{"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","trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:20.346060Z","iopub.execute_input":"2026-09-16T17:48:20.346364Z","iopub.status.idle":"2026-09-16T17:48:20.352582Z","shell.execute_reply.started":"2026-09-16T17:48:20.346340Z","shell.execute_reply":"2026-09-16T17:48:20.351656Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:20.392831Z","iopub.execute_input":"2026-09-16T17:48:20.393105Z","iopub.status.idle":"2026-09-16T17:48:21.421044Z","shell.execute_reply.started":"2026-09-16T17:48:20.393082Z","shell.execute_reply":"2026-09-16T17:48:21.419815Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:21.423072Z","iopub.execute_input":"2026-09-16T17:48:21.423391Z","iopub.status.idle":"2026-09-16T17:48:22.427378Z","shell.execute_reply.started":"2026-09-16T17:48:21.423365Z","shell.execute_reply":"2026-09-16T17:48:22.426299Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:22.429188Z","iopub.execute_input":"2026-09-16T17:48:22.429579Z","iopub.status.idle":"2026-09-16T17:48:32.004249Z","shell.execute_reply.started":"2026-09-16T17:48:22.429551Z","shell.execute_reply":"2026-09-16T17:48:32.003503Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:32.006400Z","iopub.execute_input":"2026-09-16T17:48:32.006754Z","iopub.status.idle":"2026-09-16T17:48:33.029847Z","shell.execute_reply.started":"2026-09-16T17:48:32.006728Z","shell.execute_reply":"2026-09-16T17:48:33.028596Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:33.032100Z","iopub.execute_input":"2026-09-16T17:48:33.033164Z","iopub.status.idle":"2026-09-16T17:48:34.092370Z","shell.execute_reply.started":"2026-09-16T17:48:33.033122Z","shell.execute_reply":"2026-09-16T17:48:34.091447Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:34.093850Z","iopub.execute_input":"2026-09-16T17:48:34.094162Z","iopub.status.idle":"2026-09-16T17:48:35.134478Z","shell.execute_reply.started":"2026-09-16T17:48:34.094136Z","shell.execute_reply":"2026-09-16T17:48:35.133212Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:35.136545Z","iopub.execute_input":"2026-09-16T17:48:35.136997Z","iopub.status.idle":"2026-09-16T17:48:36.216663Z","shell.execute_reply.started":"2026-09-16T17:48:35.136954Z","shell.execute_reply":"2026-09-16T17:48:36.215677Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:36.218140Z","iopub.execute_input":"2026-09-16T17:48:36.218934Z","iopub.status.idle":"2026-09-16T17:48:36.224740Z","shell.execute_reply.started":"2026-09-16T17:48:36.218904Z","shell.execute_reply":"2026-09-16T17:48:36.223734Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:36.226703Z","iopub.execute_input":"2026-09-16T17:48:36.226987Z","iopub.status.idle":"2026-09-16T17:48:37.302500Z","shell.execute_reply.started":"2026-09-16T17:48:36.226964Z","shell.execute_reply":"2026-09-16T17:48:37.301198Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:37.307056Z","iopub.execute_input":"2026-09-16T17:48:37.307485Z","iopub.status.idle":"2026-09-16T17:48:38.342450Z","shell.execute_reply.started":"2026-09-16T17:48:37.307417Z","shell.execute_reply":"2026-09-16T17:48:38.341519Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:38.343936Z","iopub.execute_input":"2026-09-16T17:48:38.344247Z","iopub.status.idle":"2026-09-16T17:48:39.256012Z","shell.execute_reply.started":"2026-09-16T17:48:38.344222Z","shell.execute_reply":"2026-09-16T17:48:39.255159Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:39.257771Z","iopub.execute_input":"2026-09-16T17:48:39.258135Z","iopub.status.idle":"2026-09-16T17:48:40.162845Z","shell.execute_reply.started":"2026-09-16T17:48:39.258101Z","shell.execute_reply":"2026-09-16T17:48:40.161807Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:40.164317Z","iopub.execute_input":"2026-09-16T17:48:40.165285Z","iopub.status.idle":"2026-09-16T17:48:41.197227Z","shell.execute_reply.started":"2026-09-16T17:48:40.165248Z","shell.execute_reply":"2026-09-16T17:48:41.196246Z"}},"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":"2026-09-16T17:48:41.198798Z","iopub.execute_input":"2026-09-16T17:48:41.199528Z","iopub.status.idle":"2026-09-16T17:48:41.205505Z","shell.execute_reply.started":"2026-09-16T17:48:41.199502Z","shell.execute_reply":"2026-09-16T17:48:41.204486Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:41.206736Z","iopub.execute_input":"2026-09-16T17:48:41.207046Z","iopub.status.idle":"2026-09-16T17:48:41.214248Z","shell.execute_reply.started":"2026-09-16T17:48:41.207023Z","shell.execute_reply":"2026-09-16T17:48:41.213501Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:41.215385Z","iopub.execute_input":"2026-09-16T17:48:41.215727Z","iopub.status.idle":"2026-09-16T17:48:41.222161Z","shell.execute_reply.started":"2026-09-16T17:48:41.215693Z","shell.execute_reply":"2026-09-16T17:48:41.221400Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:41.223517Z","iopub.execute_input":"2026-09-16T17:48:41.223840Z","iopub.status.idle":"2026-09-16T17:48:41.231297Z","shell.execute_reply.started":"2026-09-16T17:48:41.223810Z","shell.execute_reply":"2026-09-16T17:48:41.230503Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:41.232653Z","iopub.execute_input":"2026-09-16T17:48:41.233034Z","iopub.status.idle":"2026-09-16T17:48:42.238203Z","shell.execute_reply.started":"2026-09-16T17:48:41.232991Z","shell.execute_reply":"2026-09-16T17:48:42.237105Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:42.239842Z","iopub.execute_input":"2026-09-16T17:48:42.240155Z","iopub.status.idle":"2026-09-16T17:48:43.247360Z","shell.execute_reply.started":"2026-09-16T17:48:42.240129Z","shell.execute_reply":"2026-09-16T17:48:43.246114Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:43.249126Z","iopub.execute_input":"2026-09-16T17:48:43.249531Z","iopub.status.idle":"2026-09-16T17:48:44.255061Z","shell.execute_reply.started":"2026-09-16T17:48:43.249496Z","shell.execute_reply":"2026-09-16T17:48:44.254018Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:44.256588Z","iopub.execute_input":"2026-09-16T17:48:44.256898Z","iopub.status.idle":"2026-09-16T17:48:47.245401Z","shell.execute_reply.started":"2026-09-16T17:48:44.256871Z","shell.execute_reply":"2026-09-16T17:48:47.244316Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:47.246627Z","iopub.execute_input":"2026-09-16T17:48:47.246980Z","iopub.status.idle":"2026-09-16T17:48:47.251550Z","shell.execute_reply.started":"2026-09-16T17:48:47.246954Z","shell.execute_reply":"2026-09-16T17:48:47.250509Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:47.252769Z","iopub.execute_input":"2026-09-16T17:48:47.253078Z","iopub.status.idle":"2026-09-16T17:48:49.403320Z","shell.execute_reply.started":"2026-09-16T17:48:47.253048Z","shell.execute_reply":"2026-09-16T17:48:49.402254Z"}},"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:49.404815Z","iopub.execute_input":"2026-09-16T17:48:49.405115Z","iopub.status.idle":"2026-09-16T17:48:51.610800Z","shell.execute_reply.started":"2026-09-16T17:48:49.405088Z","shell.execute_reply":"2026-09-16T17:48:51.609771Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:51.612517Z","iopub.execute_input":"2026-09-16T17:48:51.612840Z","iopub.status.idle":"2026-09-16T17:48:59.717660Z","shell.execute_reply.started":"2026-09-16T17:48:51.612812Z","shell.execute_reply":"2026-09-16T17:48:59.716523Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:59.719275Z","iopub.execute_input":"2026-09-16T17:48:59.719612Z","iopub.status.idle":"2026-09-16T17:48:59.724272Z","shell.execute_reply.started":"2026-09-16T17:48:59.719583Z","shell.execute_reply":"2026-09-16T17:48:59.723336Z"}},"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":"2026-09-16T17:48:59.725565Z","iopub.execute_input":"2026-09-16T17:48:59.725918Z","iopub.status.idle":"2026-09-16T17:48:59.733168Z","shell.execute_reply.started":"2026-09-16T17:48:59.725888Z","shell.execute_reply":"2026-09-16T17:48:59.732394Z"}},"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":"2026-09-16T17:48:59.741256Z","iopub.execute_input":"2026-09-16T17:48:59.741786Z","iopub.status.idle":"2026-09-16T17:48:59.746529Z","shell.execute_reply.started":"2026-09-16T17:48:59.741761Z","shell.execute_reply":"2026-09-16T17:48:59.745687Z"}},"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":"2026-09-16T17:48:59.747920Z","iopub.execute_input":"2026-09-16T17:48:59.748228Z","iopub.status.idle":"2026-09-16T17:48:59.755070Z","shell.execute_reply.started":"2026-09-16T17:48:59.748197Z","shell.execute_reply":"2026-09-16T17:48:59.754314Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:48:59.756163Z","iopub.execute_input":"2026-09-16T17:48:59.756498Z","iopub.status.idle":"2026-09-16T17:48:59.827162Z","shell.execute_reply.started":"2026-09-16T17:48:59.756466Z","shell.execute_reply":"2026-09-16T17:48:59.826137Z"}},"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":"2026-09-16T17:48:59.828370Z","iopub.execute_input":"2026-09-16T17:48:59.829067Z","iopub.status.idle":"2026-09-16T17:48:59.834462Z","shell.execute_reply.started":"2026-09-16T17:48:59.829044Z","shell.execute_reply":"2026-09-16T17:48:59.833654Z"}},"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":"2026-09-16T17:48:59.835673Z","iopub.execute_input":"2026-09-16T17:48:59.836294Z","iopub.status.idle":"2026-09-16T17:48:59.897086Z","shell.execute_reply.started":"2026-09-16T17:48:59.836257Z","shell.execute_reply":"2026-09-16T17:48:59.895307Z"}},"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":"2026-09-16T17:48:59.898066Z","iopub.execute_input":"2026-09-16T17:48:59.898313Z","iopub.status.idle":"2026-09-16T17:48:59.966246Z","shell.execute_reply.started":"2026-09-16T17:48:59.898291Z","shell.execute_reply":"2026-09-16T17:48:59.965331Z"}},"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":"2026-09-16T17:48:59.967330Z","iopub.execute_input":"2026-09-16T17:48:59.967619Z","iopub.status.idle":"2026-09-16T17:49:00.051903Z","shell.execute_reply.started":"2026-09-16T17:48:59.967594Z","shell.execute_reply":"2026-09-16T17:49:00.051059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:00.052936Z","iopub.execute_input":"2026-09-16T17:49:00.053405Z","iopub.status.idle":"2026-09-16T17:49:00.058975Z","shell.execute_reply.started":"2026-09-16T17:49:00.053382Z","shell.execute_reply":"2026-09-16T17:49:00.058082Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:00.060098Z","iopub.execute_input":"2026-09-16T17:49:00.060624Z","iopub.status.idle":"2026-09-16T17:49:01.099652Z","shell.execute_reply.started":"2026-09-16T17:49:00.060599Z","shell.execute_reply":"2026-09-16T17:49:01.098715Z"}},"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":"2026-09-16T17:49:01.101363Z","iopub.execute_input":"2026-09-16T17:49:01.101783Z","iopub.status.idle":"2026-09-16T17:49:01.107000Z","shell.execute_reply.started":"2026-09-16T17:49:01.101745Z","shell.execute_reply":"2026-09-16T17:49:01.105972Z"}},"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":"2026-09-16T17:49:01.108306Z","iopub.execute_input":"2026-09-16T17:49:01.108655Z","iopub.status.idle":"2026-09-16T17:49:06.171374Z","shell.execute_reply.started":"2026-09-16T17:49:01.108620Z","shell.execute_reply":"2026-09-16T17:49:06.170639Z"}},"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":"2026-09-16T17:49:06.173852Z","iopub.execute_input":"2026-09-16T17:49:06.174521Z","iopub.status.idle":"2026-09-16T17:49:06.180760Z","shell.execute_reply.started":"2026-09-16T17:49:06.174485Z","shell.execute_reply":"2026-09-16T17:49:06.179817Z"}},"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":"2026-09-16T17:49:06.181912Z","iopub.execute_input":"2026-09-16T17:49:06.182217Z","iopub.status.idle":"2026-09-16T17:49:06.196291Z","shell.execute_reply.started":"2026-09-16T17:49:06.182193Z","shell.execute_reply":"2026-09-16T17:49:06.195417Z"}},"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":"2026-09-16T17:49:06.197564Z","iopub.execute_input":"2026-09-16T17:49:06.197824Z","iopub.status.idle":"2026-09-16T17:49:06.204394Z","shell.execute_reply.started":"2026-09-16T17:49:06.197802Z","shell.execute_reply":"2026-09-16T17:49:06.203504Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:06.205683Z","iopub.execute_input":"2026-09-16T17:49:06.206560Z","iopub.status.idle":"2026-09-16T17:49:06.213039Z","shell.execute_reply.started":"2026-09-16T17:49:06.206522Z","shell.execute_reply":"2026-09-16T17:49:06.212340Z"}},"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":"2026-09-16T17:49:06.214183Z","iopub.execute_input":"2026-09-16T17:49:06.214750Z","iopub.status.idle":"2026-09-16T17:49:06.220762Z","shell.execute_reply.started":"2026-09-16T17:49:06.214727Z","shell.execute_reply":"2026-09-16T17:49:06.219908Z"}},"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":"2026-09-16T17:49:06.221873Z","iopub.execute_input":"2026-09-16T17:49:06.222156Z","iopub.status.idle":"2026-09-16T17:49:07.232000Z","shell.execute_reply.started":"2026-09-16T17:49:06.222120Z","shell.execute_reply":"2026-09-16T17:49:07.231085Z"}},"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":"2026-09-16T17:49:07.233544Z","iopub.execute_input":"2026-09-16T17:49:07.233929Z","iopub.status.idle":"2026-09-16T17:49:07.239890Z","shell.execute_reply.started":"2026-09-16T17:49:07.233903Z","shell.execute_reply":"2026-09-16T17:49:07.238520Z"}},"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":"2026-09-16T17:49:07.241338Z","iopub.execute_input":"2026-09-16T17:49:07.241722Z","iopub.status.idle":"2026-09-16T17:49:07.249929Z","shell.execute_reply.started":"2026-09-16T17:49:07.241681Z","shell.execute_reply":"2026-09-16T17:49:07.249126Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:07.250965Z","iopub.execute_input":"2026-09-16T17:49:07.251492Z","iopub.status.idle":"2026-09-16T17:49:07.257949Z","shell.execute_reply.started":"2026-09-16T17:49:07.251460Z","shell.execute_reply":"2026-09-16T17:49:07.257122Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:07.259162Z","iopub.execute_input":"2026-09-16T17:49:07.259879Z","iopub.status.idle":"2026-09-16T17:49:07.265514Z","shell.execute_reply.started":"2026-09-16T17:49:07.259847Z","shell.execute_reply":"2026-09-16T17:49:07.264724Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:07.266667Z","iopub.execute_input":"2026-09-16T17:49:07.267189Z","iopub.status.idle":"2026-09-16T17:49:07.273060Z","shell.execute_reply.started":"2026-09-16T17:49:07.267156Z","shell.execute_reply":"2026-09-16T17:49:07.272256Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:07.274087Z","iopub.execute_input":"2026-09-16T17:49:07.274287Z","iopub.status.idle":"2026-09-16T17:49:07.281411Z","shell.execute_reply.started":"2026-09-16T17:49:07.274269Z","shell.execute_reply":"2026-09-16T17:49:07.280467Z"}},"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":"2026-09-16T17:49:07.282646Z","iopub.execute_input":"2026-09-16T17:49:07.282973Z","iopub.status.idle":"2026-09-16T17:49:07.289290Z","shell.execute_reply.started":"2026-09-16T17:49:07.282941Z","shell.execute_reply":"2026-09-16T17:49:07.288623Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:07.290261Z","iopub.execute_input":"2026-09-16T17:49:07.290619Z","iopub.status.idle":"2026-09-16T17:49:07.299768Z","shell.execute_reply.started":"2026-09-16T17:49:07.290596Z","shell.execute_reply":"2026-09-16T17:49:07.298753Z"}},"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)\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":"2026-09-16T17:49:07.300833Z","iopub.execute_input":"2026-09-16T17:49:07.301174Z","iopub.status.idle":"2026-09-16T17:49:12.280751Z","shell.execute_reply.started":"2026-09-16T17:49:07.301143Z","shell.execute_reply":"2026-09-16T17:49:12.280027Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True\n)\n\ntrain_it = train_datagen.flow_from_directory(\n    train_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":"2026-09-16T17:49:12.282273Z","iopub.execute_input":"2026-09-16T17:49:12.282655Z","iopub.status.idle":"2026-09-16T17:49:12.645758Z","shell.execute_reply.started":"2026-09-16T17:49:12.282620Z","shell.execute_reply":"2026-09-16T17:49:12.644827Z"}},"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":"2026-09-16T17:49:12.646986Z","iopub.execute_input":"2026-09-16T17:49:12.648157Z","iopub.status.idle":"2026-09-16T17:49:12.654045Z","shell.execute_reply.started":"2026-09-16T17:49:12.648132Z","shell.execute_reply":"2026-09-16T17:49:12.653029Z"}},"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":"2026-09-16T17:49:12.655152Z","iopub.execute_input":"2026-09-16T17:49:12.655395Z","iopub.status.idle":"2026-09-16T17:49:21.833917Z","shell.execute_reply.started":"2026-09-16T17:49:12.655359Z","shell.execute_reply":"2026-09-16T17:49:21.831354Z"}},"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":"2026-09-16T17:49:21.835738Z","iopub.execute_input":"2026-09-16T17:49:21.836191Z","iopub.status.idle":"2026-09-16T17:49:29.841154Z","shell.execute_reply.started":"2026-09-16T17:49:21.836145Z","shell.execute_reply":"2026-09-16T17:49:29.839635Z"}},"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,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2026-09-16T17:49:29.842578Z","iopub.execute_input":"2026-09-16T17:49:29.842883Z","iopub.status.idle":"2026-09-16T17:49:29.849138Z","shell.execute_reply.started":"2026-09-16T17:49:29.842858Z","shell.execute_reply":"2026-09-16T17:49:29.848055Z"}},"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":"2026-09-16T17:49:29.850294Z","iopub.execute_input":"2026-09-16T17:49:29.850996Z","iopub.status.idle":"2026-09-16T17:49:38.426140Z","shell.execute_reply.started":"2026-09-16T17:49:29.850972Z","shell.execute_reply":"2026-09-16T17:49:38.422545Z"}},"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":"2026-09-16T17:49:38.427929Z","iopub.execute_input":"2026-09-16T17:49:38.428323Z","iopub.status.idle":"2026-09-16T17:49:38.434615Z","shell.execute_reply.started":"2026-09-16T17:49:38.428271Z","shell.execute_reply":"2026-09-16T17:49:38.433501Z"}},"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":"2026-09-16T17:49:38.435884Z","iopub.execute_input":"2026-09-16T17:49:38.436174Z","iopub.status.idle":"2026-09-16T17:49:38.445662Z","shell.execute_reply.started":"2026-09-16T17:49:38.436151Z","shell.execute_reply":"2026-09-16T17:49:38.444778Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:38.446826Z","iopub.execute_input":"2026-09-16T17:49:38.447228Z","iopub.status.idle":"2026-09-16T17:49:38.455590Z","shell.execute_reply.started":"2026-09-16T17:49:38.447201Z","shell.execute_reply":"2026-09-16T17:49:38.454723Z"}},"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.mobilenet_v2 import MobileNetV2\nfrom keras.models import Model\nfrom keras.layers import Dense, GlobalAveragePooling2D, Dropout  # <--- จุดที่ 1: เปลี่ยน Flatten เป็น GlobalAveragePooling2D\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 = MobileNetV2(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 = GlobalAveragePooling2D()(model.layers[-1].output)     # <--- จุดที่ 2: เปลี่ยน Flatten() เป็น GlobalAveragePooling2D()\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\tdrop1 = Dropout(0.5)(class1)\n\toutput = Dense(1, activation='sigmoid')(drop1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\n\t# compile model\n\tmodel.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model\n\nvgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:38.456706Z","iopub.execute_input":"2026-09-16T17:49:38.457015Z","iopub.status.idle":"2026-09-16T17:49:39.603846Z","shell.execute_reply.started":"2026-09-16T17:49:38.456993Z","shell.execute_reply":"2026-09-16T17:49:39.603065Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.vgg16 import VGG16","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:39.605036Z","iopub.execute_input":"2026-09-16T17:49:39.605382Z","iopub.status.idle":"2026-09-16T17:49:39.611156Z","shell.execute_reply.started":"2026-09-16T17:49:39.605358Z","shell.execute_reply":"2026-09-16T17:49:39.610323Z"}},"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":"2026-09-16T17:49:39.612320Z","iopub.execute_input":"2026-09-16T17:49:39.612659Z","iopub.status.idle":"2026-09-16T17:49:41.841541Z","shell.execute_reply.started":"2026-09-16T17:49:39.612628Z","shell.execute_reply":"2026-09-16T17:49:41.840590Z"}},"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":"2026-09-16T17:49:41.842683Z","iopub.execute_input":"2026-09-16T17:49:41.843052Z","iopub.status.idle":"2026-09-16T17:49:42.169345Z","shell.execute_reply.started":"2026-09-16T17:49:41.843028Z","shell.execute_reply":"2026-09-16T17:49:42.168381Z"}},"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":"2026-09-16T17:49:42.170471Z","iopub.execute_input":"2026-09-16T17:49:42.170730Z","iopub.status.idle":"2026-09-16T17:49:42.176183Z","shell.execute_reply.started":"2026-09-16T17:49:42.170706Z","shell.execute_reply":"2026-09-16T17:49:42.175163Z"}},"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":"2026-09-16T17:49:42.177422Z","iopub.execute_input":"2026-09-16T17:49:42.177788Z","iopub.status.idle":"2026-09-16T17:49:42.186375Z","shell.execute_reply.started":"2026-09-16T17:49:42.177763Z","shell.execute_reply":"2026-09-16T17:49:42.185504Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:42.187379Z","iopub.execute_input":"2026-09-16T17:49:42.187710Z","iopub.status.idle":"2026-09-16T17:49:42.198548Z","shell.execute_reply.started":"2026-09-16T17:49:42.187687Z","shell.execute_reply":"2026-09-16T17:49:42.197643Z"}},"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":"2026-09-16T17:49:42.199735Z","iopub.execute_input":"2026-09-16T17:49:42.199997Z","iopub.status.idle":"2026-09-16T17:49:42.209732Z","shell.execute_reply.started":"2026-09-16T17:49:42.199975Z","shell.execute_reply":"2026-09-16T17:49:42.208824Z"}},"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":"2026-09-16T17:49:42.210855Z","iopub.execute_input":"2026-09-16T17:49:42.211169Z","iopub.status.idle":"2026-09-16T17:49:42.226085Z","shell.execute_reply.started":"2026-09-16T17:49:42.211132Z","shell.execute_reply":"2026-09-16T17:49:42.225367Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:42.227013Z","iopub.execute_input":"2026-09-16T17:49:42.227537Z","iopub.status.idle":"2026-09-16T17:49:42.242166Z","shell.execute_reply.started":"2026-09-16T17:49:42.227503Z","shell.execute_reply":"2026-09-16T17:49:42.241491Z"}},"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":"2026-09-16T17:49:42.243186Z","iopub.execute_input":"2026-09-16T17:49:42.243640Z","iopub.status.idle":"2026-09-16T17:49:42.257771Z","shell.execute_reply.started":"2026-09-16T17:49:42.243617Z","shell.execute_reply":"2026-09-16T17:49:42.257084Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:42.258769Z","iopub.execute_input":"2026-09-16T17:49:42.259015Z","iopub.status.idle":"2026-09-16T17:49:42.307613Z","shell.execute_reply.started":"2026-09-16T17:49:42.258995Z","shell.execute_reply":"2026-09-16T17:49:42.306728Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:42.308694Z","iopub.execute_input":"2026-09-16T17:49:42.308943Z","iopub.status.idle":"2026-09-16T17:49:42.314169Z","shell.execute_reply.started":"2026-09-16T17:49:42.308922Z","shell.execute_reply":"2026-09-16T17:49:42.313216Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T17:49:42.315157Z","iopub.execute_input":"2026-09-16T17:49:42.315805Z","iopub.status.idle":"2026-09-16T17:49:42.321421Z","shell.execute_reply.started":"2026-09-16T17:49:42.315781Z","shell.execute_reply":"2026-09-16T17:49:42.320512Z"}},"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":"2026-09-16T17:49:42.322762Z","iopub.execute_input":"2026-09-16T17:49:42.323429Z","iopub.status.idle":"2026-09-16T18:54:18.420879Z","shell.execute_reply.started":"2026-09-16T17:49:42.323405Z","shell.execute_reply":"2026-09-16T18:54:18.419756Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:54:18.422541Z","iopub.execute_input":"2026-09-16T18:54:18.422907Z","iopub.status.idle":"2026-09-16T18:54:18.774798Z","shell.execute_reply.started":"2026-09-16T18:54:18.422870Z","shell.execute_reply":"2026-09-16T18:54:18.774098Z"}},"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":"2026-09-16T18:54:18.775792Z","iopub.execute_input":"2026-09-16T18:54:18.776099Z","iopub.status.idle":"2026-09-16T18:54:38.818780Z","shell.execute_reply.started":"2026-09-16T18:54:18.776074Z","shell.execute_reply":"2026-09-16T18:54:38.817939Z"}},"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":"2026-09-16T18:54:38.819840Z","iopub.execute_input":"2026-09-16T18:54:38.821260Z","iopub.status.idle":"2026-09-16T18:55:11.792426Z","shell.execute_reply.started":"2026-09-16T18:54:38.821233Z","shell.execute_reply":"2026-09-16T18:55:11.791635Z"}},"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":"2026-09-16T18:55:11.793627Z","iopub.execute_input":"2026-09-16T18:55:11.795645Z","iopub.status.idle":"2026-09-16T18:55:45.280226Z","shell.execute_reply.started":"2026-09-16T18:55:11.795616Z","shell.execute_reply":"2026-09-16T18:55:45.279503Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:55:45.288805Z","iopub.execute_input":"2026-09-16T18:55:45.289641Z","iopub.status.idle":"2026-09-16T18:55:45.295800Z","shell.execute_reply.started":"2026-09-16T18:55:45.289603Z","shell.execute_reply":"2026-09-16T18:55:45.294939Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:55:45.313820Z","iopub.execute_input":"2026-09-16T18:55:45.314074Z","iopub.status.idle":"2026-09-16T18:55:45.320836Z","execution_failed":"2026-09-17T00:36:16.625Z"}},"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":"2026-09-16T18:55:45.327132Z","iopub.execute_input":"2026-09-16T18:55:45.327593Z","iopub.status.idle":"2026-09-16T18:55:45.346739Z","execution_failed":"2026-09-17T00:36:16.625Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:55:45.347646Z","iopub.execute_input":"2026-09-16T18:55:45.347947Z","iopub.status.idle":"2026-09-16T18:55:45.353990Z","execution_failed":"2026-09-17T00:36:16.626Z"}},"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":"2026-09-16T18:55:45.354940Z","iopub.execute_input":"2026-09-16T18:55:45.355225Z","iopub.status.idle":"2026-09-16T18:55:46.521138Z","execution_failed":"2026-09-17T00:36:16.626Z"}},"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":"2026-09-16T18:55:46.522116Z","iopub.execute_input":"2026-09-16T18:55:46.522343Z","iopub.status.idle":"2026-09-16T18:55:54.424957Z","execution_failed":"2026-09-17T00:36:16.626Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import classification_report\nimport numpy as np\n\ntest_it.reset()\ny_pred = vgg16.predict(test_it)\ny_pred_classes = (y_pred > 0.5).astype(int)\ny_true = test_it.classes\n\n\nprint(classification_report(y_true, y_pred_classes, target_names=['Cat', 'Dog']))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T19:11:26.412414Z","iopub.execute_input":"2026-09-16T19:11:26.413135Z","iopub.status.idle":"2026-09-16T19:11:51.368760Z","shell.execute_reply.started":"2026-09-16T19:11:26.413105Z","shell.execute_reply":"2026-09-16T19:11:51.367801Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.resnet50 import ResNet50\n\ndef define_model_resnet():\n    model = ResNet50(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\n    for layer in model.layers:\n        layer.trainable = False\n    flat1 = GlobalAveragePooling2D()(model.layers[-1].output)\n    class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n    drop1 = Dropout(0.5)(class1)\n    output = Dense(1, activation='sigmoid')(drop1)\n    model = Model(inputs=model.inputs, outputs=output)\n    model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\nresnet_model = define_model_resnet()\nresnet_history = resnet_model.fit(train_it, steps_per_epoch=len(train_it), validation_data=test_it, validation_steps=len(test_it), epochs=EPOCHS, verbose=1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T19:14:07.989393Z","iopub.execute_input":"2026-09-16T19:14:07.989744Z","iopub.status.idle":"2026-09-16T20:38:52.906596Z","shell.execute_reply.started":"2026-09-16T19:14:07.989720Z","shell.execute_reply":"2026-09-16T20:38:52.905665Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:55:54.426326Z","iopub.execute_input":"2026-09-16T18:55:54.426715Z","iopub.status.idle":"2026-09-16T18:55:54.456193Z","execution_failed":"2026-09-17T00:36:16.627Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"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=(299, 299, 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(2, activation='softmax')(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":"2026-09-17T00:39:00.309956Z","iopub.execute_input":"2026-09-17T00:39:00.311028Z","iopub.status.idle":"2026-09-17T00:39:12.308189Z","shell.execute_reply.started":"2026-09-17T00:39:00.310991Z","shell.execute_reply":"2026-09-17T00:39:12.307319Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T00:39:15.672141Z","iopub.execute_input":"2026-09-17T00:39:15.673282Z","iopub.status.idle":"2026-09-17T00:39:20.797305Z","shell.execute_reply.started":"2026-09-17T00:39:15.673248Z","shell.execute_reply":"2026-09-17T00:39:20.795917Z"}},"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":"2026-09-17T00:39:31.780166Z","iopub.execute_input":"2026-09-17T00:39:31.780575Z","iopub.status.idle":"2026-09-17T00:39:31.932829Z","shell.execute_reply.started":"2026-09-17T00:39:31.780544Z","shell.execute_reply":"2026-09-17T00:39:31.931572Z"}},"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":"2026-09-17T00:39:39.120512Z","iopub.execute_input":"2026-09-17T00:39:39.121319Z","iopub.status.idle":"2026-09-17T00:39:39.148958Z","shell.execute_reply.started":"2026-09-17T00:39:39.121285Z","shell.execute_reply":"2026-09-17T00:39:39.147578Z"}},"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":"2026-09-16T18:55:54.464579Z","iopub.status.idle":"2026-09-16T18:55:54.464845Z","execution_failed":"2026-09-17T00:36:16.628Z"}},"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":"2026-09-16T18:55:54.466155Z","iopub.status.idle":"2026-09-16T18:55:54.466509Z","execution_failed":"2026-09-17T00:36:16.628Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:55:54.467825Z","iopub.status.idle":"2026-09-16T18:55:54.468083Z","execution_failed":"2026-09-17T00:36:16.628Z"}},"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":"2026-09-16T18:55:54.469167Z","iopub.status.idle":"2026-09-16T18:55:54.469423Z","execution_failed":"2026-09-17T00:36:16.629Z"}},"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":"2026-09-16T18:55:54.470856Z","iopub.status.idle":"2026-09-16T18:55:54.471116Z","execution_failed":"2026-09-17T00:36:16.629Z"}},"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":"2026-09-16T18:55:54.472230Z","iopub.status.idle":"2026-09-16T18:55:54.472544Z","execution_failed":"2026-09-17T00:36:16.629Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T18:55:54.473770Z","iopub.status.idle":"2026-09-16T18:55:54.474079Z","execution_failed":"2026-09-17T00:36:16.629Z"}},"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":"2026-09-16T18:55:54.475717Z","iopub.status.idle":"2026-09-16T18:55:54.476030Z","execution_failed":"2026-09-17T00:36:16.630Z"}},"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":"2026-09-16T18:55:54.476996Z","iopub.status.idle":"2026-09-16T18:55:54.477253Z","execution_failed":"2026-09-17T00:36:16.630Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}