{"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":"2026-09-15T13:05:33.982232Z","iopub.execute_input":"2026-09-15T13:05:33.98301Z","iopub.status.idle":"2026-09-15T13:05:33.987522Z","shell.execute_reply.started":"2026-09-15T13:05:33.982978Z","shell.execute_reply":"2026-09-15T13:05:33.986484Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:33.989519Z","iopub.execute_input":"2026-09-15T13:05:33.989889Z","iopub.status.idle":"2026-09-15T13:05:35.022027Z","shell.execute_reply.started":"2026-09-15T13:05:33.989833Z","shell.execute_reply":"2026-09-15T13:05:35.020897Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:35.023706Z","iopub.execute_input":"2026-09-15T13:05:35.024066Z","iopub.status.idle":"2026-09-15T13:05:36.04797Z","shell.execute_reply.started":"2026-09-15T13:05:35.024036Z","shell.execute_reply":"2026-09-15T13:05:36.04699Z"}},"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":"2026-09-15T13:05:36.05033Z","iopub.execute_input":"2026-09-15T13:05:36.05062Z","iopub.status.idle":"2026-09-15T13:05:45.470332Z","shell.execute_reply.started":"2026-09-15T13:05:36.050595Z","shell.execute_reply":"2026-09-15T13:05:45.469601Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:45.47141Z","iopub.execute_input":"2026-09-15T13:05:45.471762Z","iopub.status.idle":"2026-09-15T13:05:46.48328Z","shell.execute_reply.started":"2026-09-15T13:05:45.471738Z","shell.execute_reply":"2026-09-15T13:05:46.482017Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:46.484906Z","iopub.execute_input":"2026-09-15T13:05:46.485231Z","iopub.status.idle":"2026-09-15T13:05:47.556605Z","shell.execute_reply.started":"2026-09-15T13:05:46.485196Z","shell.execute_reply":"2026-09-15T13:05:47.555258Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:47.558414Z","iopub.execute_input":"2026-09-15T13:05:47.558728Z","iopub.status.idle":"2026-09-15T13:05:48.667252Z","shell.execute_reply.started":"2026-09-15T13:05:47.558702Z","shell.execute_reply":"2026-09-15T13:05:48.666343Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:48.668683Z","iopub.execute_input":"2026-09-15T13:05:48.669273Z","iopub.status.idle":"2026-09-15T13:05:49.759513Z","shell.execute_reply.started":"2026-09-15T13:05:48.669245Z","shell.execute_reply":"2026-09-15T13:05:49.758602Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:49.762851Z","iopub.execute_input":"2026-09-15T13:05:49.763109Z","iopub.status.idle":"2026-09-15T13:05:49.767807Z","shell.execute_reply.started":"2026-09-15T13:05:49.763087Z","shell.execute_reply":"2026-09-15T13:05:49.766913Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:49.768851Z","iopub.execute_input":"2026-09-15T13:05:49.769105Z","iopub.status.idle":"2026-09-15T13:05:50.889334Z","shell.execute_reply.started":"2026-09-15T13:05:49.769083Z","shell.execute_reply":"2026-09-15T13:05:50.888102Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:50.891224Z","iopub.execute_input":"2026-09-15T13:05:50.891646Z","iopub.status.idle":"2026-09-15T13:05:51.937898Z","shell.execute_reply.started":"2026-09-15T13:05:50.891608Z","shell.execute_reply":"2026-09-15T13:05:51.936958Z"}},"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":"2026-09-15T13:05:51.939305Z","iopub.execute_input":"2026-09-15T13:05:51.939595Z","iopub.status.idle":"2026-09-15T13:05:52.897327Z","shell.execute_reply.started":"2026-09-15T13:05:51.939527Z","shell.execute_reply":"2026-09-15T13:05:52.896501Z"},"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":"2026-09-15T13:05:52.898788Z","iopub.execute_input":"2026-09-15T13:05:52.899051Z","iopub.status.idle":"2026-09-15T13:05:53.847653Z","shell.execute_reply.started":"2026-09-15T13:05:52.899027Z","shell.execute_reply":"2026-09-15T13:05:53.846753Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:53.848791Z","iopub.execute_input":"2026-09-15T13:05:53.849034Z","iopub.status.idle":"2026-09-15T13:05:54.868717Z","shell.execute_reply.started":"2026-09-15T13:05:53.849011Z","shell.execute_reply":"2026-09-15T13:05:54.867713Z"}},"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":"2026-09-15T13:05:54.870219Z","iopub.execute_input":"2026-09-15T13:05:54.870655Z","iopub.status.idle":"2026-09-15T13:05:54.876614Z","shell.execute_reply.started":"2026-09-15T13:05:54.870628Z","shell.execute_reply":"2026-09-15T13:05:54.87556Z"}},"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":"2026-09-15T13:05:54.877706Z","iopub.execute_input":"2026-09-15T13:05:54.878585Z","iopub.status.idle":"2026-09-15T13:05:54.884667Z","shell.execute_reply.started":"2026-09-15T13:05:54.878535Z","shell.execute_reply":"2026-09-15T13:05:54.883839Z"},"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":"2026-09-15T13:05:54.88577Z","iopub.execute_input":"2026-09-15T13:05:54.886112Z","iopub.status.idle":"2026-09-15T13:05:54.893208Z","shell.execute_reply.started":"2026-09-15T13:05:54.886089Z","shell.execute_reply":"2026-09-15T13:05:54.892522Z"},"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":"2026-09-15T13:05:54.894465Z","iopub.execute_input":"2026-09-15T13:05:54.894854Z","iopub.status.idle":"2026-09-15T13:05:54.902391Z","shell.execute_reply.started":"2026-09-15T13:05:54.894832Z","shell.execute_reply":"2026-09-15T13:05:54.901732Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:54.903451Z","iopub.execute_input":"2026-09-15T13:05:54.90377Z","iopub.status.idle":"2026-09-15T13:05:55.918078Z","shell.execute_reply.started":"2026-09-15T13:05:54.90374Z","shell.execute_reply":"2026-09-15T13:05:55.916748Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:55.919776Z","iopub.execute_input":"2026-09-15T13:05:55.920188Z","iopub.status.idle":"2026-09-15T13:05:56.942419Z","shell.execute_reply.started":"2026-09-15T13:05:55.920158Z","shell.execute_reply":"2026-09-15T13:05:56.941431Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:05:56.943923Z","iopub.execute_input":"2026-09-15T13:05:56.944256Z","iopub.status.idle":"2026-09-15T13:05:57.972737Z","shell.execute_reply.started":"2026-09-15T13:05:56.94423Z","shell.execute_reply":"2026-09-15T13:05:57.971481Z"}},"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":"2026-09-15T13:05:57.974436Z","iopub.execute_input":"2026-09-15T13:05:57.974963Z","iopub.status.idle":"2026-09-15T13:06:01.317301Z","shell.execute_reply.started":"2026-09-15T13:05:57.974931Z","shell.execute_reply":"2026-09-15T13:06:01.316464Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:01.318563Z","iopub.execute_input":"2026-09-15T13:06:01.318881Z","iopub.status.idle":"2026-09-15T13:06:01.324307Z","shell.execute_reply.started":"2026-09-15T13:06:01.318848Z","shell.execute_reply":"2026-09-15T13:06:01.323327Z"}},"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":"2026-09-15T13:06:01.330899Z","iopub.execute_input":"2026-09-15T13:06:01.331839Z","iopub.status.idle":"2026-09-15T13:06:03.527132Z","shell.execute_reply.started":"2026-09-15T13:06:01.331813Z","shell.execute_reply":"2026-09-15T13:06:03.526165Z"},"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":"2026-09-15T13:06:03.528727Z","iopub.execute_input":"2026-09-15T13:06:03.529041Z","iopub.status.idle":"2026-09-15T13:06:05.737737Z","shell.execute_reply.started":"2026-09-15T13:06:03.529015Z","shell.execute_reply":"2026-09-15T13:06:05.7366Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-15T13:06:05.73931Z","iopub.execute_input":"2026-09-15T13:06:05.739654Z","iopub.status.idle":"2026-09-15T13:06:14.212746Z","shell.execute_reply.started":"2026-09-15T13:06:05.739627Z","shell.execute_reply":"2026-09-15T13:06:14.211572Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-15T13:06:14.214422Z","iopub.execute_input":"2026-09-15T13:06:14.214741Z","iopub.status.idle":"2026-09-15T13:06:14.221649Z","shell.execute_reply.started":"2026-09-15T13:06:14.214714Z","shell.execute_reply":"2026-09-15T13:06:14.220521Z"},"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":"2026-09-15T13:06:14.223106Z","iopub.execute_input":"2026-09-15T13:06:14.223485Z","iopub.status.idle":"2026-09-15T13:06:14.23177Z","shell.execute_reply.started":"2026-09-15T13:06:14.223451Z","shell.execute_reply":"2026-09-15T13:06:14.23096Z"}},"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":"2026-09-15T13:06:14.232878Z","iopub.execute_input":"2026-09-15T13:06:14.2332Z","iopub.status.idle":"2026-09-15T13:06:14.243407Z","shell.execute_reply.started":"2026-09-15T13:06:14.233177Z","shell.execute_reply":"2026-09-15T13:06:14.242579Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\n\tmodel = Sequential()\n\tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:14.244654Z","iopub.execute_input":"2026-09-15T13:06:14.244928Z","iopub.status.idle":"2026-09-15T13:06:14.253623Z","shell.execute_reply.started":"2026-09-15T13:06:14.244905Z","shell.execute_reply":"2026-09-15T13:06:14.252824Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:14.254859Z","iopub.execute_input":"2026-09-15T13:06:14.255164Z","iopub.status.idle":"2026-09-15T13:06:14.332259Z","shell.execute_reply.started":"2026-09-15T13:06:14.255139Z","shell.execute_reply":"2026-09-15T13:06:14.33114Z"}},"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":"2026-09-15T13:06:14.333314Z","iopub.execute_input":"2026-09-15T13:06:14.333677Z","iopub.status.idle":"2026-09-15T13:06:14.339412Z","shell.execute_reply.started":"2026-09-15T13:06:14.333652Z","shell.execute_reply":"2026-09-15T13:06:14.33836Z"}},"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":"2026-09-15T13:06:14.34062Z","iopub.execute_input":"2026-09-15T13:06:14.340943Z","iopub.status.idle":"2026-09-15T13:06:14.403869Z","shell.execute_reply.started":"2026-09-15T13:06:14.340896Z","shell.execute_reply":"2026-09-15T13:06:14.403115Z"}},"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)\nx2 = MaxPooling2D((2, 2))(x1)\nx3 = Flatten()(x2)\nx5 = Dense(256, activation='relu')(x3)\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":"2026-09-15T13:06:14.405513Z","iopub.execute_input":"2026-09-15T13:06:14.405879Z","iopub.status.idle":"2026-09-15T13:06:14.483491Z","shell.execute_reply.started":"2026-09-15T13:06:14.405844Z","shell.execute_reply":"2026-09-15T13:06:14.480192Z"}},"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)\nx1 = Conv2D(64, (3, 3), activation='relu')(x1)\nx2 = MaxPooling2D((2, 2))(x1)\nx3 = Flatten()(x2)\nx5 = Dense(256, activation='relu')(x3)\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":"2026-09-15T13:06:14.484768Z","iopub.execute_input":"2026-09-15T13:06:14.485307Z","iopub.status.idle":"2026-09-15T13:06:14.570804Z","shell.execute_reply.started":"2026-09-15T13:06:14.48528Z","shell.execute_reply":"2026-09-15T13:06:14.569978Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:14.572221Z","iopub.execute_input":"2026-09-15T13:06:14.572587Z","iopub.status.idle":"2026-09-15T13:06:14.580124Z","shell.execute_reply.started":"2026-09-15T13:06:14.572553Z","shell.execute_reply":"2026-09-15T13:06:14.579011Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:14.581339Z","iopub.execute_input":"2026-09-15T13:06:14.581753Z","iopub.status.idle":"2026-09-15T13:06:15.614379Z","shell.execute_reply.started":"2026-09-15T13:06:14.581729Z","shell.execute_reply":"2026-09-15T13:06:15.613083Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = 224 #for vgg16\nBATCH_SIZE = 64\nEPOCHS = 20","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:15.616207Z","iopub.execute_input":"2026-09-15T13:06:15.616621Z","iopub.status.idle":"2026-09-15T13:06:15.621784Z","shell.execute_reply.started":"2026-09-15T13:06:15.616581Z","shell.execute_reply":"2026-09-15T13:06:15.620812Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.applications.vgg16 import preprocess_input\n\n# 1. Instantiate the generator with the validation_split ratio\ntrain_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\n    horizontal_flip=True,\n    validation_split=0.2\n)\n\nval_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\n    validation_split=0.2\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 = 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    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 = val_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":"2026-09-15T13:06:15.623067Z","iopub.execute_input":"2026-09-15T13:06:15.623798Z","iopub.status.idle":"2026-09-15T13:06:16.13705Z","shell.execute_reply.started":"2026-09-15T13:06:15.623738Z","shell.execute_reply":"2026-09-15T13:06:16.136334Z"}},"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":"2026-09-15T13:06:16.138305Z","iopub.execute_input":"2026-09-15T13:06:16.138907Z","iopub.status.idle":"2026-09-15T13:06:16.145763Z","shell.execute_reply.started":"2026-09-15T13:06:16.138858Z","shell.execute_reply":"2026-09-15T13:06:16.144938Z"}},"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":"2026-09-15T13:06:16.147019Z","iopub.execute_input":"2026-09-15T13:06:16.148052Z","iopub.status.idle":"2026-09-15T13:06:16.156877Z","shell.execute_reply.started":"2026-09-15T13:06:16.148025Z","shell.execute_reply":"2026-09-15T13:06:16.155882Z"}},"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":"2026-09-15T13:06:16.158358Z","iopub.execute_input":"2026-09-15T13:06:16.158754Z","iopub.status.idle":"2026-09-15T13:06:16.16623Z","shell.execute_reply.started":"2026-09-15T13:06:16.158702Z","shell.execute_reply":"2026-09-15T13:06:16.165308Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:16.167232Z","iopub.execute_input":"2026-09-15T13:06:16.167483Z","iopub.status.idle":"2026-09-15T13:06:16.174803Z","shell.execute_reply.started":"2026-09-15T13:06:16.167461Z","shell.execute_reply":"2026-09-15T13:06:16.173739Z"}},"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":"2026-09-15T13:06:16.17614Z","iopub.execute_input":"2026-09-15T13:06:16.176578Z","iopub.status.idle":"2026-09-15T13:06:16.182584Z","shell.execute_reply.started":"2026-09-15T13:06:16.176524Z","shell.execute_reply":"2026-09-15T13:06:16.181439Z"}},"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":"2026-09-15T13:06:16.18391Z","iopub.execute_input":"2026-09-15T13:06:16.184915Z","iopub.status.idle":"2026-09-15T13:06:17.215902Z","shell.execute_reply.started":"2026-09-15T13:06:16.184884Z","shell.execute_reply":"2026-09-15T13:06:17.214899Z"}},"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":"2026-09-15T13:06:17.21737Z","iopub.execute_input":"2026-09-15T13:06:17.218129Z","iopub.status.idle":"2026-09-15T13:06:17.224156Z","shell.execute_reply.started":"2026-09-15T13:06:17.2181Z","shell.execute_reply":"2026-09-15T13:06:17.223094Z"}},"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":"2026-09-15T13:06:17.225308Z","iopub.execute_input":"2026-09-15T13:06:17.225893Z","iopub.status.idle":"2026-09-15T13:06:17.237529Z","shell.execute_reply.started":"2026-09-15T13:06:17.225868Z","shell.execute_reply":"2026-09-15T13:06:17.236879Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:17.238839Z","iopub.execute_input":"2026-09-15T13:06:17.239144Z","iopub.status.idle":"2026-09-15T13:06:17.246107Z","shell.execute_reply.started":"2026-09-15T13:06:17.239122Z","shell.execute_reply":"2026-09-15T13:06:17.245236Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:17.247345Z","iopub.execute_input":"2026-09-15T13:06:17.248056Z","iopub.status.idle":"2026-09-15T13:06:17.253563Z","shell.execute_reply.started":"2026-09-15T13:06:17.248032Z","shell.execute_reply":"2026-09-15T13:06:17.252797Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:17.254788Z","iopub.execute_input":"2026-09-15T13:06:17.255139Z","iopub.status.idle":"2026-09-15T13:06:17.263088Z","shell.execute_reply.started":"2026-09-15T13:06:17.255106Z","shell.execute_reply":"2026-09-15T13:06:17.262304Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:17.264267Z","iopub.execute_input":"2026-09-15T13:06:17.265057Z","iopub.status.idle":"2026-09-15T13:06:17.271317Z","shell.execute_reply.started":"2026-09-15T13:06:17.265022Z","shell.execute_reply":"2026-09-15T13:06:17.270462Z"}},"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":"2026-09-15T13:06:17.272746Z","iopub.execute_input":"2026-09-15T13:06:17.273103Z","iopub.status.idle":"2026-09-15T13:06:17.280572Z","shell.execute_reply.started":"2026-09-15T13:06:17.273067Z","shell.execute_reply":"2026-09-15T13:06:17.279741Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:17.281786Z","iopub.execute_input":"2026-09-15T13:06:17.282057Z","iopub.status.idle":"2026-09-15T13:06:17.290377Z","shell.execute_reply.started":"2026-09-15T13:06:17.282021Z","shell.execute_reply":"2026-09-15T13:06:17.289611Z"}},"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":"2026-09-15T13:06:22.770279Z","iopub.execute_input":"2026-09-15T13:06:22.770944Z","iopub.status.idle":"2026-09-15T13:06:22.776527Z","shell.execute_reply.started":"2026-09-15T13:06:22.770907Z","shell.execute_reply":"2026-09-15T13:06:22.775607Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True\n)\n\ntest_it = test_datagen.flow_from_directory(\n    test_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:17.291481Z","iopub.execute_input":"2026-09-15T13:06:17.291849Z","iopub.status.idle":"2026-09-15T13:06:22.768715Z","shell.execute_reply.started":"2026-09-15T13:06:17.291807Z","shell.execute_reply":"2026-09-15T13:06:22.767706Z"}},"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":"2026-09-15T13:06:22.777732Z","iopub.execute_input":"2026-09-15T13:06:22.778041Z","iopub.status.idle":"2026-09-15T13:06:31.843085Z","shell.execute_reply.started":"2026-09-15T13:06:22.778019Z","shell.execute_reply":"2026-09-15T13:06:31.842093Z"}},"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":"2026-09-15T13:06:31.844852Z","iopub.execute_input":"2026-09-15T13:06:31.845191Z","iopub.status.idle":"2026-09-15T13:06:40.208018Z","shell.execute_reply.started":"2026-09-15T13:06:31.845159Z","shell.execute_reply":"2026-09-15T13:06:40.206835Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_exmaple_test(images, indices):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(indices[i]))  # ตั้งค่า title ด้วย index จาก list/array indices\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:40.209369Z","iopub.execute_input":"2026-09-15T13:06:40.209691Z","iopub.status.idle":"2026-09-15T13:06:40.217324Z","shell.execute_reply.started":"2026-09-15T13:06:40.209661Z","shell.execute_reply":"2026-09-15T13:06:40.216046Z"},"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images, test_labels = test_it.__next__()  # หรือ next(test_it)\nprint(f\"{test_images.shape=}, {test_labels.shape}\")\n\n# สร้าง list เลขดัชนีตามจำนวนภาพที่มี\nindices = list(range(len(test_images)))\n\nplot_exmaple(test_images, test_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:40.218992Z","iopub.execute_input":"2026-09-15T13:06:40.219305Z","iopub.status.idle":"2026-09-15T13:06:49.724047Z","shell.execute_reply.started":"2026-09-15T13:06:40.21928Z","shell.execute_reply":"2026-09-15T13:06:49.722383Z"}},"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":"2026-09-15T13:06:49.725261Z","iopub.execute_input":"2026-09-15T13:06:49.725889Z","iopub.status.idle":"2026-09-15T13:06:49.729991Z","shell.execute_reply.started":"2026-09-15T13:06:49.725859Z","shell.execute_reply":"2026-09-15T13:06:49.729078Z"}},"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":"2026-09-15T13:06:49.731218Z","iopub.execute_input":"2026-09-15T13:06:49.731626Z","iopub.status.idle":"2026-09-15T13:06:49.741762Z","shell.execute_reply.started":"2026-09-15T13:06:49.731593Z","shell.execute_reply":"2026-09-15T13:06:49.740724Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it),id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:49.743147Z","iopub.execute_input":"2026-09-15T13:06:49.743606Z","iopub.status.idle":"2026-09-15T13:06:49.752085Z","shell.execute_reply.started":"2026-09-15T13:06:49.743569Z","shell.execute_reply":"2026-09-15T13:06:49.751081Z"}},"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, Dropout\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.optimizers import Adam\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# Hyperparameter => changable\nIMAGE_SIZE = 224\nBATCH_SIE = 64\nEPOCHS = 20\n\ndef define_model_vgg16():\n    # load model\n    model = VGG16(\n        include_top=False,\n        input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n    )\n\n        # freeze all VGG16 layers\n    for layer in model.layers:\n        layer.trainable = False\n\n    # fine-tuning last 4 layers\n    for layer in model.layers[-4:]:\n        layer.trainable = True\n\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n\n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    \n    class1 = Dense(\n        128,\n        activation='relu',\n        kernel_initializer='he_uniform'\n    )(flat1)\n\n    class1 = Dropout(0.1)(class1)\n    \n    class2 = Dense(\n        64,\n        activation='relu',\n        kernel_initializer='he_uniform'\n    )(class1)\n\n    class2 = Dropout(0.1)(class2)\n\n    class3 = Dense(\n        32,\n        activation='relu',\n        kernel_initializer='he_uniform'\n    )(class2)\n\n    class3 = Dropout(0.1)(class3)\n    \n    output = Dense(1, activation='sigmoid')(class1)\n\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n\n    # compile model\n    opt = Adam(learning_rate=0.00001)\n\n    model.compile(\n        optimizer =opt,\n        loss='binary_crossentropy',\n        metrics=['accuracy']\n    )\n\n    return model\n\nvgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:49.753163Z","iopub.execute_input":"2026-09-15T13:06:49.753377Z","iopub.status.idle":"2026-09-15T13:06:50.142075Z","shell.execute_reply.started":"2026-09-15T13:06:49.753358Z","shell.execute_reply":"2026-09-15T13:06:50.141248Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_vgg16_top = VGG16(include_top=True, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\nmodel_vgg16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:50.143283Z","iopub.execute_input":"2026-09-15T13:06:50.143628Z","iopub.status.idle":"2026-09-15T13:06:52.440419Z","shell.execute_reply.started":"2026-09-15T13:06:50.1436Z","shell.execute_reply":"2026-09-15T13:06:52.439617Z"}},"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))\nmodel_16_feature_extractor.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.441961Z","iopub.execute_input":"2026-09-15T13:06:52.442327Z","iopub.status.idle":"2026-09-15T13:06:52.809975Z","shell.execute_reply.started":"2026-09-15T13:06:52.442291Z","shell.execute_reply":"2026-09-15T13:06:52.80897Z"}},"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":"2026-09-15T13:06:52.811194Z","iopub.execute_input":"2026-09-15T13:06:52.811603Z","iopub.status.idle":"2026-09-15T13:06:52.817199Z","shell.execute_reply.started":"2026-09-15T13:06:52.811566Z","shell.execute_reply":"2026-09-15T13:06:52.816229Z"}},"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":"2026-09-15T13:06:52.818298Z","iopub.execute_input":"2026-09-15T13:06:52.81884Z","iopub.status.idle":"2026-09-15T13:06:52.828249Z","shell.execute_reply.started":"2026-09-15T13:06:52.818815Z","shell.execute_reply":"2026-09-15T13:06:52.827251Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.829409Z","iopub.execute_input":"2026-09-15T13:06:52.829859Z","iopub.status.idle":"2026-09-15T13:06:52.837353Z","shell.execute_reply.started":"2026-09-15T13:06:52.829808Z","shell.execute_reply":"2026-09-15T13:06:52.836306Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"flat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\nprint(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.844902Z","iopub.execute_input":"2026-09-15T13:06:52.845193Z","iopub.status.idle":"2026-09-15T13:06:52.854312Z","shell.execute_reply.started":"2026-09-15T13:06:52.84517Z","shell.execute_reply":"2026-09-15T13:06:52.853341Z"}},"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":"2026-09-15T13:06:52.855466Z","iopub.execute_input":"2026-09-15T13:06:52.855825Z","iopub.status.idle":"2026-09-15T13:06:52.874366Z","shell.execute_reply.started":"2026-09-15T13:06:52.855799Z","shell.execute_reply":"2026-09-15T13:06:52.873577Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.875393Z","iopub.execute_input":"2026-09-15T13:06:52.875927Z","iopub.status.idle":"2026-09-15T13:06:52.892326Z","shell.execute_reply.started":"2026-09-15T13:06:52.875901Z","shell.execute_reply":"2026-09-15T13:06:52.891609Z"}},"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\n#opt = SGD(lr=0.001, momentum=0.9)\nopt = 'adam'\n\nmodel_vgg16.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.893376Z","iopub.execute_input":"2026-09-15T13:06:52.893726Z","iopub.status.idle":"2026-09-15T13:06:52.910586Z","shell.execute_reply.started":"2026-09-15T13:06:52.893692Z","shell.execute_reply":"2026-09-15T13:06:52.909503Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.911921Z","iopub.execute_input":"2026-09-15T13:06:52.912792Z","iopub.status.idle":"2026-09-15T13:06:52.957331Z","shell.execute_reply.started":"2026-09-15T13:06:52.912766Z","shell.execute_reply":"2026-09-15T13:06:52.956611Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.958454Z","iopub.execute_input":"2026-09-15T13:06:52.958756Z","iopub.status.idle":"2026-09-15T13:06:52.965031Z","shell.execute_reply.started":"2026-09-15T13:06:52.958733Z","shell.execute_reply":"2026-09-15T13:06:52.963917Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.966167Z","iopub.execute_input":"2026-09-15T13:06:52.966379Z","iopub.status.idle":"2026-09-15T13:06:52.973258Z","shell.execute_reply.started":"2026-09-15T13:06:52.966359Z","shell.execute_reply":"2026-09-15T13:06:52.972176Z"}},"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=1, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:06:52.97438Z","iopub.execute_input":"2026-09-15T13:06:52.974769Z","iopub.status.idle":"2026-09-15T13:38:58.146906Z","shell.execute_reply.started":"2026-09-15T13:06:52.974745Z","shell.execute_reply":"2026-09-15T13:38:58.146106Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:38:58.148148Z","iopub.execute_input":"2026-09-15T13:38:58.148919Z","iopub.status.idle":"2026-09-15T13:38:58.524136Z","shell.execute_reply.started":"2026-09-15T13:38:58.148891Z","shell.execute_reply":"2026-09-15T13:38:58.522992Z"}},"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":"2026-09-15T13:38:58.526242Z","iopub.execute_input":"2026-09-15T13:38:58.527026Z","iopub.status.idle":"2026-09-15T13:39:16.569072Z","shell.execute_reply.started":"2026-09-15T13:38:58.526998Z","shell.execute_reply":"2026-09-15T13:39:16.568285Z"}},"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":"2026-09-15T13:39:16.570238Z","iopub.execute_input":"2026-09-15T13:39:16.571244Z","iopub.status.idle":"2026-09-15T13:39:46.901317Z","shell.execute_reply.started":"2026-09-15T13:39:16.571196Z","shell.execute_reply":"2026-09-15T13:39:46.900595Z"}},"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":"2026-09-15T13:39:46.902424Z","iopub.execute_input":"2026-09-15T13:39:46.902735Z","iopub.status.idle":"2026-09-15T13:40:16.86358Z","shell.execute_reply.started":"2026-09-15T13:39:46.902709Z","shell.execute_reply":"2026-09-15T13:40:16.862459Z"}},"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":"2026-09-15T13:40:16.864847Z","iopub.execute_input":"2026-09-15T13:40:16.865375Z","iopub.status.idle":"2026-09-15T13:40:16.886212Z","shell.execute_reply.started":"2026-09-15T13:40:16.865348Z","shell.execute_reply":"2026-09-15T13:40:16.885278Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Predict\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# 1. Aggregate sufficient samples from the iterator\nimages_list = []\nlabels_list = []\n\n# Fetch 2 batches (2 * 64 = 128 samples) to ensure we have pool > 100\nfor _ in range(2):\n    batch_images, batch_labels = next(test_it)\n    images_list.append(batch_images)\n    labels_list.append(batch_labels)\n\n# Concatenate into a single tensor\nall_images = np.concatenate(images_list, axis=0)\nall_labels = np.concatenate(labels_list, axis=0)\n\n# 2. Stochastically sample 100 unique indices\nnp.random.seed(42) # For reproducibility\nrandom_indices = np.random.choice(all_images.shape[0], size=100, replace=False)\n\nsample_images = all_images[random_indices]\nsample_labels = all_labels[random_indices]\n\n# 3. Execute the forward pass\n# Squeeze is used to convert shape (100, 1) to (100,)\nprobabilities = model_vgg16.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:40:16.887208Z","iopub.execute_input":"2026-09-15T13:40:16.88753Z","iopub.status.idle":"2026-09-15T13:40:18.048771Z","shell.execute_reply.started":"2026-09-15T13:40:16.887506Z","shell.execute_reply":"2026-09-15T13:40:18.047792Z"}},"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":"2026-09-15T13:40:18.049968Z","iopub.execute_input":"2026-09-15T13:40:18.050498Z","iopub.status.idle":"2026-09-15T13:40:26.392519Z","shell.execute_reply.started":"2026-09-15T13:40:18.050472Z","shell.execute_reply":"2026-09-15T13:40:26.390709Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T13:40:26.39391Z","iopub.execute_input":"2026-09-15T13:40:26.394357Z","iopub.status.idle":"2026-09-15T13:40:26.427384Z","shell.execute_reply.started":"2026-09-15T13:40:26.39431Z","shell.execute_reply":"2026-09-15T13:40:26.42621Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications.inception_v3 import preprocess_input\n\n# 1. Instantiate the generator with the validation_split ratio\ntrain_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\n    horizontal_flip=True,\n    validation_split=0.2\n)\n\nval_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\n    validation_split=0.2\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 = 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    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 = val_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":"2026-09-15T14:13:16.715489Z","iopub.execute_input":"2026-09-15T14:13:16.716347Z","iopub.status.idle":"2026-09-15T14:13:17.184164Z","shell.execute_reply.started":"2026-09-15T14:13:16.716315Z","shell.execute_reply":"2026-09-15T14:13:17.183425Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\nfrom keras.models import Model\nfrom keras.layers import Dense, Dropout, GlobalAveragePooling2D\nfrom keras.optimizers import Adam\n\n\ndef define_model_inceptionv3():\n\n    # load model\n    model = InceptionV3(\n        include_top=False,\n        weights='imagenet',\n        input_shape=(224, 224, 3)\n    )\n\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n\n    # fine-tuning last 4 layers\n    for layer in model.layers[-4:]:\n        layer.trainable = True\n\n    # add new classifier layers\n    flat1 = GlobalAveragePooling2D()(model.output)\n\n    class1 = Dense(\n        256,\n        activation='relu',\n        kernel_initializer='he_uniform'\n    )(flat1)\n\n    class1 = Dropout(0.1)(class1)\n\n    # binary classification\n    output = Dense(\n        1,\n        activation='sigmoid'\n    )(class1)\n\n    # define new model\n    model = Model(\n        inputs=model.input,\n        outputs=output\n    )\n\n    # compile model\n    opt = Adam(\n        learning_rate=0.00001\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":"2026-09-15T14:13:17.185481Z","iopub.execute_input":"2026-09-15T14:13:17.1859Z","iopub.status.idle":"2026-09-15T14:13:17.192871Z","shell.execute_reply.started":"2026-09-15T14:13:17.185873Z","shell.execute_reply":"2026-09-15T14:13:17.191826Z"}},"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":"2026-09-15T14:13:17.194088Z","iopub.execute_input":"2026-09-15T14:13:17.194421Z","iopub.status.idle":"2026-09-15T14:13:19.345671Z","shell.execute_reply.started":"2026-09-15T14:13:17.194388Z","shell.execute_reply":"2026-09-15T14:13:19.344603Z"},"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":"2026-09-15T14:13:19.347539Z","iopub.execute_input":"2026-09-15T14:13:19.347887Z","iopub.status.idle":"2026-09-15T14:13:19.354064Z","shell.execute_reply.started":"2026-09-15T14:13:19.347862Z","shell.execute_reply":"2026-09-15T14:13:19.353026Z"}},"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":"2026-09-15T14:13:19.355064Z","iopub.execute_input":"2026-09-15T14:13:19.355352Z","iopub.status.idle":"2026-09-15T14:13:19.364495Z","shell.execute_reply.started":"2026-09-15T14:13:19.355327Z","shell.execute_reply":"2026-09-15T14:13:19.363703Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(train_it.image_shape)\nprint(train_it.batch_size)\nprint(model_inceptionv3.input_shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T14:13:19.365877Z","iopub.execute_input":"2026-09-15T14:13:19.36613Z","iopub.status.idle":"2026-09-15T14:13:19.374635Z","shell.execute_reply.started":"2026-09-15T14:13:19.366108Z","shell.execute_reply":"2026-09-15T14:13:19.373584Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T14:13:19.375814Z","iopub.execute_input":"2026-09-15T14:13:19.376208Z","iopub.status.idle":"2026-09-15T14:13:21.551785Z","shell.execute_reply.started":"2026-09-15T14:13:19.37617Z","shell.execute_reply":"2026-09-15T14:13:21.550973Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\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":"2026-09-15T14:13:21.552881Z","iopub.execute_input":"2026-09-15T14:13:21.553221Z","iopub.status.idle":"2026-09-15T14:23:33.32622Z","shell.execute_reply.started":"2026-09-15T14:13:21.553194Z","shell.execute_reply":"2026-09-15T14:23:33.325022Z"}},"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":"2026-09-15T14:25:20.635512Z","iopub.execute_input":"2026-09-15T14:25:20.636445Z","iopub.status.idle":"2026-09-15T14:25:53.144374Z","shell.execute_reply.started":"2026-09-15T14:25:20.636411Z","shell.execute_reply":"2026-09-15T14:25:53.143036Z"}},"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":"2026-09-15T14:26:00.805713Z","iopub.execute_input":"2026-09-15T14:26:00.806574Z","iopub.status.idle":"2026-09-15T14:26:00.827189Z","shell.execute_reply.started":"2026-09-15T14:26:00.806509Z","shell.execute_reply":"2026-09-15T14:26:00.826458Z"}},"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":"2026-09-15T14:23:33.328424Z","iopub.execute_input":"2026-09-15T14:23:33.32928Z","iopub.status.idle":"2026-09-15T14:23:33.336137Z","shell.execute_reply.started":"2026-09-15T14:23:33.329253Z","shell.execute_reply":"2026-09-15T14:23:33.335259Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T14:23:33.339438Z","iopub.execute_input":"2026-09-15T14:23:33.34006Z","iopub.status.idle":"2026-09-15T14:23:33.348863Z","shell.execute_reply.started":"2026-09-15T14:23:33.340034Z","shell.execute_reply":"2026-09-15T14:23:33.347977Z"}},"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":"2026-09-15T14:23:33.349992Z","iopub.execute_input":"2026-09-15T14:23:33.350293Z","iopub.status.idle":"2026-09-15T14:23:33.357676Z","shell.execute_reply.started":"2026-09-15T14:23:33.350269Z","shell.execute_reply":"2026-09-15T14:23:33.35697Z"}},"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":"2026-09-15T14:23:33.358743Z","iopub.execute_input":"2026-09-15T14:23:33.35945Z","iopub.status.idle":"2026-09-15T14:23:33.365889Z","shell.execute_reply.started":"2026-09-15T14:23:33.359416Z","shell.execute_reply":"2026-09-15T14:23:33.364976Z"}},"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":"2026-09-15T14:23:33.366955Z","iopub.execute_input":"2026-09-15T14:23:33.36726Z","iopub.status.idle":"2026-09-15T14:23:56.83956Z","shell.execute_reply.started":"2026-09-15T14:23:33.367229Z","shell.execute_reply":"2026-09-15T14:23:56.838819Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T14:23:56.840606Z","iopub.execute_input":"2026-09-15T14:23:56.841109Z","iopub.status.idle":"2026-09-15T14:23:57.014981Z","shell.execute_reply.started":"2026-09-15T14:23:56.84108Z","shell.execute_reply":"2026-09-15T14:23:57.013603Z"}},"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":"2026-09-15T14:30:52.597622Z","iopub.execute_input":"2026-09-15T14:30:52.598376Z","iopub.status.idle":"2026-09-15T14:30:52.624374Z","shell.execute_reply.started":"2026-09-15T14:30:52.598342Z","shell.execute_reply":"2026-09-15T14:30:52.623295Z"}},"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":"2026-09-15T14:30:47.91041Z","iopub.execute_input":"2026-09-15T14:30:47.91085Z","iopub.status.idle":"2026-09-15T14:30:47.93877Z","shell.execute_reply.started":"2026-09-15T14:30:47.910815Z","shell.execute_reply":"2026-09-15T14:30:47.937614Z"}},"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_inceptionv3.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T14:30:05.636364Z","iopub.execute_input":"2026-09-15T14:30:05.637137Z","iopub.status.idle":"2026-09-15T14:30:10.621931Z","shell.execute_reply.started":"2026-09-15T14:30:05.6371Z","shell.execute_reply":"2026-09-15T14:30:10.620897Z"}},"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":"2026-09-15T14:31:00.141285Z","iopub.execute_input":"2026-09-15T14:31:00.142238Z","iopub.status.idle":"2026-09-15T14:31:07.662049Z","shell.execute_reply.started":"2026-09-15T14:31:00.142203Z","shell.execute_reply":"2026-09-15T14:31:07.658396Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## **NASNetLarge**","metadata":{}},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications.nasnet import preprocess_input\n\n# 1. Instantiate the generator with the validation_split ratio\ntrain_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\n    horizontal_flip=True,\n    validation_split=0.2\n)\n\nval_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input,\n    validation_split=0.2\n)\n\ntest_datagen = ImageDataGenerator(\n    preprocessing_function=preprocess_input\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 = train_datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(331, 331),\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 = val_datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(331, 331),\n    subset='validation',   # Explicitly request the validation partition\n    shuffle=False          # Disable shuffle to maintain index alignment for metrics\n)\n\ntest_it = test_datagen.flow_from_directory(\n    test_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(331, 331),\n    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T16:12:56.037345Z","iopub.execute_input":"2026-09-15T16:12:56.037834Z","iopub.status.idle":"2026-09-15T16:13:05.848627Z","shell.execute_reply.started":"2026-09-15T16:12:56.037799Z","shell.execute_reply":"2026-09-15T16:13:05.847926Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from keras.applications import NASNetLarge\nfrom keras.models import Model\nfrom keras.layers import Dense, Dropout, GlobalAveragePooling2D\nfrom keras.optimizers import Adam\n\n\ndef define_model_nasnetlarge():\n\n    # Load NASNetLarge\n    model = NASNetLarge(\n        include_top=False,\n        weights='imagenet',\n        input_shape=(331, 331, 3)\n    )\n\n    # Freeze all layers\n    for layer in model.layers:\n        layer.trainable = False\n\n    # Fine-tuning last 4 layers\n    for layer in model.layers[-4:]:\n        layer.trainable = True\n\n    # Global Average Pooling\n    x = GlobalAveragePooling2D()(model.output)\n\n    # Classifier\n    x = Dense(\n        256,\n        activation='relu',\n        kernel_initializer='he_uniform'\n    )(x)\n\n    x = Dropout(0.1)(x)\n\n    # Binary classification\n    output = Dense(\n        1,\n        activation='sigmoid'\n    )(x)\n\n    # Define model\n    model = Model(\n        inputs=model.input,\n        outputs=output\n    )\n\n    # Compile\n    opt = Adam(\n        learning_rate=0.00001\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":"2026-09-15T16:13:05.849875Z","iopub.execute_input":"2026-09-15T16:13:05.850522Z","iopub.status.idle":"2026-09-15T16:13:05.857304Z","shell.execute_reply.started":"2026-09-15T16:13:05.850495Z","shell.execute_reply":"2026-09-15T16:13:05.856491Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_nasnetlarge = define_model_nasnetlarge()\n# model_nasnetlarge.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T16:13:09.548033Z","iopub.execute_input":"2026-09-15T16:13:09.548776Z","iopub.status.idle":"2026-09-15T16:13:18.001576Z","shell.execute_reply.started":"2026-09-15T16:13:09.548743Z","shell.execute_reply":"2026-09-15T16:13:18.000694Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history_nasnetlarge = model_nasnetlarge.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=1,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T16:13:20.273914Z","iopub.execute_input":"2026-09-15T16:13:20.274596Z","iopub.status.idle":"2026-09-15T16:23:35.852978Z","shell.execute_reply.started":"2026-09-15T16:13:20.274529Z","shell.execute_reply":"2026-09-15T16:23:35.851938Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc =  model_nasnetlarge.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":"2026-09-15T16:23:47.87075Z","iopub.execute_input":"2026-09-15T16:23:47.871502Z","iopub.status.idle":"2026-09-15T16:27:10.982145Z","shell.execute_reply.started":"2026-09-15T16:23:47.87147Z","shell.execute_reply":"2026-09-15T16:27:10.981383Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(train_it.image_shape)\nprint(val_it.image_shape)\nprint(model_nasnetlarge.input_shape)\nprint(test_it.image_shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T16:27:39.680599Z","iopub.execute_input":"2026-09-15T16:27:39.681222Z","iopub.status.idle":"2026-09-15T16:27:39.688629Z","shell.execute_reply.started":"2026-09-15T16:27:39.681185Z","shell.execute_reply":"2026-09-15T16:27:39.687605Z"}},"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_nasnetlarge.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T16:27:42.822793Z","iopub.execute_input":"2026-09-15T16:27:42.82319Z","iopub.status.idle":"2026-09-15T16:27:55.71186Z","shell.execute_reply.started":"2026-09-15T16:27:42.823162Z","shell.execute_reply":"2026-09-15T16:27:55.711003Z"}},"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":"2026-09-15T16:28:18.845582Z","iopub.execute_input":"2026-09-15T16:28:18.846348Z","iopub.status.idle":"2026-09-15T16:28:26.936673Z","shell.execute_reply.started":"2026-09-15T16:28:18.846315Z","shell.execute_reply":"2026-09-15T16:28:26.934132Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-15T16:46:52.50231Z","iopub.execute_input":"2026-09-15T16:46:52.503032Z","iopub.status.idle":"2026-09-15T16:46:52.508909Z","shell.execute_reply.started":"2026-09-15T16:46:52.502998Z","shell.execute_reply":"2026-09-15T16:46:52.508027Z"}},"outputs":[],"execution_count":null}]}