle":"2026-09-19T14:54:55.487563Z","shell.execute_reply.started":"2026-09-19T14:54:52.756262Z","shell.execute_reply":"2026-09-19T14:54:55.486713Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\nmodel_inceptionv3.summary()","metadata":{"execution":{"iopub.status.busy":"2026-09-19T14:55:21.995212Z","iopub.execute_input":"2026-09-19T14:55:21.995546Z","iopub.status.idle":"2026-09-19T14:55:25.087905Z","shell.execute_reply.started":"2026-09-19T14:55:21.995522Z","shell.execute_reply":"2026-09-19T14:55:25.086849Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras import backend as K\n\ntrainable_params = int(np.sum([K.count_params(w) for w in model_inceptionv3.trainable_weights]))\nprint(trainable_params)\n","metadata":{"trusted":true,"scrolled":true,"execution":{"iopub.status.busy":"2026-09-19T14:56:17.405263Z","iopub.execute_input":"2026-09-19T14:56:17.406397Z","iopub.status.idle":"2026-09-19T14:56:17.413608Z","shell.execute_reply.started":"2026-09-19T14:56:17.40636Z","shell.execute_reply":"2026-09-19T14:56:17.412615Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\nfor w in model_inceptionv3.trainable_weights:\n    print(w.name, K.count_params(w))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T14:56:26.495015Z","iopub.execute_input":"2026-09-19T14:56:26.495655Z","iopub.status.idle":"2026-09-19T14:56:26.502748Z","shell.execute_reply.started":"2026-09-19T14:56:26.495626Z","shell.execute_reply":"2026-09-19T14:56:26.50165Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\n# ลบ model_inceptionv3.reset_states() ออก\n# เพิ่ม Callbacks ปรับ Learning Rate และหยุดเมื่อกราฟนิ่งเพื่อป้องกัน Overfitting\ncustom_callbacks = [\n    PlotLossesKeras(),\n    ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=2, min_lr=1e-6, verbose=1),\n    EarlyStopping(monitor='val_accuracy', patience=5, restore_best_weights=True)\n]\n\n# fit model\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=20, # ปรับเพิ่มเป็น 20 epochs\n    verbose=1,\n    callbacks=custom_callbacks\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T14:56:35.37945Z","iopub.execute_input":"2026-09-19T14:56:35.38028Z","iopub.status.idle":"2026-09-19T15:16:50.208716Z","shell.execute_reply.started":"2026-09-19T14:56:35.380245Z","shell.execute_reply":"2026-09-19T15:16:50.207884Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_images_with_labels(images, labels, train_log, set_label, save=False):\n    \"\"\"\n    Plots a grid of images with their corresponding labels and saves the figure.\n    \n    Args:\n    - images (list or np.array): List of images to be displayed.\n    - labels (np.array): Array of one-hot encoded labels.\n    - train_log (str): The directory or log name to save the plot.\n    - set_label (str): The specific set label (e.g., \"train\", \"validation\", etc.).\n    - config (dict): Configuration dictionary containing image dimensions.\n    \n    Returns:\n    - None: Displays and saves the plot.\n    \"\"\"\n    # Convert one-hot encoded labels to class indices\n    class_indices = labels\n\n    # Create subplots\n    fig, axes = plt.subplots(3, 4, figsize=(14, 10), dpi=120)\n    axes = axes.flatten()\n\n    for img, label_idx, ax in zip(images, class_indices, axes):\n        # Undo any preprocessing (like rescaling for pre-trained models)\n        if np.max(img) == 1:\n            img = img * 255\n\n        # Display the image\n        img_shape = (224, 224, 3)\n        ax.imshow(img.astype(\"uint8\"))\n        # ax.imshow(img)\n\n        # Set the title to the corresponding class label\n        ax.set_title(f\"Label: {label_idx}\", fontsize=18)\n        ax.axis('on')\n\n    # Set the overall title for the figure\n    plot_title = f\"{train_log}-{set_label}\"\n    plt.suptitle(plot_title, fontsize=18)\n\n    # Show the plot\n    plt.show()\n\n    # Save the figure\n    if save:\n        plot_file = os.path.join(train_log, f\"{plot_title}.png\")\n        fig.savefig(plot_file, dpi=120)\n        print(f'Saved {plot_file}')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T15:17:29.018726Z","iopub.execute_input":"2026-09-19T15:17:29.019541Z","iopub.status.idle":"2026-09-19T15:17:29.027437Z","shell.execute_reply.started":"2026-09-19T15:17:29.019507Z","shell.execute_reply":"2026-09-19T15:17:29.026314Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.993271Z","iopub.status.idle":"2026-09-12T14:09:21.993619Z","shell.execute_reply.started":"2026-09-12T14:09:21.993474Z","shell.execute_reply":"2026-09-12T14:09:21.993489Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.995318Z","iopub.status.idle":"2026-09-12T14:09:21.995645Z","shell.execute_reply.started":"2026-09-12T14:09:21.995499Z","shell.execute_reply":"2026-09-12T14:09:21.995514Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # mark loaded layers as not trainable\n# for index, layer in enumerate(model.layers[:15]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = False\n    \n# for index, layer in enumerate(model.layers[15:]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.996782Z","iopub.status.idle":"2026-09-12T14:09:21.997163Z","shell.execute_reply.started":"2026-09-12T14:09:21.997018Z","shell.execute_reply":"2026-09-12T14:09:21.997034Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_inceptionv3.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\n# summarize_diagnostics(history)\n\n# best_model = 'vgg16_model.hdf5'\n# my_model.save(best_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-13T03:51:29.796468Z","iopub.execute_input":"2026-09-13T03:51:29.796781Z","iopub.status.idle":"2026-09-13T03:51:30.967284Z","shell.execute_reply.started":"2026-09-13T03:51:29.796759Z","shell.execute_reply":"2026-09-13T03:51:30.966045Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. แตกข้อมูล tuple ออกเป็น รูปภาพ (images) และ เลเบล (labels)\nimages, labels = test_it.__next__()\n\n# 2. เรียกดูขนาดของอาร์เรย์รูปภาพได้ทันที\nprint(images.shape)  # ผลลัพธ์จะเป็น (batch_size, height, width, channels) เช่น (32, 299, 299, 3)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T15:20:42.653117Z","iopub.execute_input":"2026-09-19T15:20:42.653619Z","iopub.status.idle":"2026-09-19T15:20:42.955131Z","shell.execute_reply.started":"2026-09-19T15:20:42.653581Z","shell.execute_reply":"2026-09-19T15:20:42.954112Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 5 first img: 1, 0, 1, 1, 0\nimages_to_predict = images[:5]\nimages_to_predict.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T15:22:14.674442Z","iopub.execute_input":"2026-09-19T15:22:14.675393Z","iopub.status.idle":"2026-09-19T15:22:14.681709Z","shell.execute_reply.started":"2026-09-19T15:22:14.675361Z","shell.execute_reply":"2026-09-19T15:22:14.680643Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprint(probs)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T15:22:27.589837Z","iopub.execute_input":"2026-09-19T15:22:27.590221Z","iopub.status.idle":"2026-09-19T15:22:27.707206Z","shell.execute_reply.started":"2026-09-19T15:22:27.59019Z","shell.execute_reply":"2026-09-19T15:22:27.705829Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# ResNet50","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.applications import ResNet50V2\nfrom tensorflow.keras import layers, models, optimizers\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n\n# --- 1. สร้างโครงสร้างโมเดล ---\ndef define_model_resnet50v2(input_shape=(224, 224, 3)):\n    base_model = ResNet50V2(\n        include_top=False, \n        weights='imagenet', \n        input_shape=input_shape\n    )\n    \n    # สเต็ปแรก: Freeze เลเยอร์ทั้งหมดของ Base Model\n    base_model.trainable = False\n    \n    inputs = layers.Input(shape=input_shape)\n    x = base_model(inputs, training=False)\n    \n    x = layers.GlobalAveragePooling2D()(x)\n    x = layers.BatchNormalization()(x) # ช่วยให้การเรียนรู้เสถียรยิ่งขึ้น\n    x = layers.Dense(256, activation='relu', kernel_initializer='he_uniform')(x)\n    x = layers.Dropout(0.4)(x) # ช่วยป้องกัน Overfitting\n    \n    outputs = layers.Dense(1, activation='sigmoid')(x)\n    \n    model = models.Model(inputs=inputs, outputs=outputs)\n    return model, base_model\n\nmodel_resnet, base_model = define_model_resnet50v2()\n\n# --- Callbacks ---\ncustom_callbacks = [\n    PlotLossesKeras(),\n    ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=2, min_lr=1e-7, verbose=1),\n    EarlyStopping(monitor='val_accuracy', patience=5, restore_best_weights=True)\n]\n\n# ==========================================\n# Phase 1: Warmup Training (เทรนเฉพาะ Classifier Head)\n# ==========================================\nprint(\"--- Phase 1: Warmup Training ---\")\nmodel_resnet.compile(\n    optimizer=optimizers.Adam(learning_rate=1e-3),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\nhistory_phase1 = model_resnet.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=5,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)\n\n# ==========================================\n# Phase 2: Fine-Tuning (ปลดล็อก เลเยอร์ท้ายๆ เพื่อดัน Accuracy ทะลุ 0.97)\n# ==========================================\nprint(\"--- Phase 2: Fine-Tuning ---\")\nbase_model.trainable = True\n\n# Unfreeze เฉพาะ 40 เลเยอร์สุดท้ายของ ResNet50V2\nfor layer in base_model.layers[:-40]:\n    layer.trainable = False\n\n# Compile ใหม่ด้วย Learning Rate ต่ำมาก\nmodel_resnet.compile(\n    optimizer=optimizers.Adam(learning_rate=1e-5),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\nhistory_resnet50 = model_resnet.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=15,\n    verbose=1,\n    callbacks=custom_callbacks\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T15:49:46.389038Z","iopub.execute_input":"2026-09-19T15:49:46.389752Z","iopub.status.idle":"2026-09-19T16:12:46.785186Z","shell.execute_reply.started":"2026-09-19T15:49:46.38972Z","shell.execute_reply":"2026-09-19T16:12:46.783804Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-19T15:26:42.703868Z","iopub.execute_input":"2026-09-19T15:26:42.704926Z","iopub.status.idle":"2026-09-19T15:49:03.447333Z","shell.execute_reply.started":"2026-09-19T15:26:42.704888Z","shell.execute_reply":"2026-09-19T15:49:03.445171Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}