{"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":"2026-09-30T15:55:22.80512Z","iopub.execute_input":"2026-09-30T15:55:22.819081Z","iopub.status.idle":"2026-09-30T15:55:23.140333Z","shell.execute_reply.started":"2026-09-30T15:55:22.819004Z","shell.execute_reply":"2026-09-30T15:55:23.026326Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:23.364744Z","iopub.execute_input":"2026-09-30T15:55:23.39491Z","iopub.status.idle":"2026-09-30T15:55:25.009745Z","shell.execute_reply.started":"2026-09-30T15:55:23.394857Z","shell.execute_reply":"2026-09-30T15:55:24.908472Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:25.086891Z","iopub.execute_input":"2026-09-30T15:55:25.087376Z","iopub.status.idle":"2026-09-30T15:55:26.609337Z","shell.execute_reply.started":"2026-09-30T15:55:25.087331Z","shell.execute_reply":"2026-09-30T15:55:26.526885Z"}},"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":"2026-09-30T15:55:26.660384Z","iopub.execute_input":"2026-09-30T15:55:26.660723Z","iopub.status.idle":"2026-09-30T15:55:38.714567Z","shell.execute_reply.started":"2026-09-30T15:55:26.660694Z","shell.execute_reply":"2026-09-30T15:55:38.713738Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:38.716887Z","iopub.execute_input":"2026-09-30T15:55:38.717215Z","iopub.status.idle":"2026-09-30T15:55:39.822454Z","shell.execute_reply.started":"2026-09-30T15:55:38.717189Z","shell.execute_reply":"2026-09-30T15:55:39.820892Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:39.824274Z","iopub.execute_input":"2026-09-30T15:55:39.824644Z","iopub.status.idle":"2026-09-30T15:55:40.880638Z","shell.execute_reply.started":"2026-09-30T15:55:39.824615Z","shell.execute_reply":"2026-09-30T15:55:40.879696Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:40.882223Z","iopub.execute_input":"2026-09-30T15:55:40.882546Z","iopub.status.idle":"2026-09-30T15:55:41.977885Z","shell.execute_reply.started":"2026-09-30T15:55:40.88252Z","shell.execute_reply":"2026-09-30T15:55:41.976887Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:41.9796Z","iopub.execute_input":"2026-09-30T15:55:41.98037Z","iopub.status.idle":"2026-09-30T15:55:43.121076Z","shell.execute_reply.started":"2026-09-30T15:55:41.980322Z","shell.execute_reply":"2026-09-30T15:55:43.119966Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:43.122572Z","iopub.execute_input":"2026-09-30T15:55:43.122892Z","iopub.status.idle":"2026-09-30T15:55:43.12752Z","shell.execute_reply.started":"2026-09-30T15:55:43.12285Z","shell.execute_reply":"2026-09-30T15:55:43.12656Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:43.128506Z","iopub.execute_input":"2026-09-30T15:55:43.129083Z","iopub.status.idle":"2026-09-30T15:55:44.266422Z","shell.execute_reply.started":"2026-09-30T15:55:43.129022Z","shell.execute_reply":"2026-09-30T15:55:44.265407Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:44.267816Z","iopub.execute_input":"2026-09-30T15:55:44.26826Z","iopub.status.idle":"2026-09-30T15:55:45.373073Z","shell.execute_reply.started":"2026-09-30T15:55:44.268228Z","shell.execute_reply":"2026-09-30T15:55:45.372118Z"}},"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":"2026-09-30T15:55:45.374592Z","iopub.execute_input":"2026-09-30T15:55:45.375358Z","iopub.status.idle":"2026-09-30T15:55:46.379781Z","shell.execute_reply.started":"2026-09-30T15:55:45.37533Z","shell.execute_reply":"2026-09-30T15:55:46.378852Z"},"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":"2026-09-30T15:55:46.381315Z","iopub.execute_input":"2026-09-30T15:55:46.381681Z","iopub.status.idle":"2026-09-30T15:55:47.377454Z","shell.execute_reply.started":"2026-09-30T15:55:46.381644Z","shell.execute_reply":"2026-09-30T15:55:47.376608Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:47.381687Z","iopub.execute_input":"2026-09-30T15:55:47.382347Z","iopub.status.idle":"2026-09-30T15:55:48.446835Z","shell.execute_reply.started":"2026-09-30T15:55:47.382315Z","shell.execute_reply":"2026-09-30T15:55:48.445511Z"}},"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":"2026-09-30T15:55:48.448905Z","iopub.execute_input":"2026-09-30T15:55:48.449335Z","iopub.status.idle":"2026-09-30T15:55:48.455276Z","shell.execute_reply.started":"2026-09-30T15:55:48.449304Z","shell.execute_reply":"2026-09-30T15:55:48.454301Z"}},"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":"2026-09-30T15:55:48.456622Z","iopub.execute_input":"2026-09-30T15:55:48.456846Z","iopub.status.idle":"2026-09-30T15:55:48.466748Z","shell.execute_reply.started":"2026-09-30T15:55:48.456826Z","shell.execute_reply":"2026-09-30T15:55:48.465953Z"},"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":"2026-09-30T15:55:48.467964Z","iopub.execute_input":"2026-09-30T15:55:48.468686Z","iopub.status.idle":"2026-09-30T15:55:48.475204Z","shell.execute_reply.started":"2026-09-30T15:55:48.468661Z","shell.execute_reply":"2026-09-30T15:55:48.474359Z"},"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":"2026-09-30T15:55:48.476395Z","iopub.execute_input":"2026-09-30T15:55:48.47716Z","iopub.status.idle":"2026-09-30T15:55:48.489371Z","shell.execute_reply.started":"2026-09-30T15:55:48.477137Z","shell.execute_reply":"2026-09-30T15:55:48.48846Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:48.490524Z","iopub.execute_input":"2026-09-30T15:55:48.491382Z","iopub.status.idle":"2026-09-30T15:55:49.553344Z","shell.execute_reply.started":"2026-09-30T15:55:48.491359Z","shell.execute_reply":"2026-09-30T15:55:49.552199Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:49.554829Z","iopub.execute_input":"2026-09-30T15:55:49.555233Z","iopub.status.idle":"2026-09-30T15:55:50.648799Z","shell.execute_reply.started":"2026-09-30T15:55:49.5552Z","shell.execute_reply":"2026-09-30T15:55:50.647397Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:50.650857Z","iopub.execute_input":"2026-09-30T15:55:50.65153Z","iopub.status.idle":"2026-09-30T15:55:51.717232Z","shell.execute_reply.started":"2026-09-30T15:55:50.6515Z","shell.execute_reply":"2026-09-30T15:55:51.716144Z"}},"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":"2026-09-30T15:55:51.718713Z","iopub.execute_input":"2026-09-30T15:55:51.719037Z","iopub.status.idle":"2026-09-30T15:55:55.550281Z","shell.execute_reply.started":"2026-09-30T15:55:51.719009Z","shell.execute_reply":"2026-09-30T15:55:55.549463Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:55:55.551396Z","iopub.execute_input":"2026-09-30T15:55:55.551686Z","iopub.status.idle":"2026-09-30T15:55:55.556495Z","shell.execute_reply.started":"2026-09-30T15:55:55.55166Z","shell.execute_reply":"2026-09-30T15:55:55.555657Z"}},"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":"2026-09-30T15:55:55.557824Z","iopub.execute_input":"2026-09-30T15:55:55.558207Z","iopub.status.idle":"2026-09-30T15:55:57.842382Z","shell.execute_reply.started":"2026-09-30T15:55:55.55817Z","shell.execute_reply":"2026-09-30T15:55:57.841284Z"},"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":"2026-09-30T15:55:57.843976Z","iopub.execute_input":"2026-09-30T15:55:57.844788Z","iopub.status.idle":"2026-09-30T15:56:00.12253Z","shell.execute_reply.started":"2026-09-30T15:55:57.844757Z","shell.execute_reply":"2026-09-30T15:56:00.121375Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-30T15:56:00.124274Z","iopub.execute_input":"2026-09-30T15:56:00.125148Z","iopub.status.idle":"2026-09-30T15:56:08.88062Z","shell.execute_reply.started":"2026-09-30T15:56:00.125118Z","shell.execute_reply":"2026-09-30T15:56:08.879164Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-30T15:56:08.882492Z","iopub.execute_input":"2026-09-30T15:56:08.882839Z","iopub.status.idle":"2026-09-30T15:56:08.888032Z","shell.execute_reply.started":"2026-09-30T15:56:08.882811Z","shell.execute_reply":"2026-09-30T15:56:08.887033Z"},"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":"2026-09-30T15:56:08.88911Z","iopub.execute_input":"2026-09-30T15:56:08.889353Z","iopub.status.idle":"2026-09-30T15:56:08.903925Z","shell.execute_reply.started":"2026-09-30T15:56:08.889332Z","shell.execute_reply":"2026-09-30T15:56:08.902832Z"}},"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":"2026-09-30T15:56:08.905311Z","iopub.execute_input":"2026-09-30T15:56:08.90586Z","iopub.status.idle":"2026-09-30T15:56:08.919534Z","shell.execute_reply.started":"2026-09-30T15:56:08.905835Z","shell.execute_reply":"2026-09-30T15:56:08.918616Z"}},"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":"2026-09-30T15:56:08.920707Z","iopub.execute_input":"2026-09-30T15:56:08.921377Z","iopub.status.idle":"2026-09-30T15:56:08.934075Z","shell.execute_reply.started":"2026-09-30T15:56:08.921338Z","shell.execute_reply":"2026-09-30T15:56:08.932945Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:56:08.935444Z","iopub.execute_input":"2026-09-30T15:56:08.935782Z","iopub.status.idle":"2026-09-30T15:56:09.009463Z","shell.execute_reply.started":"2026-09-30T15:56:08.935759Z","shell.execute_reply":"2026-09-30T15:56:09.00861Z"}},"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":"2026-09-30T15:56:09.01081Z","iopub.execute_input":"2026-09-30T15:56:09.011189Z","iopub.status.idle":"2026-09-30T15:56:09.020261Z","shell.execute_reply.started":"2026-09-30T15:56:09.011141Z","shell.execute_reply":"2026-09-30T15:56:09.019118Z"}},"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":"2026-09-30T15:56:09.021364Z","iopub.execute_input":"2026-09-30T15:56:09.022255Z","iopub.status.idle":"2026-09-30T15:56:09.089318Z","shell.execute_reply.started":"2026-09-30T15:56:09.022221Z","shell.execute_reply":"2026-09-30T15:56:09.08834Z"}},"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\nmy_outputs = Dense(1, activation='sigmoid')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(\n    inputs=my_inputs,\n    outputs=my_outputs\n)\n\n# Compile the model\nmodel.compile(\n    loss='binary_crossentropy',\n    optimizer='adam',\n    metrics=['accuracy']\n)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:56:09.090646Z","iopub.execute_input":"2026-09-30T15:56:09.090992Z","iopub.status.idle":"2026-09-30T15:56:09.170573Z","shell.execute_reply.started":"2026-09-30T15:56:09.090957Z","shell.execute_reply":"2026-09-30T15:56:09.169579Z"}},"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":"2026-09-30T15:56:09.172039Z","iopub.execute_input":"2026-09-30T15:56:09.172353Z","iopub.status.idle":"2026-09-30T15:56:09.260677Z","shell.execute_reply.started":"2026-09-30T15:56:09.172328Z","shell.execute_reply":"2026-09-30T15:56:09.256796Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:56:09.261735Z","iopub.execute_input":"2026-09-30T15:56:09.262002Z","iopub.status.idle":"2026-09-30T15:56:09.26836Z","shell.execute_reply.started":"2026-09-30T15:56:09.26198Z","shell.execute_reply":"2026-09-30T15:56:09.267331Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:56:09.269725Z","iopub.execute_input":"2026-09-30T15:56:09.270172Z","iopub.status.idle":"2026-09-30T15:56:10.360982Z","shell.execute_reply.started":"2026-09-30T15:56:09.27012Z","shell.execute_reply":"2026-09-30T15:56:10.35998Z"}},"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":"2026-09-30T15:56:10.36258Z","iopub.execute_input":"2026-09-30T15:56:10.362893Z","iopub.status.idle":"2026-09-30T15:56:10.368032Z","shell.execute_reply.started":"2026-09-30T15:56:10.362866Z","shell.execute_reply":"2026-09-30T15:56:10.366819Z"}},"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":"2026-09-30T15:56:10.369607Z","iopub.execute_input":"2026-09-30T15:56:10.369963Z","iopub.status.idle":"2026-09-30T15:58:26.333486Z","shell.execute_reply.started":"2026-09-30T15:56:10.369928Z","shell.execute_reply":"2026-09-30T15:58:26.332529Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# =============================================================================\n# Dogs vs Cats — data pipeline with a switchable stratified 10% sample\n#\n# Paste each BLOCK into its own notebook cell, in order.\n# To switch corpora, edit exactly one line: DATA_MODE in BLOCK 0.\n# =============================================================================\n\n\n# =============================================================================\n# BLOCK 0 — CONFIG\n# =============================================================================\nimport os\nimport json\nimport math\nimport random\nimport shutil\nimport time\n\nimport numpy as np\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\nDATA_MODE       = 'sample'   # 'full' | 'sample'   <- the only line you edit\nSAMPLE_FRACTION = 0.15       # ignored when DATA_MODE == 'full'\nVAL_SPLIT       = 0.2\nSEED            = 42\n\nBATCH_SIZE = 32              # keep your existing values\nIMAGE_SIZE = 224\n\nFULL_TRAIN_PATH = ('/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset'\n                   '/dataset_dogs_vs_cats/train')\nSAMPLE_ROOT     = '/kaggle/working/sample_train'\nMANIFEST_NAME   = '.sample_manifest.json'\n\nassert DATA_MODE in ('full', 'sample'), f\"DATA_MODE must be 'full' or 'sample', got {DATA_MODE!r}\"\n\n# sorted() matches the alphabetical ordering flow_from_directory uses internally,\n# so passing this as `classes=` locks the mapping to {'cats': 0, 'dogs': 1}.\nCLASS_NAMES = sorted(d for d in os.listdir(FULL_TRAIN_PATH)\n                     if os.path.isdir(os.path.join(FULL_TRAIN_PATH, d)))\n\nprint(f'DATA_MODE      : {DATA_MODE}')\nprint(f'classes        : {CLASS_NAMES}')\nprint(f'seed           : {SEED}')\n\n\n# =============================================================================\n# BLOCK 1 — BUILD THE STRATIFIED SUBSET TREE   (runs only when DATA_MODE == 'sample')\n#\n# Per-class sampling IS the stratification: taking round(N_c * fraction) files from\n# each class directory preserves the original class proportions by construction.\n# The tree is made of symlinks, so it costs no disk and takes seconds. It must live\n# under /kaggle/working because /kaggle/input is read-only.\n# =============================================================================\nIMG_EXT = ('.jpg', '.jpeg', '.png', '.bmp', '.ppm', '.tif', '.tiff', '.gif')\n\n\ndef list_class_files(root, cls):\n    \"\"\"Sorted image filenames for one class, so the listing order is not FS-dependent.\"\"\"\n    d = os.path.join(root, cls)\n    return sorted(f for f in os.listdir(d) if f.lower().endswith(IMG_EXT))\n\n\ndef build_stratified_sample(src_root, dst_root, classes, fraction, seed):\n    manifest_path = os.path.join(dst_root, MANIFEST_NAME)\n    wanted = {'source': src_root, 'fraction': fraction, 'seed': seed, 'classes': list(classes)}\n\n    if os.path.isdir(dst_root):\n        # Safety guard: only ever delete a tree this function created.\n        if not os.path.exists(manifest_path):\n            raise RuntimeError(\n                f'{dst_root} exists but has no {MANIFEST_NAME}; refusing to delete it. '\n                'Point SAMPLE_ROOT somewhere else or remove that directory yourself.')\n        with open(manifest_path) as fh:\n            old = json.load(fh)\n        if all(old.get(k) == v for k, v in wanted.items()):\n            print(f'reusing existing sample at {dst_root}')\n            for cls, c in old['counts'].items():\n                print(f\"  {cls:<10} {c['sampled']:>6} / {c['available']:>6}\")\n            return dst_root\n        print(f'config changed -> rebuilding {dst_root}')\n        shutil.rmtree(dst_root)\n\n    rng = random.Random(seed)          # one stream, so the whole draw is reproducible\n    counts, symlinked = {}, True\n\n    for cls in classes:\n        files = list_class_files(src_root, cls)\n        n = max(1, round(len(files) * fraction))\n        picked = rng.sample(files, n)\n\n        outdir = os.path.join(dst_root, cls)\n        os.makedirs(outdir, exist_ok=True)\n        for fname in picked:\n            # abspath matters: a relative symlink target is resolved relative to the\n            # LINK's directory, not the cwd, which would silently produce dead links.\n            src = os.path.abspath(os.path.join(src_root, cls, fname))\n            dst = os.path.join(outdir, fname)\n            try:\n                os.symlink(src, dst)\n            except (OSError, NotImplementedError, AttributeError):\n                shutil.copy2(src, dst)  # filesystem without symlink support\n                symlinked = False\n\n        counts[cls] = {'sampled': n, 'available': len(files)}\n        print(f'  {cls:<10} {n:>6} / {len(files):>6}  ({n / len(files):.1%})')\n\n    manifest = dict(wanted,\n                    counts=counts,\n                    symlinked=symlinked,\n                    created=time.strftime('%Y-%m-%d %H:%M:%S'))\n    with open(manifest_path, 'w') as fh:\n        json.dump(manifest, fh, indent=2)\n\n    print(f'built {dst_root}  (symlinked={symlinked})')\n    return dst_root\n\n\nif DATA_MODE == 'sample':\n    build_stratified_sample(FULL_TRAIN_PATH, SAMPLE_ROOT,\n                            CLASS_NAMES, SAMPLE_FRACTION, SEED)\nelse:\n    print('DATA_MODE=full -> skipping sample build')\n\n\n# =============================================================================\n# BLOCK 2 — SELECT THE ACTIVE CORPUS\n# Everything downstream reads TRAIN_DIR and is identical between the two modes.\n# =============================================================================\nTRAIN_DIR = SAMPLE_ROOT if DATA_MODE == 'sample' else FULL_TRAIN_PATH\nprint(f'TRAIN_DIR = {TRAIN_DIR}')\n\n\n# =============================================================================\n# BLOCK 3 — TWO GENERATORS\n#\n# Augmentation on train only. The original code shared one generator, so validation\n# images were randomly flipped every epoch: val metrics wobbled for no modelling\n# reason and the confusion matrix was computed on augmented inputs.\n#\n# Both generators MUST carry the same validation_split. flow_from_directory\n# partitions by slicing the sorted filename list *within each class directory*, so\n# the 80/20 split is itself stratified, is deterministic, and is unaffected by\n# `seed` — two separate instances therefore yield identical, non-overlapping\n# partitions. BLOCK 5 asserts this rather than trusting it.\n# =============================================================================\ntrain_datagen = ImageDataGenerator(\n    rescale=1.0 / 255.0,\n    horizontal_flip=True,\n    validation_split=VAL_SPLIT,\n)\n\nval_datagen = ImageDataGenerator(\n    rescale=1.0 / 255.0,          # no augmentation\n    validation_split=VAL_SPLIT,\n)\n\n\n# =============================================================================\n# BLOCK 4 — THE TWO ITERATORS\n# =============================================================================\ntrain_it = train_datagen.flow_from_directory(\n    TRAIN_DIR,\n    classes=CLASS_NAMES,          # lock the label mapping explicitly\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='training',\n    shuffle=True,\n    seed=SEED,\n)\n\nval_it = val_datagen.flow_from_directory(\n    TRAIN_DIR,\n    classes=CLASS_NAMES,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='validation',\n    shuffle=False,                # keep index alignment for the confusion matrix\n)\n\n\n# =============================================================================\n# BLOCK 5 — VERIFICATION (print + assert)\n# =============================================================================\ndef class_counts(it):\n    n = np.bincount(it.classes, minlength=len(CLASS_NAMES))\n    return {cls: int(c) for cls, c in zip(CLASS_NAMES, n)}\n\n\nfull_total   = sum(len(list_class_files(FULL_TRAIN_PATH, c)) for c in CLASS_NAMES)\nactive_total = sum(len(list_class_files(TRAIN_DIR, c)) for c in CLASS_NAMES)\n\nprint(f'class_indices  : {train_it.class_indices}')\nprint(f'full train set : {full_total}')\nprint(f'active corpus  : {active_total}  ({active_total / full_total:.1%} of full)')\nprint(f'train          : {train_it.samples:>6}  {class_counts(train_it)}')\nprint(f'val            : {val_it.samples:>6}  {class_counts(val_it)}')\n\nassert train_it.class_indices == {c: i for i, c in enumerate(CLASS_NAMES)}\nassert val_it.class_indices == train_it.class_indices\nassert not (set(train_it.filenames) & set(val_it.filenames)), 'train/val leakage'\nassert train_it.samples + val_it.samples == active_total, 'iterators lost files'\n\n# class balance must survive the sampling\nfor cls, c in class_counts(train_it).items():\n    share = c / train_it.samples\n    assert abs(share - 1 / len(CLASS_NAMES)) < 0.05, f'{cls} is imbalanced in train: {share:.1%}'\n\nprint('all checks passed')\n\n\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:26.334836Z","iopub.execute_input":"2026-09-30T15:58:26.335273Z","iopub.status.idle":"2026-09-30T15:58:26.650774Z","shell.execute_reply.started":"2026-09-30T15:58:26.335247Z","shell.execute_reply":"2026-09-30T15:58:26.649863Z"}},"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":"2026-09-30T15:58:26.659594Z","iopub.execute_input":"2026-09-30T15:58:26.660256Z","iopub.status.idle":"2026-09-30T15:58:26.668172Z","shell.execute_reply.started":"2026-09-30T15:58:26.660228Z","shell.execute_reply":"2026-09-30T15:58:26.667305Z"}},"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":"2026-09-30T15:58:26.6696Z","iopub.execute_input":"2026-09-30T15:58:26.669949Z","iopub.status.idle":"2026-09-30T15:58:26.683293Z","shell.execute_reply.started":"2026-09-30T15:58:26.669923Z","shell.execute_reply":"2026-09-30T15:58:26.682369Z"}},"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":"2026-09-30T15:58:26.684608Z","iopub.execute_input":"2026-09-30T15:58:26.685426Z","iopub.status.idle":"2026-09-30T15:58:26.69678Z","shell.execute_reply.started":"2026-09-30T15:58:26.685393Z","shell.execute_reply":"2026-09-30T15:58:26.695996Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:26.697922Z","iopub.execute_input":"2026-09-30T15:58:26.698266Z","iopub.status.idle":"2026-09-30T15:58:26.710721Z","shell.execute_reply.started":"2026-09-30T15:58:26.698242Z","shell.execute_reply":"2026-09-30T15:58:26.709938Z"}},"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":"2026-09-30T15:58:26.711777Z","iopub.execute_input":"2026-09-30T15:58:26.712884Z","iopub.status.idle":"2026-09-30T15:58:26.72334Z","shell.execute_reply.started":"2026-09-30T15:58:26.71285Z","shell.execute_reply":"2026-09-30T15:58:26.722346Z"}},"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":"2026-09-30T15:58:26.724462Z","iopub.execute_input":"2026-09-30T15:58:26.724771Z","iopub.status.idle":"2026-09-30T15:58:27.835554Z","shell.execute_reply.started":"2026-09-30T15:58:26.72474Z","shell.execute_reply":"2026-09-30T15:58:27.834432Z"}},"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":"2026-09-30T15:58:27.837691Z","iopub.execute_input":"2026-09-30T15:58:27.83813Z","iopub.status.idle":"2026-09-30T15:58:27.844847Z","shell.execute_reply.started":"2026-09-30T15:58:27.838089Z","shell.execute_reply":"2026-09-30T15:58:27.84381Z"}},"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":"2026-09-30T15:58:27.84646Z","iopub.execute_input":"2026-09-30T15:58:27.846769Z","iopub.status.idle":"2026-09-30T15:58:27.858397Z","shell.execute_reply.started":"2026-09-30T15:58:27.846738Z","shell.execute_reply":"2026-09-30T15:58:27.857544Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:27.859814Z","iopub.execute_input":"2026-09-30T15:58:27.860802Z","iopub.status.idle":"2026-09-30T15:58:27.870848Z","shell.execute_reply.started":"2026-09-30T15:58:27.860775Z","shell.execute_reply":"2026-09-30T15:58:27.869864Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:27.872022Z","iopub.execute_input":"2026-09-30T15:58:27.872383Z","iopub.status.idle":"2026-09-30T15:58:27.88478Z","shell.execute_reply.started":"2026-09-30T15:58:27.872351Z","shell.execute_reply":"2026-09-30T15:58:27.88382Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:27.886121Z","iopub.execute_input":"2026-09-30T15:58:27.886496Z","iopub.status.idle":"2026-09-30T15:58:27.902151Z","shell.execute_reply.started":"2026-09-30T15:58:27.88647Z","shell.execute_reply":"2026-09-30T15:58:27.901101Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:27.903583Z","iopub.execute_input":"2026-09-30T15:58:27.903871Z","iopub.status.idle":"2026-09-30T15:58:27.910195Z","shell.execute_reply.started":"2026-09-30T15:58:27.903849Z","shell.execute_reply":"2026-09-30T15:58:27.908833Z"}},"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":"2026-09-30T15:58:27.91139Z","iopub.execute_input":"2026-09-30T15:58:27.911693Z","iopub.status.idle":"2026-09-30T15:58:27.925747Z","shell.execute_reply.started":"2026-09-30T15:58:27.911669Z","shell.execute_reply":"2026-09-30T15:58:27.924557Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:58:27.927197Z","iopub.execute_input":"2026-09-30T15:58:27.927596Z","iopub.status.idle":"2026-09-30T15:58:27.942928Z","shell.execute_reply.started":"2026-09-30T15:58:27.927568Z","shell.execute_reply":"2026-09-30T15:58:27.941863Z"}},"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":"2026-09-30T15:58:27.944506Z","iopub.execute_input":"2026-09-30T15:58:27.944881Z","iopub.status.idle":"2026-09-30T15:58:47.268489Z","shell.execute_reply.started":"2026-09-30T15:58:27.944842Z","shell.execute_reply":"2026-09-30T15:58:47.267557Z"}},"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":"2026-09-30T15:58:47.269626Z","iopub.execute_input":"2026-09-30T15:58:47.269945Z","iopub.status.idle":"2026-09-30T15:58:47.276083Z","shell.execute_reply.started":"2026-09-30T15:58:47.269919Z","shell.execute_reply":"2026-09-30T15:58:47.27522Z"}},"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":"2026-09-30T15:58:47.27722Z","iopub.execute_input":"2026-09-30T15:58:47.277506Z","iopub.status.idle":"2026-09-30T15:58:53.588272Z","shell.execute_reply.started":"2026-09-30T15:58:47.277466Z","shell.execute_reply":"2026-09-30T15:58:53.586746Z"}},"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":"2026-09-30T15:58:53.589438Z","iopub.execute_input":"2026-09-30T15:58:53.589802Z","iopub.status.idle":"2026-09-30T15:58:59.865826Z","shell.execute_reply.started":"2026-09-30T15:58:53.589774Z","shell.execute_reply":"2026-09-30T15:58:59.864619Z"}},"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[:len(sample_images)]):\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":"2026-09-30T15:58:59.867126Z","iopub.execute_input":"2026-09-30T15:58:59.867526Z","iopub.status.idle":"2026-09-30T15:58:59.874269Z","shell.execute_reply.started":"2026-09-30T15:58:59.867498Z","shell.execute_reply":"2026-09-30T15:58:59.872975Z"}},"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":"2026-09-30T15:58:59.875525Z","iopub.execute_input":"2026-09-30T15:58:59.875843Z","iopub.status.idle":"2026-09-30T15:59:05.503749Z","shell.execute_reply.started":"2026-09-30T15:58:59.875818Z","shell.execute_reply":"2026-09-30T15:59:05.502811Z"}},"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":"2026-09-30T15:59:05.505027Z","iopub.execute_input":"2026-09-30T15:59:05.505374Z","iopub.status.idle":"2026-09-30T15:59:05.510379Z","shell.execute_reply.started":"2026-09-30T15:59:05.505343Z","shell.execute_reply":"2026-09-30T15:59:05.509634Z"}},"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":"2026-09-30T15:59:05.511916Z","iopub.execute_input":"2026-09-30T15:59:05.512569Z","iopub.status.idle":"2026-09-30T15:59:05.525123Z","shell.execute_reply.started":"2026-09-30T15:59:05.512528Z","shell.execute_reply":"2026-09-30T15:59:05.524037Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:05.526175Z","iopub.execute_input":"2026-09-30T15:59:05.526588Z","iopub.status.idle":"2026-09-30T15:59:05.539415Z","shell.execute_reply.started":"2026-09-30T15:59:05.526552Z","shell.execute_reply":"2026-09-30T15:59:05.538505Z"}},"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":"2026-09-30T15:59:05.540912Z","iopub.execute_input":"2026-09-30T15:59:05.54128Z","iopub.status.idle":"2026-09-30T15:59:05.948949Z","shell.execute_reply.started":"2026-09-30T15:59:05.541253Z","shell.execute_reply":"2026-09-30T15:59:05.948119Z"}},"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":"2026-09-30T15:59:05.950186Z","iopub.execute_input":"2026-09-30T15:59:05.950569Z","iopub.status.idle":"2026-09-30T15:59:08.438513Z","shell.execute_reply.started":"2026-09-30T15:59:05.950542Z","shell.execute_reply":"2026-09-30T15:59:08.437439Z"}},"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":"2026-09-30T15:59:08.439832Z","iopub.execute_input":"2026-09-30T15:59:08.440257Z","iopub.status.idle":"2026-09-30T15:59:08.841626Z","shell.execute_reply.started":"2026-09-30T15:59:08.440229Z","shell.execute_reply":"2026-09-30T15:59:08.83932Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n\t\tprint(index, \n              layer.name,\n              layer.trainable,\n              layer.output.shape\n        )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.843727Z","iopub.execute_input":"2026-09-30T15:59:08.844029Z","iopub.status.idle":"2026-09-30T15:59:08.849796Z","shell.execute_reply.started":"2026-09-30T15:59:08.844003Z","shell.execute_reply":"2026-09-30T15:59:08.848825Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n    if index <= 14:\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":"2026-09-30T15:59:08.85106Z","iopub.execute_input":"2026-09-30T15:59:08.851442Z","iopub.status.idle":"2026-09-30T15:59:08.865411Z","shell.execute_reply.started":"2026-09-30T15:59:08.851406Z","shell.execute_reply":"2026-09-30T15:59:08.864462Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.866503Z","iopub.execute_input":"2026-09-30T15:59:08.867112Z","iopub.status.idle":"2026-09-30T15:59:08.881433Z","shell.execute_reply.started":"2026-09-30T15:59:08.86704Z","shell.execute_reply":"2026-09-30T15:59:08.880582Z"}},"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":"2026-09-30T15:59:08.882994Z","iopub.execute_input":"2026-09-30T15:59:08.883331Z","iopub.status.idle":"2026-09-30T15:59:08.89745Z","shell.execute_reply.started":"2026-09-30T15:59:08.883306Z","shell.execute_reply":"2026-09-30T15:59:08.896314Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"layer1 = Dense(256, activation='relu', kernel_initializer='he_uniform')(flat1)\nprint(layer1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.898619Z","iopub.execute_input":"2026-09-30T15:59:08.899361Z","iopub.status.idle":"2026-09-30T15:59:08.924478Z","shell.execute_reply.started":"2026-09-30T15:59:08.899313Z","shell.execute_reply":"2026-09-30T15:59:08.92338Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"layer2 = Dense(128, activation='relu', kernel_initializer='he_uniform')(layer1)\nprint(layer2.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.925875Z","iopub.execute_input":"2026-09-30T15:59:08.926258Z","iopub.status.idle":"2026-09-30T15:59:08.94267Z","shell.execute_reply.started":"2026-09-30T15:59:08.926223Z","shell.execute_reply":"2026-09-30T15:59:08.941879Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output1 = Dense(2, activation='softmax')(layer2)\nprint(f\"{output1.shape=}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.943823Z","iopub.execute_input":"2026-09-30T15:59:08.944461Z","iopub.status.idle":"2026-09-30T15:59:08.960318Z","shell.execute_reply.started":"2026-09-30T15:59:08.944435Z","shell.execute_reply":"2026-09-30T15:59:08.959131Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output2 = Dense(1, activation='sigmoid')(layer2)\nprint(output2.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.961504Z","iopub.execute_input":"2026-09-30T15:59:08.961779Z","iopub.status.idle":"2026-09-30T15:59:08.977945Z","shell.execute_reply.started":"2026-09-30T15:59:08.961756Z","shell.execute_reply":"2026-09-30T15:59:08.976794Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define new model to be trained\nmodel_vgg16 = Model(inputs=model_16_feature_extractor.inputs, outputs=output2)\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":"2026-09-30T15:59:08.979127Z","iopub.execute_input":"2026-09-30T15:59:08.979449Z","iopub.status.idle":"2026-09-30T15:59:08.996466Z","shell.execute_reply.started":"2026-09-30T15:59:08.979417Z","shell.execute_reply":"2026-09-30T15:59:08.995306Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_vgg16.layers):\n    print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:08.997739Z","iopub.execute_input":"2026-09-30T15:59:08.998103Z","iopub.status.idle":"2026-09-30T15:59:09.004182Z","shell.execute_reply.started":"2026-09-30T15:59:08.998067Z","shell.execute_reply":"2026-09-30T15:59:09.002934Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:09.005452Z","iopub.execute_input":"2026-09-30T15:59:09.006102Z","iopub.status.idle":"2026-09-30T15:59:09.059736Z","shell.execute_reply.started":"2026-09-30T15:59:09.006051Z","shell.execute_reply":"2026-09-30T15:59:09.058908Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:09.06087Z","iopub.execute_input":"2026-09-30T15:59:09.061211Z","iopub.status.idle":"2026-09-30T15:59:09.067234Z","shell.execute_reply.started":"2026-09-30T15:59:09.061178Z","shell.execute_reply":"2026-09-30T15:59:09.066223Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# del ตัวแปร #ลบตัวแปรออกจากหน่วยความจำ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:09.068517Z","iopub.execute_input":"2026-09-30T15:59:09.068885Z","iopub.status.idle":"2026-09-30T15:59:09.077852Z","shell.execute_reply.started":"2026-09-30T15:59:09.068847Z","shell.execute_reply":"2026-09-30T15:59:09.076964Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:09.07896Z","iopub.execute_input":"2026-09-30T15:59:09.079313Z","iopub.status.idle":"2026-09-30T15:59:09.089163Z","shell.execute_reply.started":"2026-09-30T15:59:09.079281Z","shell.execute_reply":"2026-09-30T15:59:09.08812Z"}},"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=20, \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=2, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T15:59:09.091514Z","iopub.execute_input":"2026-09-30T15:59:09.091824Z","iopub.status.idle":"2026-09-30T16:04:17.543963Z","shell.execute_reply.started":"2026-09-30T15:59:09.091801Z","shell.execute_reply":"2026-09-30T16:04:17.542815Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:04:17.545471Z","iopub.execute_input":"2026-09-30T16:04:17.545848Z","iopub.status.idle":"2026-09-30T16:04:17.87734Z","shell.execute_reply.started":"2026-09-30T16:04:17.545801Z","shell.execute_reply":"2026-09-30T16:04:17.876219Z"}},"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":"2026-09-30T16:04:17.878596Z","iopub.execute_input":"2026-09-30T16:04:17.878962Z","iopub.status.idle":"2026-09-30T16:04:20.574929Z","shell.execute_reply.started":"2026-09-30T16:04:17.87893Z","shell.execute_reply":"2026-09-30T16:04:20.573932Z"}},"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":"2026-09-30T16:04:20.576195Z","iopub.execute_input":"2026-09-30T16:04:20.576545Z","iopub.status.idle":"2026-09-30T16:05:18.573494Z","shell.execute_reply.started":"2026-09-30T16:04:20.576511Z","shell.execute_reply":"2026-09-30T16:05:18.572264Z"}},"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":"2026-09-30T16:05:18.5749Z","iopub.execute_input":"2026-09-30T16:05:18.575305Z","iopub.status.idle":"2026-09-30T16:05:46.646741Z","shell.execute_reply.started":"2026-09-30T16:05:18.57526Z","shell.execute_reply":"2026-09-30T16:05:46.645615Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:05:46.64855Z","iopub.execute_input":"2026-09-30T16:05:46.649152Z","iopub.status.idle":"2026-09-30T16:05:46.656252Z","shell.execute_reply.started":"2026-09-30T16:05:46.649115Z","shell.execute_reply":"2026-09-30T16:05:46.655394Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:05:46.657348Z","iopub.execute_input":"2026-09-30T16:05:46.658018Z","iopub.status.idle":"2026-09-30T16:05:46.666934Z","shell.execute_reply.started":"2026-09-30T16:05:46.657992Z","shell.execute_reply":"2026-09-30T16:05:46.666023Z"}},"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":"2026-09-30T16:05:46.66822Z","iopub.execute_input":"2026-09-30T16:05:46.668656Z","iopub.status.idle":"2026-09-30T16:05:46.697908Z","shell.execute_reply.started":"2026-09-30T16:05:46.668617Z","shell.execute_reply":"2026-09-30T16:05:46.696906Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:05:46.69906Z","iopub.execute_input":"2026-09-30T16:05:46.700221Z","iopub.status.idle":"2026-09-30T16:05:46.706399Z","shell.execute_reply.started":"2026-09-30T16:05:46.700195Z","shell.execute_reply":"2026-09-30T16:05:46.705378Z"}},"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(\n    all_images.shape[0],\n    size=min(100, all_images.shape[0]),\n    replace=False\n)\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":"2026-09-30T16:05:46.707838Z","iopub.execute_input":"2026-09-30T16:05:46.708245Z","iopub.status.idle":"2026-09-30T16:05:47.477204Z","shell.execute_reply.started":"2026-09-30T16:05:46.708207Z","shell.execute_reply":"2026-09-30T16:05:47.476439Z"}},"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, ax in enumerate(axes.flat):\n\n    if i >= len(sample_images):\n        ax.axis('off')\n        continue\n\n    img = sample_images[i]\n\n    # Normalize image for display\n    if img.max() > 1.0 or img.min() < 0:\n        img = (img - img.min()) / (img.max() - img.min())\n\n    gt_class = class_mapping[int(sample_labels[i])]\n    pred_class = class_mapping[int(predictions[i])]\n    prob = probabilities[i]\n\n    text_color = (\n        'darkgreen'\n        if gt_class == pred_class\n        else 'darkred'\n    )\n\n    title_str = (\n        f\"GT: {gt_class}\\n\"\n        f\"Pred: {pred_class}\\n\"\n        f\"Prob: {prob:.3f}\"\n    )\n\n    ax.imshow(img)\n    ax.set_title(\n        title_str,\n        color=text_color,\n        fontsize=9,\n        pad=4\n    )\n    ax.axis('off')\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:05:47.478194Z","iopub.execute_input":"2026-09-30T16:05:47.478707Z","iopub.status.idle":"2026-09-30T16:05:53.951727Z","shell.execute_reply.started":"2026-09-30T16:05:47.47868Z","shell.execute_reply":"2026-09-30T16:05:53.947598Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import GlobalAveragePooling2D, Dense\nfrom tensorflow.keras.optimizers import SGD\n\ndef define_model_inceptionv3():\n\n    # load pre-trained model\n    base_model = InceptionV3(\n        weights='imagenet',\n        include_top=False,\n        input_shape=(224, 224, 3)\n    )\n\n    # freeze pre-trained layers\n    for layer in base_model.layers:\n        layer.trainable = False\n\n    # classification layers\n    x = base_model.output\n    x = GlobalAveragePooling2D()(x)\n    x = Dense(\n        128,\n        activation='relu',\n        kernel_initializer='he_uniform'\n    )(x)\n\n    output = Dense(1, activation='sigmoid')(x)\n\n    model = Model(\n        inputs=base_model.input,\n        outputs=output\n    )\n\n    opt = SGD(\n        learning_rate=0.001,\n        momentum=0.9\n    )\n\n    model.compile(\n        optimizer=opt,\n        loss='binary_crossentropy',\n        metrics=['accuracy']\n    )\n\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:07:02.087808Z","iopub.execute_input":"2026-09-30T16:07:02.08846Z","iopub.status.idle":"2026-09-30T16:07:02.095306Z","shell.execute_reply.started":"2026-09-30T16:07:02.088429Z","shell.execute_reply":"2026-09-30T16:07:02.094322Z"}},"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":"2026-09-30T16:07:05.070794Z","iopub.execute_input":"2026-09-30T16:07:05.07159Z","iopub.status.idle":"2026-09-30T16:07:07.341766Z","shell.execute_reply.started":"2026-09-30T16:07:05.071551Z","shell.execute_reply":"2026-09-30T16:07:07.340945Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications import MobileNetV2\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import GlobalAveragePooling2D, Dense\nfrom tensorflow.keras.optimizers import Adam\n\n# Load pre-trained MobileNetV2\nbase_model_mobilenet = MobileNetV2(\n    weights='imagenet',\n    include_top=False,\n    input_shape=(224, 224, 3)\n)\n\n# Freeze pre-trained layers\nfor layer in base_model_mobilenet.layers:\n    layer.trainable = False\n\n# Add classification layers\nx = base_model_mobilenet.output\nx = GlobalAveragePooling2D()(x)\nx = Dense(128, activation='relu')(x)\n\noutput = Dense(\n    1,\n    activation='sigmoid'\n)(x)\n\n# Create model\nmodel_mobilenet = Model(\n    inputs=base_model_mobilenet.input,\n    outputs=output\n)\n\n# Compile\nmodel_mobilenet.compile(\n    optimizer=Adam(learning_rate=0.001),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\nprint(model_mobilenet.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:16:42.800988Z","iopub.execute_input":"2026-09-30T16:16:42.801759Z","iopub.status.idle":"2026-09-30T16:16:44.743886Z","shell.execute_reply.started":"2026-09-30T16:16:42.801721Z","shell.execute_reply":"2026-09-30T16:16:44.742223Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history_mobilenet = model_mobilenet.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=10,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:17:12.511894Z","iopub.execute_input":"2026-09-30T16:17:12.512785Z","iopub.status.idle":"2026-09-30T16:19:04.207985Z","shell.execute_reply.started":"2026-09-30T16:17:12.51275Z","shell.execute_reply":"2026-09-30T16:19:04.206904Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\n# Reset test generator\ntest_it.reset()\n\n# True labels\ny_true_mobilenet = test_it.classes\n\n# Number of steps\nsteps = int(\n    np.ceil(test_it.samples / test_it.batch_size)\n)\n\n# Predict test set\nprobabilities_mobilenet = model_mobilenet.predict(\n    test_it,\n    steps=steps,\n    verbose=1\n).squeeze()\n\n# Convert probability to class\ny_pred_mobilenet = (\n    probabilities_mobilenet > 0.5\n).astype(int)\n\n# Class names\ntarget_names = list(\n    test_it.class_indices.keys()\n)\n\n# Classification Report\nreport_mobilenet = classification_report(\n    y_true_mobilenet,\n    y_pred_mobilenet,\n    target_names=target_names\n)\n\nprint(report_mobilenet)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:20:58.920896Z","iopub.execute_input":"2026-09-30T16:20:58.921658Z","iopub.status.idle":"2026-09-30T16:21:46.911604Z","shell.execute_reply.started":"2026-09-30T16:20:58.921621Z","shell.execute_reply":"2026-09-30T16:21:46.910585Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import 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":"2026-09-30T16:07:47.369546Z","iopub.execute_input":"2026-09-30T16:07:47.370636Z","iopub.status.idle":"2026-09-30T16:07:47.376603Z","shell.execute_reply.started":"2026-09-30T16:07:47.370599Z","shell.execute_reply":"2026-09-30T16:07:47.375735Z"}},"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":"2026-09-30T16:07:49.423743Z","iopub.execute_input":"2026-09-30T16:07:49.42465Z","iopub.status.idle":"2026-09-30T16:07:49.431562Z","shell.execute_reply.started":"2026-09-30T16:07:49.424616Z","shell.execute_reply":"2026-09-30T16:07:49.430467Z"}},"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 InceptionV3\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=10,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:07:52.543172Z","iopub.execute_input":"2026-09-30T16:07:52.543905Z","iopub.status.idle":"2026-09-30T16:09:50.919911Z","shell.execute_reply.started":"2026-09-30T16:07:52.543867Z","shell.execute_reply":"2026-09-30T16:09:50.919167Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Evaluate InceptionV3 on test set\n\ntest_it.reset()\n\n_, test_acc_inceptionv3 = model_inceptionv3.evaluate(\n    test_it,\n    steps=len(test_it),\n    verbose=1\n)\n\nprint(\n    'InceptionV3 Test Accuracy: %.3f'\n    % (test_acc_inceptionv3 * 100.0)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:11:35.488289Z","iopub.execute_input":"2026-09-30T16:11:35.488757Z","iopub.status.idle":"2026-09-30T16:12:30.058737Z","shell.execute_reply.started":"2026-09-30T16:11:35.488718Z","shell.execute_reply":"2026-09-30T16:12:30.057956Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\ntest_it.reset()\n\ny_true_inceptionv3 = test_it.classes\n\nsteps = int(\n    np.ceil(test_it.samples / test_it.batch_size)\n)\n\nprobabilities_inceptionv3 = model_inceptionv3.predict(\n    test_it,\n    steps=steps,\n    verbose=1\n).squeeze()\n\ny_pred_inceptionv3 = (\n    probabilities_inceptionv3 > 0.5\n).astype(int)\n\ntarget_names = list(\n    test_it.class_indices.keys()\n)\n\nreport_inceptionv3 = classification_report(\n    y_true_inceptionv3,\n    y_pred_inceptionv3,\n    target_names=target_names\n)\n\nprint(report_inceptionv3)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:13:24.703401Z","iopub.execute_input":"2026-09-30T16:13:24.70423Z","iopub.status.idle":"2026-09-30T16:13:52.525469Z","shell.execute_reply.started":"2026-09-30T16:13:24.704196Z","shell.execute_reply":"2026-09-30T16:13:52.524529Z"}},"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":"2026-09-30T16:25:30.958458Z","iopub.execute_input":"2026-09-30T16:25:30.958835Z","iopub.status.idle":"2026-09-30T16:25:30.966909Z","shell.execute_reply.started":"2026-09-30T16:25:30.958804Z","shell.execute_reply":"2026-09-30T16:25:30.965975Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:25:38.044401Z","iopub.execute_input":"2026-09-30T16:25:38.045228Z","iopub.status.idle":"2026-09-30T16:25:38.049278Z","shell.execute_reply.started":"2026-09-30T16:25:38.04519Z","shell.execute_reply":"2026-09-30T16:25:38.048141Z"}},"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":"2026-09-30T16:25:39.472478Z","iopub.execute_input":"2026-09-30T16:25:39.472783Z","iopub.status.idle":"2026-09-30T16:25:39.477327Z","shell.execute_reply.started":"2026-09-30T16:25:39.472758Z","shell.execute_reply":"2026-09-30T16:25:39.476142Z"}},"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":"2026-09-30T16:25:42.424216Z","iopub.execute_input":"2026-09-30T16:25:42.424569Z","iopub.status.idle":"2026-09-30T16:25:42.42931Z","shell.execute_reply.started":"2026-09-30T16:25:42.424543Z","shell.execute_reply":"2026-09-30T16:25:42.428131Z"}},"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":"2026-09-30T16:25:44.137493Z","iopub.execute_input":"2026-09-30T16:25:44.138603Z","iopub.status.idle":"2026-09-30T16:26:32.607619Z","shell.execute_reply.started":"2026-09-30T16:25:44.138567Z","shell.execute_reply":"2026-09-30T16:26:32.606604Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images, labels = test_it.__next__()\n\nprint(images.shape)\nprint(labels.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:28:54.785536Z","iopub.execute_input":"2026-09-30T16:28:54.785895Z","iopub.status.idle":"2026-09-30T16:28:54.959899Z","shell.execute_reply.started":"2026-09-30T16:28:54.785864Z","shell.execute_reply":"2026-09-30T16:28:54.958999Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 5 first images\nimages_to_predict = images[:5]\n\nprint(images_to_predict.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:29:05.461588Z","iopub.execute_input":"2026-09-30T16:29:05.462306Z","iopub.status.idle":"2026-09-30T16:29:05.467343Z","shell.execute_reply.started":"2026-09-30T16:29:05.462269Z","shell.execute_reply":"2026-09-30T16:29:05.466287Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(\n    images_to_predict,\n    verbose=1\n)\n\nprint(probs)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-30T16:29:17.196469Z","iopub.execute_input":"2026-09-30T16:29:17.196894Z","iopub.status.idle":"2026-09-30T16:29:18.478266Z","shell.execute_reply.started":"2026-09-30T16:29:17.19686Z","shell.execute_reply":"2026-09-30T16:29:18.477456Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}