{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\n# import os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2026-10-03T22:15:23.068015Z","iopub.execute_input":"2026-10-03T22:15:23.06837Z","iopub.status.idle":"2026-10-03T22:15:23.402912Z","shell.execute_reply.started":"2026-10-03T22:15:23.068344Z","shell.execute_reply":"2026-10-03T22:15:23.402141Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:15:23.60144Z","iopub.execute_input":"2026-10-03T22:15:23.602426Z","iopub.status.idle":"2026-10-03T22:15:24.659875Z","shell.execute_reply.started":"2026-10-03T22:15:23.602391Z","shell.execute_reply":"2026-10-03T22:15:24.658884Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-27T03:03:04.046401Z","iopub.execute_input":"2026-09-27T03:03:04.046681Z","iopub.status.idle":"2026-09-27T03:03:05.020612Z","shell.execute_reply.started":"2026-09-27T03:03:04.046658Z","shell.execute_reply":"2026-09-27T03:03:05.019728Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:15:38.889412Z","iopub.execute_input":"2026-10-03T22:15:38.889776Z","iopub.status.idle":"2026-10-03T22:15:53.245998Z","shell.execute_reply.started":"2026-10-03T22:15:38.889747Z","shell.execute_reply":"2026-10-03T22:15:53.245144Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:15:53.247565Z","iopub.execute_input":"2026-10-03T22:15:53.247998Z","iopub.status.idle":"2026-10-03T22:15:54.37147Z","shell.execute_reply.started":"2026-10-03T22:15:53.247968Z","shell.execute_reply":"2026-10-03T22:15:54.3703Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:15:54.373152Z","iopub.execute_input":"2026-10-03T22:15:54.373488Z","iopub.status.idle":"2026-10-03T22:15:55.586658Z","shell.execute_reply.started":"2026-10-03T22:15:54.37346Z","shell.execute_reply":"2026-10-03T22:15:55.585522Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:05.152319Z","iopub.execute_input":"2026-10-03T22:16:05.152633Z","iopub.status.idle":"2026-10-03T22:16:06.213095Z","shell.execute_reply.started":"2026-10-03T22:16:05.152609Z","shell.execute_reply":"2026-10-03T22:16:06.212143Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:06.214881Z","iopub.execute_input":"2026-10-03T22:16:06.215868Z","iopub.status.idle":"2026-10-03T22:16:07.349503Z","shell.execute_reply.started":"2026-10-03T22:16:06.215832Z","shell.execute_reply":"2026-10-03T22:16:07.348182Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:07.351229Z","iopub.execute_input":"2026-10-03T22:16:07.351518Z","iopub.status.idle":"2026-10-03T22:16:07.357283Z","shell.execute_reply.started":"2026-10-03T22:16:07.351492Z","shell.execute_reply":"2026-10-03T22:16:07.355946Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:07.359871Z","iopub.execute_input":"2026-10-03T22:16:07.360294Z","iopub.status.idle":"2026-10-03T22:16:08.466678Z","shell.execute_reply.started":"2026-10-03T22:16:07.360242Z","shell.execute_reply":"2026-10-03T22:16:08.465795Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:08.468167Z","iopub.execute_input":"2026-10-03T22:16:08.46845Z","iopub.status.idle":"2026-10-03T22:16:09.517876Z","shell.execute_reply.started":"2026-10-03T22:16:08.468425Z","shell.execute_reply":"2026-10-03T22:16:09.516853Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\n# from matplotlib import pyplot as plt\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'dog.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:11.902537Z","iopub.execute_input":"2026-10-03T22:16:11.903016Z","iopub.status.idle":"2026-10-03T22:16:13.026024Z","shell.execute_reply.started":"2026-10-03T22:16:11.902985Z","shell.execute_reply":"2026-10-03T22:16:13.024962Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot cat photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'cat.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:13.027596Z","iopub.execute_input":"2026-10-03T22:16:13.027988Z","iopub.status.idle":"2026-10-03T22:16:14.021624Z","shell.execute_reply.started":"2026-10-03T22:16:13.027961Z","shell.execute_reply":"2026-10-03T22:16:14.020569Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:14.182217Z","iopub.execute_input":"2026-10-03T22:16:14.183024Z","iopub.status.idle":"2026-10-03T22:16:15.18759Z","shell.execute_reply.started":"2026-10-03T22:16:14.182992Z","shell.execute_reply":"2026-10-03T22:16:15.186176Z"}},"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":"2026-10-03T22:16:15.190275Z","iopub.execute_input":"2026-10-03T22:16:15.190579Z","iopub.status.idle":"2026-10-03T22:16:28.790129Z","shell.execute_reply.started":"2026-10-03T22:16:15.190554Z","shell.execute_reply":"2026-10-03T22:16:28.789129Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load dogs vs cats dataset, reshape and save to a new file\nfrom os import listdir\nfrom numpy import asarray\nfrom numpy import save\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:28.791206Z","iopub.execute_input":"2026-10-03T22:16:28.791825Z","iopub.status.idle":"2026-10-03T22:16:28.796875Z","shell.execute_reply.started":"2026-10-03T22:16:28.791791Z","shell.execute_reply":"2026-10-03T22:16:28.795621Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n\t# determine class\n\toutput = 0.0\n\tif file.startswith('dog'):\n\t\toutput = 1.0\n\t# load image\n\tphoto = load_img(folder + file, target_size=(200, 200))\n\t# convert to numpy array\n\tphoto = img_to_array(photo)\n\t# store\n\tphotos.append(photo)\n\tlabels.append(output)\n# convert to a numpy arrays\nphotos = asarray(photos)\nlabels = asarray(labels)\nprint(photos.shape, labels.shape)\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:15.416611Z","iopub.execute_input":"2024-01-27T03:36:15.417128Z","iopub.status.idle":"2024-01-27T03:36:38.886396Z","shell.execute_reply.started":"2024-01-27T03:36:15.417101Z","shell.execute_reply":"2024-01-27T03:36:38.883149Z"}}},{"cell_type":"markdown","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:38.88711Z","iopub.status.idle":"2024-01-27T03:36:38.887458Z","shell.execute_reply.started":"2024-01-27T03:36:38.887281Z","shell.execute_reply":"2024-01-27T03:36:38.887296Z"}}},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:28.799585Z","iopub.execute_input":"2026-10-03T22:16:28.800213Z","iopub.status.idle":"2026-10-03T22:16:28.826046Z","shell.execute_reply.started":"2026-10-03T22:16:28.800183Z","shell.execute_reply":"2026-10-03T22:16:28.825279Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/'] #test==>validation\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir       \n        makedirs(newdir, exist_ok=True)\n        print(newdir)","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:31.071554Z","iopub.execute_input":"2026-10-03T22:16:31.07264Z","iopub.status.idle":"2026-10-03T22:16:31.079291Z","shell.execute_reply.started":"2026-10-03T22:16:31.072595Z","shell.execute_reply":"2026-10-03T22:16:31.078132Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:32.606856Z","iopub.execute_input":"2026-10-03T22:16:32.607761Z","iopub.status.idle":"2026-10-03T22:16:33.638049Z","shell.execute_reply.started":"2026-10-03T22:16:32.607729Z","shell.execute_reply":"2026-10-03T22:16:33.637102Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:33.639936Z","iopub.execute_input":"2026-10-03T22:16:33.640635Z","iopub.status.idle":"2026-10-03T22:16:34.662306Z","shell.execute_reply.started":"2026-10-03T22:16:33.640607Z","shell.execute_reply":"2026-10-03T22:16:34.66087Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:34.664004Z","iopub.execute_input":"2026-10-03T22:16:34.664929Z","iopub.status.idle":"2026-10-03T22:16:35.687413Z","shell.execute_reply.started":"2026-10-03T22:16:34.664892Z","shell.execute_reply":"2026-10-03T22:16:35.686162Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1337)\n# define ratio of pictures to use for validation\nval_ratio = 0.25 #changable\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\n\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:48.257536Z","iopub.execute_input":"2026-10-03T22:16:48.258302Z","iopub.status.idle":"2026-10-03T22:16:51.55286Z","shell.execute_reply.started":"2026-10-03T22:16:48.258269Z","shell.execute_reply":"2026-10-03T22:16:51.551782Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:16:51.55464Z","iopub.execute_input":"2026-10-03T22:16:51.555446Z","iopub.status.idle":"2026-10-03T22:16:51.838814Z","shell.execute_reply.started":"2026-10-03T22:16:51.555413Z","shell.execute_reply":"2026-10-03T22:16:51.837725Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:51.839978Z","iopub.execute_input":"2026-10-03T22:16:51.840506Z","iopub.status.idle":"2026-10-03T22:16:54.110061Z","shell.execute_reply.started":"2026-10-03T22:16:51.840477Z","shell.execute_reply":"2026-10-03T22:16:54.108775Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#validation set\n!ls -l dataset_dogs_vs_cats/test/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/test/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:54.113217Z","iopub.execute_input":"2026-10-03T22:16:54.113522Z","iopub.status.idle":"2026-10-03T22:16:56.192573Z","shell.execute_reply.started":"2026-10-03T22:16:54.113497Z","shell.execute_reply":"2026-10-03T22:16:56.19117Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:16:56.194195Z","iopub.execute_input":"2026-10-03T22:16:56.194577Z","iopub.status.idle":"2026-10-03T22:17:07.525999Z","shell.execute_reply.started":"2026-10-03T22:16:56.194542Z","shell.execute_reply":"2026-10-03T22:17:07.52487Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-10-03T22:17:07.527625Z","iopub.execute_input":"2026-10-03T22:17:07.527955Z","iopub.status.idle":"2026-10-03T22:17:07.543979Z","shell.execute_reply.started":"2026-10-03T22:17:07.527926Z","shell.execute_reply":"2026-10-03T22:17:07.543125Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:07.545265Z","iopub.execute_input":"2026-10-03T22:17:07.545811Z","iopub.status.idle":"2026-10-03T22:17:07.551219Z","shell.execute_reply.started":"2026-10-03T22:17:07.545784Z","shell.execute_reply":"2026-10-03T22:17:07.550135Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# baseline model for the dogs vs cats dataset\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:07.554369Z","iopub.execute_input":"2026-10-03T22:17:07.554675Z","iopub.status.idle":"2026-10-03T22:17:07.562058Z","shell.execute_reply.started":"2026-10-03T22:17:07.554651Z","shell.execute_reply":"2026-10-03T22:17:07.561327Z"}},"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":"2026-10-03T22:17:07.56335Z","iopub.execute_input":"2026-10-03T22:17:07.564223Z","iopub.status.idle":"2026-10-03T22:17:07.574892Z","shell.execute_reply.started":"2026-10-03T22:17:07.564188Z","shell.execute_reply":"2026-10-03T22:17:07.574149Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:07.576002Z","iopub.execute_input":"2026-10-03T22:17:07.57636Z","iopub.status.idle":"2026-10-03T22:17:09.789776Z","shell.execute_reply.started":"2026-10-03T22:17:07.576327Z","shell.execute_reply":"2026-10-03T22:17:09.788574Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot diagnostic learning curves\ndef summarize_diagnostics(history):\n    # plot loss\n    pyplot.subplot(211)\n    pyplot.title('Cross Entropy Loss')\n    pyplot.plot(history.history['loss'], color='blue', label='train')\n    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n    # plot accuracy\n    pyplot.subplot(212)\n    pyplot.title('Classification Accuracy')\n    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n    \n    # save plot to file\n    filename = sys.argv[0].split('/')[-1]\n    pyplot.savefig(filename + '_plot.png') \n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:09.791195Z","iopub.execute_input":"2026-10-03T22:17:09.791587Z","iopub.status.idle":"2026-10-03T22:17:09.798973Z","shell.execute_reply.started":"2026-10-03T22:17:09.791549Z","shell.execute_reply":"2026-10-03T22:17:09.797737Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(2, activation='softmax'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:09.800472Z","iopub.execute_input":"2026-10-03T22:17:09.800942Z","iopub.status.idle":"2026-10-03T22:17:09.882857Z","shell.execute_reply.started":"2026-10-03T22:17:09.800876Z","shell.execute_reply":"2026-10-03T22:17:09.881902Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:09.884418Z","iopub.execute_input":"2026-10-03T22:17:09.884822Z","iopub.status.idle":"2026-10-03T22:17:09.979001Z","shell.execute_reply.started":"2026-10-03T22:17:09.884783Z","shell.execute_reply":"2026-10-03T22:17:09.977744Z"}},"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":"2026-10-03T22:17:09.980556Z","iopub.execute_input":"2026-10-03T22:17:09.980962Z","iopub.status.idle":"2026-10-03T22:17:10.086365Z","shell.execute_reply.started":"2026-10-03T22:17:09.980925Z","shell.execute_reply":"2026-10-03T22:17:10.08558Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:10.087498Z","iopub.execute_input":"2026-10-03T22:17:10.087803Z","iopub.status.idle":"2026-10-03T22:17:10.094256Z","shell.execute_reply.started":"2026-10-03T22:17:10.087778Z","shell.execute_reply":"2026-10-03T22:17:10.093134Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:10.095524Z","iopub.execute_input":"2026-10-03T22:17:10.095885Z","iopub.status.idle":"2026-10-03T22:17:11.243885Z","shell.execute_reply.started":"2026-10-03T22:17:10.095852Z","shell.execute_reply":"2026-10-03T22:17:11.242465Z"}},"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":"2026-10-03T22:17:36.753767Z","iopub.execute_input":"2026-10-03T22:17:36.754201Z","iopub.status.idle":"2026-10-03T22:17:36.758869Z","shell.execute_reply.started":"2026-10-03T22:17:36.754168Z","shell.execute_reply":"2026-10-03T22:17:36.758107Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True,\n    validation_split=0.2  # Defined here at initialization\n)\n\ntrain_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/train'\n\n# 2. Extract the training subset (80% of data)\ntrain_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='training',     # Explicitly request the training partition\n    shuffle=True           # Stochastic sampling is standard for training\n)\n\n# 3. Extract the validation subset (20% of data)\nval_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='validation',   # Explicitly request the validation partition\n    shuffle=False          # Disable shuffle to maintain index alignment for metrics\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:17:37.73484Z","iopub.execute_input":"2026-10-03T22:17:37.735697Z","iopub.status.idle":"2026-10-03T22:18:05.020709Z","shell.execute_reply.started":"2026-10-03T22:17:37.735632Z","shell.execute_reply":"2026-10-03T22:18:05.01989Z"}},"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":"2026-10-03T22:19:09.010191Z","iopub.execute_input":"2026-10-03T22:19:09.010582Z","iopub.status.idle":"2026-10-03T22:19:10.950186Z","shell.execute_reply.started":"2026-10-03T22:19:09.010558Z","shell.execute_reply":"2026-10-03T22:19:10.949359Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_it), len(train_it.classes), train_it.classes[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:13.896351Z","iopub.execute_input":"2026-10-03T22:19:13.896689Z","iopub.status.idle":"2026-10-03T22:19:13.904308Z","shell.execute_reply.started":"2026-10-03T22:19:13.896664Z","shell.execute_reply":"2026-10-03T22:19:13.903283Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(val_it), len(val_it.classes), val_it.classes[-10:]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:14.14148Z","iopub.execute_input":"2026-10-03T22:19:14.14197Z","iopub.status.idle":"2026-10-03T22:19:14.150551Z","shell.execute_reply.started":"2026-10-03T22:19:14.141936Z","shell.execute_reply":"2026-10-03T22:19:14.149543Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\n# model_1.reset_states()\n# history_1 = model_1.fit(\n#     train_it,\n#     steps_per_epoch=len(train_it),\n#     validation_data=val_it,\n#     validation_steps=len(val_it),\n#     epochs=EPOCHS,\n#     verbose=2,\n#     callbacks = [PlotLossesKeras()]\n#     )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:22.66369Z","iopub.execute_input":"2026-10-03T22:19:22.664698Z","iopub.status.idle":"2026-10-03T22:19:22.668597Z","shell.execute_reply.started":"2026-10-03T22:19:22.664663Z","shell.execute_reply":"2026-10-03T22:19:22.667631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:23.246545Z","iopub.execute_input":"2026-10-03T22:19:23.247023Z","iopub.status.idle":"2026-10-03T22:19:23.251057Z","shell.execute_reply.started":"2026-10-03T22:19:23.246991Z","shell.execute_reply":"2026-10-03T22:19:23.25015Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n# _, acc = model_1.evaluate(val_it, steps=len(val_it), verbose=1)\n# print('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:24.878257Z","iopub.execute_input":"2026-10-03T22:19:24.878729Z","iopub.status.idle":"2026-10-03T22:19:24.882318Z","shell.execute_reply.started":"2026-10-03T22:19:24.878699Z","shell.execute_reply":"2026-10-03T22:19:24.881455Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Create test datagenerator from 308-456 Dogs vs Cats ","metadata":{}},{"cell_type":"code","source":"ls /kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:25.798062Z","iopub.execute_input":"2026-10-03T22:19:25.79862Z","iopub.status.idle":"2026-10-03T22:19:26.825337Z","shell.execute_reply.started":"2026-10-03T22:19:25.798589Z","shell.execute_reply":"2026-10-03T22:19:26.824391Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport pandas as pd\nfrom glob import glob\n\n# Define the image folder path\ntest_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test'\n\nprint(test_path)\n# # List all .jpg files in the directory (adjust the pattern if needed)\n# image_files = glob(os.path.join(image_folder, '*.jpg'))\n\n# # Check if images were found\n# if not image_files:\n#     print(\"No images found. Please verify the directory and file extensions.\")\n    \n# # Create a DataFrame with the file paths\n# test_df = pd.DataFrame({'filename': image_files})\n\n# If your use-case doesn't require labels (for example, during testing), you can leave out the label column.\n# Otherwise, if you need a dummy label, you can add one:\n# df['class'] = 'dummy_label'\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:28.654347Z","iopub.execute_input":"2026-10-03T22:19:28.654851Z","iopub.status.idle":"2026-10-03T22:19:28.661255Z","shell.execute_reply.started":"2026-10-03T22:19:28.654818Z","shell.execute_reply":"2026-10-03T22:19:28.660333Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:30.216838Z","iopub.execute_input":"2026-10-03T22:19:30.217219Z","iopub.status.idle":"2026-10-03T22:19:30.221747Z","shell.execute_reply.started":"2026-10-03T22:19:30.21719Z","shell.execute_reply":"2026-10-03T22:19:30.220719Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:30.382269Z","iopub.execute_input":"2026-10-03T22:19:30.382727Z","iopub.status.idle":"2026-10-03T22:19:30.387634Z","shell.execute_reply.started":"2026-10-03T22:19:30.382698Z","shell.execute_reply":"2026-10-03T22:19:30.38647Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:30.540813Z","iopub.execute_input":"2026-10-03T22:19:30.541508Z","iopub.status.idle":"2026-10-03T22:19:30.54728Z","shell.execute_reply.started":"2026-10-03T22:19:30.541476Z","shell.execute_reply":"2026-10-03T22:19:30.546245Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:30.654874Z","iopub.execute_input":"2026-10-03T22:19:30.655669Z","iopub.status.idle":"2026-10-03T22:19:30.659907Z","shell.execute_reply.started":"2026-10-03T22:19:30.655637Z","shell.execute_reply":"2026-10-03T22:19:30.658861Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:32.014318Z","iopub.execute_input":"2026-10-03T22:19:32.014799Z","iopub.status.idle":"2026-10-03T22:19:32.020597Z","shell.execute_reply.started":"2026-10-03T22:19:32.014769Z","shell.execute_reply":"2026-10-03T22:19:32.019803Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # Create test data generator\n# from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# # Initialize your ImageDataGenerator (modify parameters as needed)\n# datagen_test = ImageDataGenerator(rescale=1./255,\n#                                  vertical_flip=True)\n\n# # Create the data generator using the DataFrame\n# test_it = datagen_test.flow_from_dataframe(\n#     dataframe=test_df,\n#     x_col='filename',\n#     y_col=None,            # No labels for testing, so set to None\n#     target_size=IMAGE_SIZE,\n#     batch_size=BATCH_SIZE,\n#     class_mode=None,       # Since there are no labels\n#     # shuffle=True,         # Usually testing data should not be shuffled\n#     shuffle=False,\n# )\n\n# type(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:32.790385Z","iopub.execute_input":"2026-10-03T22:19:32.791362Z","iopub.status.idle":"2026-10-03T22:19:32.797427Z","shell.execute_reply.started":"2026-10-03T22:19:32.79133Z","shell.execute_reply":"2026-10-03T22:19:32.796207Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:34.926247Z","iopub.execute_input":"2026-10-03T22:19:34.926797Z","iopub.status.idle":"2026-10-03T22:19:34.932953Z","shell.execute_reply.started":"2026-10-03T22:19:34.926763Z","shell.execute_reply":"2026-10-03T22:19:34.932129Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 1. Instantiate the generator with the validation_split ratio\ntest_datagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True\n)\n\ntest_it = test_datagen.flow_from_directory(\n    test_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE)\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:53.235656Z","iopub.execute_input":"2026-10-03T22:19:53.236569Z","iopub.status.idle":"2026-10-03T22:19:55.262121Z","shell.execute_reply.started":"2026-10-03T22:19:53.236533Z","shell.execute_reply":"2026-10-03T22:19:55.261364Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_exmaple(images, labels):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(labels[i]))  # Fixed: set_title instead of title\n            # ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n            ax.axis(\"on\")\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:55.263607Z","iopub.execute_input":"2026-10-03T22:19:55.263972Z","iopub.status.idle":"2026-10-03T22:19:55.269841Z","shell.execute_reply.started":"2026-10-03T22:19:55.263947Z","shell.execute_reply":"2026-10-03T22:19:55.268974Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_images, train_labels = train_it.__next__()\nprint(train_images.shape, len(train_labels))\nplot_exmaple(train_images, train_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:19:55.271181Z","iopub.execute_input":"2026-10-03T22:19:55.271493Z","iopub.status.idle":"2026-10-03T22:20:01.895994Z","shell.execute_reply.started":"2026-10-03T22:19:55.271464Z","shell.execute_reply":"2026-10-03T22:20:01.894662Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_images, val_labels = val_it.__next__()\nval_images.shape\nplot_exmaple(val_images, val_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:01.89824Z","iopub.execute_input":"2026-10-03T22:20:01.898592Z","iopub.status.idle":"2026-10-03T22:20:09.035997Z","shell.execute_reply.started":"2026-10-03T22:20:01.898564Z","shell.execute_reply":"2026-10-03T22:20:09.034935Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_exmaple_test(images, indices):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(indices[i]))  # ตั้งค่า title ด้วย index จาก list/array indices\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:15.712571Z","iopub.execute_input":"2026-10-03T22:20:15.71292Z","iopub.status.idle":"2026-10-03T22:20:15.724444Z","shell.execute_reply.started":"2026-10-03T22:20:15.712888Z","shell.execute_reply":"2026-10-03T22:20:15.723325Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images, test_labels = test_it.__next__()  # หรือ next(test_it)\nprint(f\"{test_images.shape=}, {test_labels.shape}\")\n\n# สร้าง list เลขดัชนีตามจำนวนภาพที่มี\nindices = list(range(len(test_images)))\n\nplot_exmaple(test_images, test_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:15.725694Z","iopub.execute_input":"2026-10-03T22:20:15.7263Z","iopub.status.idle":"2026-10-03T22:20:21.822439Z","shell.execute_reply.started":"2026-10-03T22:20:15.726268Z","shell.execute_reply":"2026-10-03T22:20:21.821395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import numpy as np\n\n\n# # 1. สุ่ม index มา 10 ตัวจากชุดข้อมูล\n# sample_indices = np.random.choice(len(test_images), size=10, replace=False)\n# sample_images = test_images[sample_indices]\n\n# # 2. Predict \n# predictions = model_1.predict(sample_images)\n# predicted_classes = np.argmax(predictions, axis=1)  # ดึง class ที่ได้คะแนนสูงสุด\n\n# # 3. แสดงผล 10 ภาพ (ปรับเป็น grid 2x5)\n# fig, axes = plt.subplots(2, 5, figsize=(15, 6))\n# axes = axes.flatten()\n\n# for i, ax in enumerate(axes):\n#     ax.imshow(sample_images[i])\n#     # แสดง Index เดิม และ Class ที่ทายได้\n#     ax.set_title(f\"Idx: {sample_indices[i]}\\nPred: {predicted_classes[i]}\")\n#     ax.axis(\"off\")\n\n# plt.tight_layout()\n# plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:21.823744Z","iopub.execute_input":"2026-10-03T22:20:21.824098Z","iopub.status.idle":"2026-10-03T22:20:21.829249Z","shell.execute_reply.started":"2026-10-03T22:20:21.824048Z","shell.execute_reply":"2026-10-03T22:20:21.82826Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 2026-09-13\n# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:21.831648Z","iopub.execute_input":"2026-10-03T22:20:21.832308Z","iopub.status.idle":"2026-10-03T22:20:21.842751Z","shell.execute_reply.started":"2026-10-03T22:20:21.832274Z","shell.execute_reply":"2026-10-03T22:20:21.841742Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:21.843944Z","iopub.execute_input":"2026-10-03T22:20:21.844535Z","iopub.status.idle":"2026-10-03T22:20:21.855728Z","shell.execute_reply.started":"2026-10-03T22:20:21.844502Z","shell.execute_reply":"2026-10-03T22:20:21.854926Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Create transfer learning model for VGG16\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# Hyperparameter => changable\nIMAGE_SIZE = 224\nBATCH_SIE = 64\nEPOCHS = 20\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\n\t# mark loaded layers as not trainable\n\tfor layer in model.layers:\n\t\tlayer.trainable = False\n\t# add new classifier layers\n\tflat1 = Flatten()(model.layers[-1].output)\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\toutput = Dense(1, activation='sigmoid')(class1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model\n\nvgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:20:28.119246Z","iopub.execute_input":"2026-10-03T22:20:28.120226Z","iopub.status.idle":"2026-10-03T22:20:30.688405Z","shell.execute_reply.started":"2026-10-03T22:20:28.12019Z","shell.execute_reply":"2026-10-03T22:20:30.687337Z"}},"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":"2026-10-03T22:20:35.26493Z","iopub.execute_input":"2026-10-03T22:20:35.266067Z","iopub.status.idle":"2026-10-03T22:20:51.217448Z","shell.execute_reply.started":"2026-10-03T22:20:35.266028Z","shell.execute_reply":"2026-10-03T22:20:51.216423Z"}},"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":"2026-10-03T22:20:51.219431Z","iopub.execute_input":"2026-10-03T22:20:51.219814Z","iopub.status.idle":"2026-10-03T22:20:51.643046Z","shell.execute_reply.started":"2026-10-03T22:20:51.219778Z","shell.execute_reply":"2026-10-03T22:20:51.641926Z"}},"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":"2026-10-03T22:20:51.645606Z","iopub.execute_input":"2026-10-03T22:20:51.645958Z","iopub.status.idle":"2026-10-03T22:20:51.65186Z","shell.execute_reply.started":"2026-10-03T22:20:51.64593Z","shell.execute_reply":"2026-10-03T22:20:51.650758Z"}},"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":"2026-10-03T22:21:12.241847Z","iopub.execute_input":"2026-10-03T22:21:12.242735Z","iopub.status.idle":"2026-10-03T22:21:12.249212Z","shell.execute_reply.started":"2026-10-03T22:21:12.242701Z","shell.execute_reply":"2026-10-03T22:21:12.248104Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:12.464896Z","iopub.execute_input":"2026-10-03T22:21:12.465493Z","iopub.status.idle":"2026-10-03T22:21:12.472613Z","shell.execute_reply.started":"2026-10-03T22:21:12.465459Z","shell.execute_reply":"2026-10-03T22:21:12.471639Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use functional API\nflat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\nprint(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:15.655163Z","iopub.execute_input":"2026-10-03T22:21:15.655501Z","iopub.status.idle":"2026-10-03T22:21:15.6658Z","shell.execute_reply.started":"2026-10-03T22:21:15.655478Z","shell.execute_reply":"2026-10-03T22:21:15.664949Z"}},"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":"2026-10-03T22:21:15.814644Z","iopub.execute_input":"2026-10-03T22:21:15.815352Z","iopub.status.idle":"2026-10-03T22:21:15.833575Z","shell.execute_reply.started":"2026-10-03T22:21:15.815317Z","shell.execute_reply":"2026-10-03T22:21:15.832683Z"}},"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":"2026-10-03T22:21:16.039885Z","iopub.execute_input":"2026-10-03T22:21:16.04024Z","iopub.status.idle":"2026-10-03T22:21:16.057443Z","shell.execute_reply.started":"2026-10-03T22:21:16.040214Z","shell.execute_reply":"2026-10-03T22:21:16.056157Z"}},"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":"2026-10-03T22:21:16.519587Z","iopub.execute_input":"2026-10-03T22:21:16.520583Z","iopub.status.idle":"2026-10-03T22:21:16.53773Z","shell.execute_reply.started":"2026-10-03T22:21:16.520538Z","shell.execute_reply":"2026-10-03T22:21:16.536798Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output2 = Dense(1, activation='sigmoid')(layer2)\nprint(output2.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:18.137885Z","iopub.execute_input":"2026-10-03T22:21:18.139006Z","iopub.status.idle":"2026-10-03T22:21:18.156571Z","shell.execute_reply.started":"2026-10-03T22:21:18.138969Z","shell.execute_reply":"2026-10-03T22:21:18.155659Z"}},"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":"2026-10-03T22:21:18.359839Z","iopub.execute_input":"2026-10-03T22:21:18.360288Z","iopub.status.idle":"2026-10-03T22:21:18.379057Z","shell.execute_reply.started":"2026-10-03T22:21:18.360252Z","shell.execute_reply":"2026-10-03T22:21:18.378145Z"}},"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":"2026-10-03T22:21:19.615283Z","iopub.execute_input":"2026-10-03T22:21:19.615629Z","iopub.status.idle":"2026-10-03T22:21:19.621127Z","shell.execute_reply.started":"2026-10-03T22:21:19.615603Z","shell.execute_reply":"2026-10-03T22:21:19.620168Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:19.782993Z","iopub.execute_input":"2026-10-03T22:21:19.783593Z","iopub.status.idle":"2026-10-03T22:21:19.842068Z","shell.execute_reply.started":"2026-10-03T22:21:19.783556Z","shell.execute_reply":"2026-10-03T22:21:19.840684Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:19.898807Z","iopub.execute_input":"2026-10-03T22:21:19.899161Z","iopub.status.idle":"2026-10-03T22:21:20.260558Z","shell.execute_reply.started":"2026-10-03T22:21:19.899134Z","shell.execute_reply":"2026-10-03T22:21:20.259408Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# del ตัวแปร #ลบตัวแปรออกจากหน่วยความจำ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:20.262484Z","iopub.execute_input":"2026-10-03T22:21:20.262939Z","iopub.status.idle":"2026-10-03T22:21:20.273486Z","shell.execute_reply.started":"2026-10-03T22:21:20.262912Z","shell.execute_reply":"2026-10-03T22:21:20.272517Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:21:23.68716Z","iopub.execute_input":"2026-10-03T22:21:23.687515Z","iopub.status.idle":"2026-10-03T22:21:23.69215Z","shell.execute_reply.started":"2026-10-03T22:21:23.687488Z","shell.execute_reply":"2026-10-03T22:21:23.691132Z"}},"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":"2026-10-03T22:21:25.00746Z","iopub.execute_input":"2026-10-03T22:21:25.008008Z","iopub.status.idle":"2026-10-03T22:27:34.13094Z","shell.execute_reply.started":"2026-10-03T22:21:25.007976Z","shell.execute_reply":"2026-10-03T22:27:34.130145Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:27:34.132669Z","iopub.execute_input":"2026-10-03T22:27:34.133116Z","iopub.status.idle":"2026-10-03T22:27:34.464601Z","shell.execute_reply.started":"2026-10-03T22:27:34.133049Z","shell.execute_reply":"2026-10-03T22:27:34.463826Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_vgg16.evaluate(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:27:34.46569Z","iopub.execute_input":"2026-10-03T22:27:34.466268Z","iopub.status.idle":"2026-10-03T22:27:37.221749Z","shell.execute_reply.started":"2026-10-03T22:27:34.466239Z","shell.execute_reply":"2026-10-03T22:27:37.22091Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model for the test set\n_, test_acc = model_vgg16.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (test_acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:27:37.224515Z","iopub.execute_input":"2026-10-03T22:27:37.225438Z","iopub.status.idle":"2026-10-03T22:28:53.33735Z","shell.execute_reply.started":"2026-10-03T22:27:37.225411Z","shell.execute_reply":"2026-10-03T22:28:53.336157Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\n# 1. Reset the generator state to ensure alignment from index 0\ntest_it.reset()\n\n# 2. Extract the ordered ground truth labels from the generator\ny_true = test_it.classes\nprint(y_true.shape)\n\n# 3. Execute the forward pass over the entire test dataset\n# Calculate exact steps to prevent infinite looping or partial evaluation\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobabilities = model_vgg16.predict(test_it, steps=steps, verbose=1).squeeze()\nprint(probabilities.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:28:53.338762Z","iopub.execute_input":"2026-10-03T22:28:53.340008Z","iopub.status.idle":"2026-10-03T22:29:24.4054Z","shell.execute_reply.started":"2026-10-03T22:28:53.339968Z","shell.execute_reply":"2026-10-03T22:29:24.404382Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:29:24.406645Z","iopub.execute_input":"2026-10-03T22:29:24.407038Z","iopub.status.idle":"2026-10-03T22:29:24.41666Z","shell.execute_reply.started":"2026-10-03T22:29:24.407011Z","shell.execute_reply":"2026-10-03T22:29:24.415574Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:29:24.417865Z","iopub.execute_input":"2026-10-03T22:29:24.418204Z","iopub.status.idle":"2026-10-03T22:29:24.435169Z","shell.execute_reply.started":"2026-10-03T22:29:24.418177Z","shell.execute_reply":"2026-10-03T22:29:24.434022Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 4. Discretize continuous logistic probabilities into binary class predictions\ny_pred = (probabilities > 0.5).astype(int)\nprint(y_pred.shape)\n\n# 5. Extract dynamic class labels mapping (e.g., {'cats': 0, 'dogs': 1})\n# This ensures the report correctly maps index 0 and 1 to your string labels\ntarget_names = list(test_it.class_indices.keys())\n\n# 6. Compute and output the classification report\nreport = classification_report(y_true, y_pred, target_names=target_names)\nprint(report)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:29:24.4364Z","iopub.execute_input":"2026-10-03T22:29:24.43679Z","iopub.status.idle":"2026-10-03T22:29:24.472317Z","shell.execute_reply.started":"2026-10-03T22:29:24.436765Z","shell.execute_reply":"2026-10-03T22:29:24.471154Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:29:24.473714Z","iopub.execute_input":"2026-10-03T22:29:24.474591Z","iopub.status.idle":"2026-10-03T22:29:24.481916Z","shell.execute_reply.started":"2026-10-03T22:29:24.474552Z","shell.execute_reply":"2026-10-03T22:29:24.480963Z"}},"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(4):\n    batch_images, batch_labels = next(test_it)\n    images_list.append(batch_images)\n    labels_list.append(batch_labels)\n\n# Concatenate into a single tensor\nall_images = np.concatenate(images_list, axis=0)\nall_labels = np.concatenate(labels_list, axis=0)\n\n# 2. Stochastically sample 100 unique indices\nnp.random.seed(42) # For reproducibility\nrandom_indices = np.random.choice(all_images.shape[0], size=100, replace=False)\n\nsample_images = all_images[random_indices]\nsample_labels = all_labels[random_indices]\n\n# 3. Execute the forward pass\n# Squeeze is used to convert shape (100, 1) to (100,)\nprobabilities = model_vgg16.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}\n\nprint(\"Done.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:31:49.184921Z","iopub.execute_input":"2026-10-03T22:31:49.185377Z","iopub.status.idle":"2026-10-03T22:31:51.464919Z","shell.execute_reply.started":"2026-10-03T22:31:49.185345Z","shell.execute_reply":"2026-10-03T22:31:51.46399Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Initialize a 10x10 matrix visualization\nfig, axes = plt.subplots(10, 10, figsize=(20, 22))\naxes = axes.flatten()\n\nfor i in range(100):\n    ax = axes[i]\n    \n    # Isolate image tensor. \n    # NOTE: If your VGG16 preprocessor applies mean-centering (caffe style) \n    # instead of standard [0,1] scaling, you must reverse it here for correct plt.imshow() rendering.\n    # We assume standard [0, 1] or [0, 255] spatial tensors below.\n    img = sample_images[i]\n    if img.max() > 1.0 or img.min() < 0:\n        # Simple normalization for display purposes\n        img = (img - img.min()) / (img.max() - img.min())\n        \n    ax.imshow(img)\n    ax.axis('off')\n    \n    # Extract structural labels\n    gt_class = class_mapping[int(sample_labels[i])]\n    pred_class = class_mapping[predictions[i]]\n    prob = probabilities[i]\n    \n    # Apply conditional color coding (Green for True Positives/Negatives, Red for False Positives/Negatives)\n    text_color = 'darkgreen' if gt_class == pred_class else 'darkred'\n    \n    title_str = f\"GT: {gt_class}\\nPred: {pred_class}\\nProb: {prob:.3f}\"\n    ax.set_title(title_str, color=text_color, fontsize=9, pad=4)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:32:05.871496Z","iopub.execute_input":"2026-10-03T22:32:05.872353Z","iopub.status.idle":"2026-10-03T22:32:15.828297Z","shell.execute_reply.started":"2026-10-03T22:32:05.872299Z","shell.execute_reply":"2026-10-03T22:32:15.826315Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","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 keras.models import Model\nfrom keras.layers import Dense, Flatten\nfrom keras.optimizers import SGD\n\ndef define_model_inceptionv3():\n    model = InceptionV3(include_top=False, input_shape=(224, 224, 3))\n    \n    for layer in model.layers:\n        layer.trainable = False\n    \n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n\n    output = Dense(1, activation='sigmoid')(class4)\n    \n    model = Model(inputs=model.inputs, outputs=output)\n\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\nmodel_inceptionv3 = define_model_inceptionv3()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:32:57.538336Z","iopub.execute_input":"2026-10-03T22:32:57.538709Z","iopub.status.idle":"2026-10-03T22:33:03.206838Z","shell.execute_reply.started":"2026-10-03T22:32:57.538682Z","shell.execute_reply":"2026-10-03T22:33:03.205923Z"}},"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":"2026-10-03T22:33:03.208436Z","iopub.execute_input":"2026-10-03T22:33:03.209423Z","iopub.status.idle":"2026-10-03T22:33:06.163282Z","shell.execute_reply.started":"2026-10-03T22:33:03.209394Z","shell.execute_reply":"2026-10-03T22:33:06.162324Z"},"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":"2026-10-03T22:33:06.164479Z","iopub.execute_input":"2026-10-03T22:33:06.164819Z","iopub.status.idle":"2026-10-03T22:33:06.171611Z","shell.execute_reply.started":"2026-10-03T22:33:06.164786Z","shell.execute_reply":"2026-10-03T22:33:06.170659Z"}},"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":"2026-10-03T22:33:06.173511Z","iopub.execute_input":"2026-10-03T22:33:06.174143Z","iopub.status.idle":"2026-10-03T22:33:06.186926Z","shell.execute_reply.started":"2026-10-03T22:33:06.174061Z","shell.execute_reply":"2026-10-03T22:33:06.18595Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=5, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:33:06.614602Z","iopub.execute_input":"2026-10-03T22:33:06.615385Z","iopub.status.idle":"2026-10-03T22:34:10.428918Z","shell.execute_reply.started":"2026-10-03T22:33:06.615349Z","shell.execute_reply":"2026-10-03T22:34:10.428138Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\ntest_it.reset()\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobs_inc = model_inceptionv3.predict(test_it, steps=steps, verbose=1).squeeze()\n\ny_pred_inc = (probs_inc > 0.5).astype(int)\nprint(\"=== Classification Report: InceptionV3 ===\")\nprint(classification_report(test_it.classes, y_pred_inc, target_names=list(test_it.class_indices.keys())))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:34:10.430635Z","iopub.execute_input":"2026-10-03T22:34:10.430995Z","iopub.status.idle":"2026-10-03T22:34:36.624804Z","shell.execute_reply.started":"2026-10-03T22:34:10.430964Z","shell.execute_reply":"2026-10-03T22:34:36.623496Z"}},"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":"2026-10-03T22:35:22.866834Z","iopub.execute_input":"2026-10-03T22:35:22.86769Z","iopub.status.idle":"2026-10-03T22:35:22.875869Z","shell.execute_reply.started":"2026-10-03T22:35:22.867653Z","shell.execute_reply":"2026-10-03T22:35:22.874729Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:35:26.410434Z","iopub.execute_input":"2026-10-03T22:35:26.411159Z","iopub.status.idle":"2026-10-03T22:35:26.416803Z","shell.execute_reply.started":"2026-10-03T22:35:26.411111Z","shell.execute_reply":"2026-10-03T22:35:26.41556Z"}},"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":"2026-10-03T22:35:26.604258Z","iopub.execute_input":"2026-10-03T22:35:26.605205Z","iopub.status.idle":"2026-10-03T22:35:26.60938Z","shell.execute_reply.started":"2026-10-03T22:35:26.605168Z","shell.execute_reply":"2026-10-03T22:35:26.608204Z"}},"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":"2026-10-03T22:35:26.764832Z","iopub.execute_input":"2026-10-03T22:35:26.765379Z","iopub.status.idle":"2026-10-03T22:35:26.770194Z","shell.execute_reply.started":"2026-10-03T22:35:26.765344Z","shell.execute_reply":"2026-10-03T22:35:26.769058Z"}},"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":"2026-10-03T22:35:28.143125Z","iopub.execute_input":"2026-10-03T22:35:28.144217Z","iopub.status.idle":"2026-10-03T22:35:51.194037Z","shell.execute_reply.started":"2026-10-03T22:35:28.144171Z","shell.execute_reply":"2026-10-03T22:35:51.192907Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images, labels = test_it.__next__()\nprint(images.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:36:31.426459Z","iopub.execute_input":"2026-10-03T22:36:31.427281Z","iopub.status.idle":"2026-10-03T22:36:31.522728Z","shell.execute_reply.started":"2026-10-03T22:36:31.427237Z","shell.execute_reply":"2026-10-03T22:36:31.521775Z"}},"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":"2026-10-03T22:36:34.819003Z","iopub.execute_input":"2026-10-03T22:36:34.820167Z","iopub.status.idle":"2026-10-03T22:36:34.826636Z","shell.execute_reply.started":"2026-10-03T22:36:34.820113Z","shell.execute_reply":"2026-10-03T22:36:34.825486Z"}},"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":"2026-10-03T22:36:37.667517Z","iopub.execute_input":"2026-10-03T22:36:37.668498Z","iopub.status.idle":"2026-10-03T22:36:39.060373Z","shell.execute_reply.started":"2026-10-03T22:36:37.66846Z","shell.execute_reply":"2026-10-03T22:36:39.059511Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.applications import MobileNetV2\nfrom keras.models import Model\nfrom keras.layers import Dense, Flatten\nfrom keras.optimizers import SGD\n\ndef define_model_mobilenetv2():\n    model = MobileNetV2(include_top=False, input_shape=(224, 224, 3))\n    \n    for layer in model.layers:\n        layer.trainable = False\n        \n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n    output = Dense(1, activation='sigmoid')(class1)\n    \n    model = Model(inputs=model.inputs, outputs=output)\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\nmodel_mobilenet = define_model_mobilenetv2()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:39:15.355375Z","iopub.execute_input":"2026-10-03T22:39:15.355756Z","iopub.status.idle":"2026-10-03T22:39:18.011019Z","shell.execute_reply.started":"2026-10-03T22:39:15.355729Z","shell.execute_reply":"2026-10-03T22:39:18.010102Z"}},"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=5, \n    verbose=1\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:39:27.270861Z","iopub.execute_input":"2026-10-03T22:39:27.27142Z","iopub.status.idle":"2026-10-03T22:40:25.103282Z","shell.execute_reply.started":"2026-10-03T22:39:27.271383Z","shell.execute_reply":"2026-10-03T22:40:25.102436Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\ntest_it.reset()\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobs_mob = model_mobilenet.predict(test_it, steps=steps, verbose=1).squeeze()\n\ny_pred_mob = (probs_mob > 0.5).astype(int)\nprint(classification_report(test_it.classes, y_pred_mob, target_names=list(test_it.class_indices.keys())))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T22:40:28.028332Z","iopub.execute_input":"2026-10-03T22:40:28.028863Z","iopub.status.idle":"2026-10-03T22:40:50.989728Z","shell.execute_reply.started":"2026-10-03T22:40:28.028817Z","shell.execute_reply":"2026-10-03T22:40:50.988513Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}