{"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":"2026-09-18T12:15:59.895499Z","iopub.execute_input":"2026-09-18T12:15:59.896255Z","iopub.status.idle":"2026-09-18T12:15:59.901066Z","shell.execute_reply.started":"2026-09-18T12:15:59.896215Z","shell.execute_reply":"2026-09-18T12:15:59.900026Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T12:16:00.746348Z","iopub.execute_input":"2026-09-18T12:16:00.747431Z","iopub.status.idle":"2026-09-18T12:16:01.829288Z","shell.execute_reply.started":"2026-09-18T12:16:00.747400Z","shell.execute_reply":"2026-09-18T12:16:01.828157Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:02.802170Z","iopub.execute_input":"2026-09-18T07:05:02.802447Z","iopub.status.idle":"2026-09-18T07:05:03.893128Z","shell.execute_reply.started":"2026-09-18T07:05:02.802424Z","shell.execute_reply":"2026-09-18T07:05:03.891637Z"}},"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":"2026-09-18T07:05:03.895718Z","iopub.execute_input":"2026-09-18T07:05:03.896378Z","iopub.status.idle":"2026-09-18T07:05:16.541483Z","shell.execute_reply.started":"2026-09-18T07:05:03.896337Z","shell.execute_reply":"2026-09-18T07:05:16.540217Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:16.543736Z","iopub.execute_input":"2026-09-18T07:05:16.544145Z","iopub.status.idle":"2026-09-18T07:05:17.562382Z","shell.execute_reply.started":"2026-09-18T07:05:16.544119Z","shell.execute_reply":"2026-09-18T07:05:17.561359Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:17.563787Z","iopub.execute_input":"2026-09-18T07:05:17.564147Z","iopub.status.idle":"2026-09-18T07:05:18.601034Z","shell.execute_reply.started":"2026-09-18T07:05:17.564120Z","shell.execute_reply":"2026-09-18T07:05:18.600050Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:18.602546Z","iopub.execute_input":"2026-09-18T07:05:18.602860Z","iopub.status.idle":"2026-09-18T07:05:19.658738Z","shell.execute_reply.started":"2026-09-18T07:05:18.602834Z","shell.execute_reply":"2026-09-18T07:05:19.657622Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:19.660307Z","iopub.execute_input":"2026-09-18T07:05:19.660612Z","iopub.status.idle":"2026-09-18T07:05:20.767967Z","shell.execute_reply.started":"2026-09-18T07:05:19.660587Z","shell.execute_reply":"2026-09-18T07:05:20.767053Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:20.769474Z","iopub.execute_input":"2026-09-18T07:05:20.769786Z","iopub.status.idle":"2026-09-18T07:05:20.775065Z","shell.execute_reply.started":"2026-09-18T07:05:20.769762Z","shell.execute_reply":"2026-09-18T07:05:20.773655Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:20.776434Z","iopub.execute_input":"2026-09-18T07:05:20.776815Z","iopub.status.idle":"2026-09-18T07:05:21.876011Z","shell.execute_reply.started":"2026-09-18T07:05:20.776793Z","shell.execute_reply":"2026-09-18T07:05:21.874680Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:21.877726Z","iopub.execute_input":"2026-09-18T07:05:21.878712Z","iopub.status.idle":"2026-09-18T07:05:22.929966Z","shell.execute_reply.started":"2026-09-18T07:05:21.878674Z","shell.execute_reply":"2026-09-18T07:05:22.929070Z"}},"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":"2026-09-18T07:05:22.931337Z","iopub.execute_input":"2026-09-18T07:05:22.931658Z","iopub.status.idle":"2026-09-18T07:05:23.996641Z","shell.execute_reply.started":"2026-09-18T07:05:22.931622Z","shell.execute_reply":"2026-09-18T07:05:23.995663Z"},"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":"2026-09-18T07:05:23.997860Z","iopub.execute_input":"2026-09-18T07:05:23.998229Z","iopub.status.idle":"2026-09-18T07:05:25.027165Z","shell.execute_reply.started":"2026-09-18T07:05:23.998204Z","shell.execute_reply":"2026-09-18T07:05:25.026121Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:25.031284Z","iopub.execute_input":"2026-09-18T07:05:25.031634Z","iopub.status.idle":"2026-09-18T07:05:26.049614Z","shell.execute_reply.started":"2026-09-18T07:05:25.031608Z","shell.execute_reply":"2026-09-18T07:05:26.048557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow\nprint(tensorflow.__version__)\n\nimport keras\nprint(keras.__version__)\n\nimport tensorflow.keras\nprint(tensorflow.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T12:16:13.906836Z","iopub.execute_input":"2026-09-18T12:16:13.907662Z","iopub.status.idle":"2026-09-18T12:16:13.913450Z","shell.execute_reply.started":"2026-09-18T12:16:13.907624Z","shell.execute_reply":"2026-09-18T12:16:13.912428Z"}},"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":"2026-09-18T12:16:18.365492Z","iopub.execute_input":"2026-09-18T12:16:18.366320Z","iopub.status.idle":"2026-09-18T12:16:18.371287Z","shell.execute_reply.started":"2026-09-18T12:16:18.366285Z","shell.execute_reply":"2026-09-18T12:16:18.370063Z"},"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":"2026-09-18T12:16:22.981295Z","iopub.execute_input":"2026-09-18T12:16:22.982117Z","iopub.status.idle":"2026-09-18T12:16:22.987434Z","shell.execute_reply.started":"2026-09-18T12:16:22.982073Z","shell.execute_reply":"2026-09-18T12:16:22.986356Z"},"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":"2026-09-18T07:05:37.655704Z","iopub.execute_input":"2026-09-18T07:05:37.657404Z","iopub.status.idle":"2026-09-18T07:05:37.667121Z","shell.execute_reply.started":"2026-09-18T07:05:37.657379Z","shell.execute_reply":"2026-09-18T07:05:37.666190Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:37.668448Z","iopub.execute_input":"2026-09-18T07:05:37.668756Z","iopub.status.idle":"2026-09-18T07:05:38.775853Z","shell.execute_reply.started":"2026-09-18T07:05:37.668728Z","shell.execute_reply":"2026-09-18T07:05:38.774550Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:38.777692Z","iopub.execute_input":"2026-09-18T07:05:38.778183Z","iopub.status.idle":"2026-09-18T07:05:39.835117Z","shell.execute_reply.started":"2026-09-18T07:05:38.778141Z","shell.execute_reply":"2026-09-18T07:05:39.834063Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:39.836730Z","iopub.execute_input":"2026-09-18T07:05:39.837192Z","iopub.status.idle":"2026-09-18T07:05:40.861889Z","shell.execute_reply.started":"2026-09-18T07:05:39.837159Z","shell.execute_reply":"2026-09-18T07:05:40.860786Z"}},"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":"2026-09-18T07:05:40.863593Z","iopub.execute_input":"2026-09-18T07:05:40.863958Z","iopub.status.idle":"2026-09-18T07:05:42.931569Z","shell.execute_reply.started":"2026-09-18T07:05:40.863923Z","shell.execute_reply":"2026-09-18T07:05:42.930770Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:42.932845Z","iopub.execute_input":"2026-09-18T07:05:42.933260Z","iopub.status.idle":"2026-09-18T07:05:42.938539Z","shell.execute_reply.started":"2026-09-18T07:05:42.933233Z","shell.execute_reply":"2026-09-18T07:05:42.937396Z"}},"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":"2026-09-18T07:05:42.939607Z","iopub.execute_input":"2026-09-18T07:05:42.939871Z","iopub.status.idle":"2026-09-18T07:05:45.120797Z","shell.execute_reply.started":"2026-09-18T07:05:42.939836Z","shell.execute_reply":"2026-09-18T07:05:45.119843Z"},"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":"2026-09-18T07:05:45.122282Z","iopub.execute_input":"2026-09-18T07:05:45.122538Z","iopub.status.idle":"2026-09-18T07:05:47.199935Z","shell.execute_reply.started":"2026-09-18T07:05:45.122516Z","shell.execute_reply":"2026-09-18T07:05:47.198984Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-18T07:05:47.201419Z","iopub.execute_input":"2026-09-18T07:05:47.201843Z","iopub.status.idle":"2026-09-18T07:05:57.700350Z","shell.execute_reply.started":"2026-09-18T07:05:47.201816Z","shell.execute_reply":"2026-09-18T07:05:57.699088Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-18T07:05:57.701937Z","iopub.execute_input":"2026-09-18T07:05:57.702457Z","iopub.status.idle":"2026-09-18T07:05:57.717809Z","shell.execute_reply.started":"2026-09-18T07:05:57.702417Z","shell.execute_reply":"2026-09-18T07:05:57.716902Z"},"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":"2026-09-18T07:05:57.719134Z","iopub.execute_input":"2026-09-18T07:05:57.719681Z","iopub.status.idle":"2026-09-18T07:05:57.723589Z","shell.execute_reply.started":"2026-09-18T07:05:57.719656Z","shell.execute_reply":"2026-09-18T07:05:57.722473Z"}},"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":"2026-09-18T12:16:31.520656Z","iopub.execute_input":"2026-09-18T12:16:31.521438Z","iopub.status.idle":"2026-09-18T12:16:31.527286Z","shell.execute_reply.started":"2026-09-18T12:16:31.521394Z","shell.execute_reply":"2026-09-18T12:16:31.526077Z"}},"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',\n                     kernel_initializer='he_uniform',\n                     padding='same',\n                     input_shape=(200, 200, 3))\n             )\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":"2026-09-18T07:05:57.734123Z","iopub.execute_input":"2026-09-18T07:05:57.734480Z","iopub.status.idle":"2026-09-18T07:05:57.741614Z","shell.execute_reply.started":"2026-09-18T07:05:57.734457Z","shell.execute_reply":"2026-09-18T07:05:57.740663Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:05:57.742666Z","iopub.execute_input":"2026-09-18T07:05:57.743254Z","iopub.status.idle":"2026-09-18T07:05:59.515832Z","shell.execute_reply.started":"2026-09-18T07:05:57.743184Z","shell.execute_reply":"2026-09-18T07:05:59.512071Z"}},"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":"2026-09-18T07:05:59.517138Z","iopub.execute_input":"2026-09-18T07:05:59.517450Z","iopub.status.idle":"2026-09-18T07:05:59.523791Z","shell.execute_reply.started":"2026-09-18T07:05:59.517427Z","shell.execute_reply":"2026-09-18T07:05:59.522768Z"}},"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":"2026-09-18T07:05:59.524910Z","iopub.execute_input":"2026-09-18T07:05:59.525246Z","iopub.status.idle":"2026-09-18T07:05:59.604127Z","shell.execute_reply.started":"2026-09-18T07:05:59.525223Z","shell.execute_reply":"2026-09-18T07:05:59.603072Z"}},"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":"2026-09-18T07:05:59.605635Z","iopub.execute_input":"2026-09-18T07:05:59.606078Z","iopub.status.idle":"2026-09-18T07:05:59.702853Z","shell.execute_reply.started":"2026-09-18T07:05:59.606041Z","shell.execute_reply":"2026-09-18T07:05:59.701967Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API - new cell\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":"2026-09-18T07:05:59.704453Z","iopub.execute_input":"2026-09-18T07:05:59.704735Z","iopub.status.idle":"2026-09-18T07:06:00.803983Z","shell.execute_reply.started":"2026-09-18T07:05:59.704712Z","shell.execute_reply":"2026-09-18T07:06:00.802138Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:00.808274Z","iopub.execute_input":"2026-09-18T07:06:00.808865Z","iopub.status.idle":"2026-09-18T07:06:00.814941Z","shell.execute_reply.started":"2026-09-18T07:06:00.808837Z","shell.execute_reply":"2026-09-18T07:06:00.814059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:00.816372Z","iopub.execute_input":"2026-09-18T07:06:00.816635Z","iopub.status.idle":"2026-09-18T07:06:01.849304Z","shell.execute_reply.started":"2026-09-18T07:06:00.816614Z","shell.execute_reply":"2026-09-18T07:06:01.848255Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = 224 #for vgg16\nBATCH_SIZE = 64\nEPOCHS = 30","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:01.850857Z","iopub.execute_input":"2026-09-18T07:06:01.851290Z","iopub.status.idle":"2026-09-18T07:06:01.856142Z","shell.execute_reply.started":"2026-09-18T07:06:01.851262Z","shell.execute_reply":"2026-09-18T07:06:01.855044Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications.vgg16 import preprocess_input\n\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\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":"2026-09-18T07:06:01.857310Z","iopub.execute_input":"2026-09-18T07:06:01.857682Z","iopub.status.idle":"2026-09-18T07:06:42.777264Z","shell.execute_reply.started":"2026-09-18T07:06:01.857656Z","shell.execute_reply":"2026-09-18T07:06:42.776486Z"}},"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":"2026-09-18T07:06:42.778414Z","iopub.execute_input":"2026-09-18T07:06:42.778812Z","iopub.status.idle":"2026-09-18T07:06:42.786703Z","shell.execute_reply.started":"2026-09-18T07:06:42.778769Z","shell.execute_reply":"2026-09-18T07:06:42.785443Z"}},"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":"2026-09-18T07:06:42.799020Z","iopub.execute_input":"2026-09-18T07:06:42.799481Z","iopub.status.idle":"2026-09-18T07:06:42.807662Z","shell.execute_reply.started":"2026-09-18T07:06:42.799451Z","shell.execute_reply":"2026-09-18T07:06:42.806811Z"}},"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":"2026-09-18T07:06:42.809164Z","iopub.execute_input":"2026-09-18T07:06:42.809591Z","iopub.status.idle":"2026-09-18T07:06:42.816263Z","shell.execute_reply.started":"2026-09-18T07:06:42.809554Z","shell.execute_reply":"2026-09-18T07:06:42.815261Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:42.817615Z","iopub.execute_input":"2026-09-18T07:06:42.818013Z","iopub.status.idle":"2026-09-18T07:06:42.825551Z","shell.execute_reply.started":"2026-09-18T07:06:42.817945Z","shell.execute_reply":"2026-09-18T07:06:42.824459Z"}},"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":"2026-09-18T07:06:42.827087Z","iopub.execute_input":"2026-09-18T07:06:42.827528Z","iopub.status.idle":"2026-09-18T07:06:42.834538Z","shell.execute_reply.started":"2026-09-18T07:06:42.827488Z","shell.execute_reply":"2026-09-18T07:06:42.833296Z"}},"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":"2026-09-18T07:06:42.835796Z","iopub.execute_input":"2026-09-18T07:06:42.836136Z","iopub.status.idle":"2026-09-18T07:06:43.888448Z","shell.execute_reply.started":"2026-09-18T07:06:42.836112Z","shell.execute_reply":"2026-09-18T07:06:43.887373Z"}},"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":"2026-09-18T07:06:43.890081Z","iopub.execute_input":"2026-09-18T07:06:43.890564Z","iopub.status.idle":"2026-09-18T07:06:43.897146Z","shell.execute_reply.started":"2026-09-18T07:06:43.890534Z","shell.execute_reply":"2026-09-18T07:06:43.896151Z"}},"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":"2026-09-18T07:06:43.898377Z","iopub.execute_input":"2026-09-18T07:06:43.898673Z","iopub.status.idle":"2026-09-18T07:06:43.909815Z","shell.execute_reply.started":"2026-09-18T07:06:43.898650Z","shell.execute_reply":"2026-09-18T07:06:43.908915Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:43.911174Z","iopub.execute_input":"2026-09-18T07:06:43.911797Z","iopub.status.idle":"2026-09-18T07:06:43.918503Z","shell.execute_reply.started":"2026-09-18T07:06:43.911771Z","shell.execute_reply":"2026-09-18T07:06:43.917693Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:43.919755Z","iopub.execute_input":"2026-09-18T07:06:43.920141Z","iopub.status.idle":"2026-09-18T07:06:43.926134Z","shell.execute_reply.started":"2026-09-18T07:06:43.920107Z","shell.execute_reply":"2026-09-18T07:06:43.925327Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:43.927453Z","iopub.execute_input":"2026-09-18T07:06:43.927844Z","iopub.status.idle":"2026-09-18T07:06:43.934643Z","shell.execute_reply.started":"2026-09-18T07:06:43.927804Z","shell.execute_reply":"2026-09-18T07:06:43.933709Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:43.935730Z","iopub.execute_input":"2026-09-18T07:06:43.936618Z","iopub.status.idle":"2026-09-18T07:06:43.943090Z","shell.execute_reply.started":"2026-09-18T07:06:43.936592Z","shell.execute_reply":"2026-09-18T07:06:43.942196Z"}},"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":"2026-09-18T07:06:43.944218Z","iopub.execute_input":"2026-09-18T07:06:43.944791Z","iopub.status.idle":"2026-09-18T07:06:43.952265Z","shell.execute_reply.started":"2026-09-18T07:06:43.944767Z","shell.execute_reply":"2026-09-18T07:06:43.951218Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:06:43.953330Z","iopub.execute_input":"2026-09-18T07:06:43.953638Z","iopub.status.idle":"2026-09-18T07:06:43.961555Z","shell.execute_reply.started":"2026-09-18T07:06:43.953615Z","shell.execute_reply":"2026-09-18T07:06:43.960750Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. Instantiate the generator with the validation_split ratio\ntest_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True\n)\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":"2026-09-18T07:06:43.962683Z","iopub.execute_input":"2026-09-18T07:06:43.963536Z","iopub.status.idle":"2026-09-18T07:06:56.522466Z","shell.execute_reply.started":"2026-09-18T07:06:43.963512Z","shell.execute_reply":"2026-09-18T07:06:56.521403Z"}},"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":"2026-09-18T07:06:56.523864Z","iopub.execute_input":"2026-09-18T07:06:56.524249Z","iopub.status.idle":"2026-09-18T07:06:56.530750Z","shell.execute_reply.started":"2026-09-18T07:06:56.524215Z","shell.execute_reply":"2026-09-18T07:06:56.529929Z"}},"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":"2026-09-18T07:06:56.532273Z","iopub.execute_input":"2026-09-18T07:06:56.532618Z","iopub.status.idle":"2026-09-18T07:07:06.034410Z","shell.execute_reply.started":"2026-09-18T07:06:56.532586Z","shell.execute_reply":"2026-09-18T07:07:06.031459Z"}},"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":"2026-09-18T07:07:06.035634Z","iopub.execute_input":"2026-09-18T07:07:06.035947Z","iopub.status.idle":"2026-09-18T07:07:15.581161Z","shell.execute_reply.started":"2026-09-18T07:07:06.035919Z","shell.execute_reply":"2026-09-18T07:07:15.579704Z"}},"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":"2026-09-18T07:07:15.582570Z","iopub.execute_input":"2026-09-18T07:07:15.582960Z","iopub.status.idle":"2026-09-18T07:07:15.589020Z","shell.execute_reply.started":"2026-09-18T07:07:15.582931Z","shell.execute_reply":"2026-09-18T07:07:15.588049Z"},"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":"2026-09-18T07:07:15.590399Z","iopub.execute_input":"2026-09-18T07:07:15.591091Z","iopub.status.idle":"2026-09-18T07:07:25.306078Z","shell.execute_reply.started":"2026-09-18T07:07:15.591058Z","shell.execute_reply":"2026-09-18T07:07:25.304034Z"}},"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":"2026-09-18T07:07:25.307657Z","iopub.execute_input":"2026-09-18T07:07:25.308030Z","iopub.status.idle":"2026-09-18T07:07:25.312886Z","shell.execute_reply.started":"2026-09-18T07:07:25.307956Z","shell.execute_reply":"2026-09-18T07:07:25.311886Z"}},"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":"2026-09-18T07:07:25.314076Z","iopub.execute_input":"2026-09-18T07:07:25.314389Z","iopub.status.idle":"2026-09-18T07:07:25.325199Z","shell.execute_reply.started":"2026-09-18T07:07:25.314362Z","shell.execute_reply":"2026-09-18T07:07:25.324265Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:07:25.326495Z","iopub.execute_input":"2026-09-18T07:07:25.327070Z","iopub.status.idle":"2026-09-18T07:07:25.336964Z","shell.execute_reply.started":"2026-09-18T07:07:25.327037Z","shell.execute_reply":"2026-09-18T07:07:25.335901Z"}},"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":"2026-09-18T07:11:48.363253Z","iopub.execute_input":"2026-09-18T07:11:48.364141Z","iopub.status.idle":"2026-09-18T07:11:48.734798Z","shell.execute_reply.started":"2026-09-18T07:11:48.364106Z","shell.execute_reply":"2026-09-18T07:11:48.734064Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_vgg16_top = VGG16(include_top=True,\n                        input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n                       )\nmodel_vgg16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:48.736305Z","iopub.execute_input":"2026-09-18T07:11:48.736625Z","iopub.status.idle":"2026-09-18T07:11:51.149133Z","shell.execute_reply.started":"2026-09-18T07:11:48.736602Z","shell.execute_reply":"2026-09-18T07:11:51.148156Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_16_feature_extractor = VGG16(include_top=False,\n                                   input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n                                  )\nmodel_16_feature_extractor.summary() #feature extractor as a backbone","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.150385Z","iopub.execute_input":"2026-09-18T07:11:51.150634Z","iopub.status.idle":"2026-09-18T07:11:51.502639Z","shell.execute_reply.started":"2026-09-18T07:11:51.150613Z","shell.execute_reply":"2026-09-18T07:11:51.501676Z"}},"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":"2026-09-18T07:11:51.503733Z","iopub.execute_input":"2026-09-18T07:11:51.504648Z","iopub.status.idle":"2026-09-18T07:11:51.509521Z","shell.execute_reply.started":"2026-09-18T07:11:51.504620Z","shell.execute_reply":"2026-09-18T07:11:51.508619Z"}},"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":"2026-09-18T07:11:51.511806Z","iopub.execute_input":"2026-09-18T07:11:51.512388Z","iopub.status.idle":"2026-09-18T07:11:51.521142Z","shell.execute_reply.started":"2026-09-18T07:11:51.512362Z","shell.execute_reply":"2026-09-18T07:11:51.520278Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.522400Z","iopub.execute_input":"2026-09-18T07:11:51.522620Z","iopub.status.idle":"2026-09-18T07:11:51.533549Z","shell.execute_reply.started":"2026-09-18T07:11:51.522601Z","shell.execute_reply":"2026-09-18T07:11:51.532750Z"}},"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":"2026-09-18T07:11:51.534770Z","iopub.execute_input":"2026-09-18T07:11:51.535121Z","iopub.status.idle":"2026-09-18T07:11:51.546678Z","shell.execute_reply.started":"2026-09-18T07:11:51.535090Z","shell.execute_reply":"2026-09-18T07:11:51.545900Z"}},"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":"2026-09-18T07:11:51.547581Z","iopub.execute_input":"2026-09-18T07:11:51.547838Z","iopub.status.idle":"2026-09-18T07:11:51.567584Z","shell.execute_reply.started":"2026-09-18T07:11:51.547816Z","shell.execute_reply":"2026-09-18T07:11:51.566869Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.568577Z","iopub.execute_input":"2026-09-18T07:11:51.568911Z","iopub.status.idle":"2026-09-18T07:11:51.584085Z","shell.execute_reply.started":"2026-09-18T07:11:51.568889Z","shell.execute_reply":"2026-09-18T07:11:51.583300Z"}},"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,\n                    loss='binary_crossentropy',\n                    metrics=['accuracy']\n                   )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.585163Z","iopub.execute_input":"2026-09-18T07:11:51.585759Z","iopub.status.idle":"2026-09-18T07:11:51.599688Z","shell.execute_reply.started":"2026-09-18T07:11:51.585735Z","shell.execute_reply":"2026-09-18T07:11:51.598704Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.600801Z","iopub.execute_input":"2026-09-18T07:11:51.601078Z","iopub.status.idle":"2026-09-18T07:11:51.656155Z","shell.execute_reply.started":"2026-09-18T07:11:51.601055Z","shell.execute_reply":"2026-09-18T07:11:51.653030Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.657293Z","iopub.execute_input":"2026-09-18T07:11:51.657810Z","iopub.status.idle":"2026-09-18T07:11:51.663580Z","shell.execute_reply.started":"2026-09-18T07:11:51.657786Z","shell.execute_reply":"2026-09-18T07:11:51.662500Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.665813Z","iopub.execute_input":"2026-09-18T07:11:51.666446Z","iopub.status.idle":"2026-09-18T07:11:51.672063Z","shell.execute_reply.started":"2026-09-18T07:11:51.666415Z","shell.execute_reply":"2026-09-18T07:11:51.671051Z"}},"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=5, \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=1, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:11:51.677270Z","iopub.execute_input":"2026-09-18T07:11:51.677759Z","execution_failed":"2026-09-18T12:13:26.306Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-18T12:13:26.307Z"}},"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.idle":"2026-09-18T07:19:44.152858Z","shell.execute_reply.started":"2026-09-18T07:19:27.105370Z","shell.execute_reply":"2026-09-18T07:19:44.151892Z"}},"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":"2026-09-18T07:19:44.154082Z","iopub.execute_input":"2026-09-18T07:19:44.155222Z","iopub.status.idle":"2026-09-18T07:20:57.519369Z","shell.execute_reply.started":"2026-09-18T07:19:44.155196Z","shell.execute_reply":"2026-09-18T07:20:57.518221Z"}},"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":"2026-09-18T07:20:57.520841Z","iopub.execute_input":"2026-09-18T07:20:57.521313Z","iopub.status.idle":"2026-09-18T07:21:26.092677Z","shell.execute_reply.started":"2026-09-18T07:20:57.521275Z","shell.execute_reply":"2026-09-18T07:21:26.091689Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:21:26.093880Z","iopub.execute_input":"2026-09-18T07:21:26.094309Z","iopub.status.idle":"2026-09-18T07:21:26.101574Z","shell.execute_reply.started":"2026-09-18T07:21:26.094282Z","shell.execute_reply":"2026-09-18T07:21:26.100423Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:21:26.102925Z","iopub.execute_input":"2026-09-18T07:21:26.103438Z","iopub.status.idle":"2026-09-18T07:21:26.114918Z","shell.execute_reply.started":"2026-09-18T07:21:26.103384Z","shell.execute_reply":"2026-09-18T07:21:26.114046Z"}},"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":"2026-09-18T07:21:26.116411Z","iopub.execute_input":"2026-09-18T07:21:26.117171Z","iopub.status.idle":"2026-09-18T07:21:26.143691Z","shell.execute_reply.started":"2026-09-18T07:21:26.117127Z","shell.execute_reply":"2026-09-18T07:21:26.142956Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:21:26.144652Z","iopub.execute_input":"2026-09-18T07:21:26.144875Z","iopub.status.idle":"2026-09-18T07:21:26.151460Z","shell.execute_reply.started":"2026-09-18T07:21:26.144855Z","shell.execute_reply":"2026-09-18T07:21:26.150486Z"}},"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'}\n\nprint(\"Done.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:21:26.153027Z","iopub.execute_input":"2026-09-18T07:21:26.153306Z","iopub.status.idle":"2026-09-18T07:21:33.401232Z","shell.execute_reply.started":"2026-09-18T07:21:26.153283Z","shell.execute_reply":"2026-09-18T07:21:33.400307Z"}},"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":"2026-09-18T07:21:33.402775Z","iopub.execute_input":"2026-09-18T07:21:33.403700Z","iopub.status.idle":"2026-09-18T07:21:42.105739Z","shell.execute_reply.started":"2026-09-18T07:21:33.403658Z","shell.execute_reply":"2026-09-18T07:21:42.104140Z"}},"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":"2026-09-18T07:21:42.108425Z","iopub.execute_input":"2026-09-18T07:21:42.108729Z","iopub.status.idle":"2026-09-18T07:21:42.164100Z","shell.execute_reply.started":"2026-09-18T07:21:42.108703Z","shell.execute_reply":"2026-09-18T07:21:42.162570Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications.inception_v3 import preprocess_input\n\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\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":"2026-09-18T07:44:43.442525Z","iopub.execute_input":"2026-09-18T07:44:43.443203Z","iopub.status.idle":"2026-09-18T07:45:00.633355Z","shell.execute_reply.started":"2026-09-18T07:44:43.443168Z","shell.execute_reply":"2026-09-18T07:45:00.632468Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\n\ndef define_model_inceptionv3():\n    # load model\n    model = InceptionV3(include_top=False, input_shape=(224, 224, 3))\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n        # layer.trainable = True #try to test\n    \n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n    # output = Dense(1, activation='sigmoid')(flat1)\n    output = Dense(1, activation='sigmoid')(class4)\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    # compile model\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:45:00.635094Z","iopub.execute_input":"2026-09-18T07:45:00.635522Z","iopub.status.idle":"2026-09-18T07:45:00.643476Z","shell.execute_reply.started":"2026-09-18T07:45:00.635494Z","shell.execute_reply":"2026-09-18T07:45:00.642337Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"execution":{"iopub.status.busy":"2026-09-18T07:45:00.644622Z","iopub.execute_input":"2026-09-18T07:45:00.645102Z","iopub.status.idle":"2026-09-18T07:45:03.196155Z","shell.execute_reply.started":"2026-09-18T07:45:00.645075Z","shell.execute_reply":"2026-09-18T07:45:03.194894Z"},"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":"2026-09-18T07:45:03.197486Z","iopub.execute_input":"2026-09-18T07:45:03.197792Z","iopub.status.idle":"2026-09-18T07:45:03.204750Z","shell.execute_reply.started":"2026-09-18T07:45:03.197766Z","shell.execute_reply":"2026-09-18T07:45:03.203730Z"}},"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":"2026-09-18T07:45:03.208119Z","iopub.execute_input":"2026-09-18T07:45:03.208487Z","iopub.status.idle":"2026-09-18T07:45:03.217214Z","shell.execute_reply.started":"2026-09-18T07:45:03.208460Z","shell.execute_reply":"2026-09-18T07:45:03.215910Z"}},"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":"# fit model\nmodel_inceptionv3.reset_states()\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=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:45:03.218752Z","iopub.execute_input":"2026-09-18T07:45:03.219211Z","iopub.status.idle":"2026-09-18T07:49:08.487737Z","shell.execute_reply.started":"2026-09-18T07:45:03.219182Z","shell.execute_reply":"2026-09-18T07:49:08.486879Z"}},"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":"2026-09-18T07:49:08.489288Z","iopub.execute_input":"2026-09-18T07:49:08.489644Z","iopub.status.idle":"2026-09-18T07:49:08.497580Z","shell.execute_reply.started":"2026-09-18T07:49:08.489610Z","shell.execute_reply":"2026-09-18T07:49:08.496724Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:49:08.498823Z","iopub.execute_input":"2026-09-18T07:49:08.499139Z","iopub.status.idle":"2026-09-18T07:49:08.512756Z","shell.execute_reply.started":"2026-09-18T07:49:08.499115Z","shell.execute_reply":"2026-09-18T07:49:08.511847Z"}},"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":"2026-09-18T07:49:08.514049Z","iopub.execute_input":"2026-09-18T07:49:08.514382Z","iopub.status.idle":"2026-09-18T07:49:08.520832Z","shell.execute_reply.started":"2026-09-18T07:49:08.514351Z","shell.execute_reply":"2026-09-18T07:49:08.520006Z"}},"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":"2026-09-18T07:49:08.522079Z","iopub.execute_input":"2026-09-18T07:49:08.522598Z","iopub.status.idle":"2026-09-18T07:49:08.529533Z","shell.execute_reply.started":"2026-09-18T07:49:08.522563Z","shell.execute_reply":"2026-09-18T07:49:08.528447Z"}},"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":"2026-09-18T07:49:08.530650Z","iopub.execute_input":"2026-09-18T07:49:08.530919Z","iopub.status.idle":"2026-09-18T07:49:39.452628Z","shell.execute_reply.started":"2026-09-18T07:49:08.530863Z","shell.execute_reply":"2026-09-18T07:49:39.451743Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# images = test_it.__next__()\n# images.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T12:15:23.353954Z","iopub.execute_input":"2026-09-18T12:15:23.354842Z","iopub.status.idle":"2026-09-18T12:15:23.359976Z","shell.execute_reply.started":"2026-09-18T12:15:23.354804Z","shell.execute_reply":"2026-09-18T12:15:23.358805Z"}},"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":"2026-09-18T07:49:39.670487Z","iopub.status.idle":"2026-09-18T07:49:39.670795Z","shell.execute_reply.started":"2026-09-18T07:49:39.670646Z","shell.execute_reply":"2026-09-18T07:49:39.670661Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T07:49:39.671620Z","iopub.status.idle":"2026-09-18T07:49:39.672047Z","shell.execute_reply.started":"2026-09-18T07:49:39.671812Z","shell.execute_reply":"2026-09-18T07:49:39.671829Z"}},"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":"## EfficientNetB7","metadata":{}},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications.efficientnet import preprocess_input\n\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\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=64,\n    target_size=(224, 224),\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=64,\n    target_size=(224, 224),\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":"2026-09-18T12:18:18.448561Z","iopub.execute_input":"2026-09-18T12:18:18.449529Z","iopub.status.idle":"2026-09-18T12:19:02.796526Z","shell.execute_reply.started":"2026-09-18T12:18:18.449493Z","shell.execute_reply":"2026-09-18T12:19:02.795767Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.efficientnet import EfficientNetB0\nfrom keras.layers import Dense, Flatten\nfrom keras.models import Model\nfrom keras.optimizers import SGD\n\ndef define_model_efficientnet():\n    # load model EfficientNetB0\n    model = EfficientNetB0(include_top=False, input_shape=(224, 224, 3))\n    \n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n        \n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n    output = Dense(1, activation='sigmoid')(class4)\n    \n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    \n    # compile model (หมายเหตุ: Keras เวอร์ชั่นใหม่ใช้ learning_rate แทน lr)\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T12:23:13.824215Z","iopub.execute_input":"2026-09-18T12:23:13.825271Z","iopub.status.idle":"2026-09-18T12:23:13.833376Z","shell.execute_reply.started":"2026-09-18T12:23:13.825225Z","shell.execute_reply":"2026-09-18T12:23:13.832240Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.efficientnet import EfficientNetB0\nfrom keras.layers import Dense, GlobalAveragePooling2D\nfrom keras.models import Model\nfrom keras.optimizers import SGD\n\n# 1. สร้างฟังก์ชัน\ndef define_model_efficientnet():\n    model = EfficientNetB0(include_top=False, input_shape=(224, 224, 3))\n    for layer in model.layers:\n        layer.trainable = False\n        \n    x = GlobalAveragePooling2D()(model.output)\n    x = Dense(256, activation='relu', kernel_initializer='he_uniform')(x)\n    output = Dense(1, activation='sigmoid')(x)\n    \n    model = Model(inputs=model.inputs, outputs=output)\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# 2. เรียกใช้งานฟังก์ชัน (เช็คชื่อตัวแปรให้ตรงกัน)\nmodel_inceptionv3 = define_model_efficientnet()\n\n# 3. แสดง Memory ID ของตัวแปรที่เพิ่งสร้าง\nprint(id(model_inceptionv3))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T12:24:47.124687Z","iopub.execute_input":"2026-09-18T12:24:47.125430Z","iopub.status.idle":"2026-09-18T12:24:51.432663Z","shell.execute_reply.started":"2026-09-18T12:24:47.125395Z","shell.execute_reply":"2026-09-18T12:24:51.431747Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKerasTF\n\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=3, \n    verbose=1,\n    callbacks=[PlotLossesKerasTF()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-18T12:31:06.026697Z","iopub.execute_input":"2026-09-18T12:31:06.027631Z","iopub.status.idle":"2026-09-18T12:37:15.144315Z","shell.execute_reply.started":"2026-09-18T12:31:06.027597Z","shell.execute_reply":"2026-09-18T12:37:15.143432Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}