{"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":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:07.627219Z","iopub.execute_input":"2026-10-03T11:57:07.62758Z","iopub.status.idle":"2026-10-03T11:57:07.632763Z","shell.execute_reply.started":"2026-10-03T11:57:07.62754Z","shell.execute_reply":"2026-10-03T11:57:07.631754Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:07.63433Z","iopub.execute_input":"2026-10-03T11:57:07.634995Z","iopub.status.idle":"2026-10-03T11:57:08.670747Z","shell.execute_reply.started":"2026-10-03T11:57:07.634972Z","shell.execute_reply":"2026-10-03T11:57:08.669605Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:08.672855Z","iopub.execute_input":"2026-10-03T11:57:08.673191Z","iopub.status.idle":"2026-10-03T11:57:09.694266Z","shell.execute_reply.started":"2026-10-03T11:57:08.673162Z","shell.execute_reply":"2026-10-03T11:57:09.693298Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:09.696105Z","iopub.execute_input":"2026-10-03T11:57:09.696471Z","iopub.status.idle":"2026-10-03T11:57:20.021916Z","shell.execute_reply.started":"2026-10-03T11:57:09.696434Z","shell.execute_reply":"2026-10-03T11:57:20.021059Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:20.023852Z","iopub.execute_input":"2026-10-03T11:57:20.024157Z","iopub.status.idle":"2026-10-03T11:57:21.134682Z","shell.execute_reply.started":"2026-10-03T11:57:20.024132Z","shell.execute_reply":"2026-10-03T11:57:21.133146Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:21.136281Z","iopub.execute_input":"2026-10-03T11:57:21.136755Z","iopub.status.idle":"2026-10-03T11:57:22.183183Z","shell.execute_reply.started":"2026-10-03T11:57:21.136725Z","shell.execute_reply":"2026-10-03T11:57:22.18222Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:22.184966Z","iopub.execute_input":"2026-10-03T11:57:22.18535Z","iopub.status.idle":"2026-10-03T11:57:23.254374Z","shell.execute_reply.started":"2026-10-03T11:57:22.185316Z","shell.execute_reply":"2026-10-03T11:57:23.253248Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:23.255932Z","iopub.execute_input":"2026-10-03T11:57:23.256245Z","iopub.status.idle":"2026-10-03T11:57:24.378228Z","shell.execute_reply.started":"2026-10-03T11:57:23.256218Z","shell.execute_reply":"2026-10-03T11:57:24.377263Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:24.379713Z","iopub.execute_input":"2026-10-03T11:57:24.380361Z","iopub.status.idle":"2026-10-03T11:57:24.384691Z","shell.execute_reply.started":"2026-10-03T11:57:24.380332Z","shell.execute_reply":"2026-10-03T11:57:24.383779Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:24.385967Z","iopub.execute_input":"2026-10-03T11:57:24.386232Z","iopub.status.idle":"2026-10-03T11:57:25.493929Z","shell.execute_reply.started":"2026-10-03T11:57:24.38621Z","shell.execute_reply":"2026-10-03T11:57:25.492637Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:25.498673Z","iopub.execute_input":"2026-10-03T11:57:25.499341Z","iopub.status.idle":"2026-10-03T11:57:26.577455Z","shell.execute_reply.started":"2026-10-03T11:57:25.499313Z","shell.execute_reply":"2026-10-03T11:57:26.576466Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\n# from matplotlib import pyplot as plt\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'dog.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:26.579259Z","iopub.execute_input":"2026-10-03T11:57:26.579658Z","iopub.status.idle":"2026-10-03T11:57:27.56169Z","shell.execute_reply.started":"2026-10-03T11:57:26.579621Z","shell.execute_reply":"2026-10-03T11:57:27.560914Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot cat photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'cat.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:27.56275Z","iopub.execute_input":"2026-10-03T11:57:27.563035Z","iopub.status.idle":"2026-10-03T11:57:28.546881Z","shell.execute_reply.started":"2026-10-03T11:57:27.563011Z","shell.execute_reply":"2026-10-03T11:57:28.546053Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:28.547928Z","iopub.execute_input":"2026-10-03T11:57:28.54816Z","iopub.status.idle":"2026-10-03T11:57:29.568343Z","shell.execute_reply.started":"2026-10-03T11:57:28.54814Z","shell.execute_reply":"2026-10-03T11:57:29.567025Z"}},"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":"2026-10-03T11:57:29.570018Z","iopub.execute_input":"2026-10-03T11:57:29.57035Z","iopub.status.idle":"2026-10-03T11:57:29.576044Z","shell.execute_reply.started":"2026-10-03T11:57:29.570323Z","shell.execute_reply":"2026-10-03T11:57:29.575012Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load dogs vs cats dataset, reshape and save to a new file\nfrom os import listdir\nfrom numpy import asarray\nfrom numpy import save\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:29.577558Z","iopub.execute_input":"2026-10-03T11:57:29.578145Z","iopub.status.idle":"2026-10-03T11:57:29.588346Z","shell.execute_reply.started":"2026-10-03T11:57:29.578113Z","shell.execute_reply":"2026-10-03T11:57:29.587295Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n\t# determine class\n\toutput = 0.0\n\tif file.startswith('dog'):\n\t\toutput = 1.0\n\t# load image\n\tphoto = load_img(folder + file, target_size=(200, 200))\n\t# convert to numpy array\n\tphoto = img_to_array(photo)\n\t# store\n\tphotos.append(photo)\n\tlabels.append(output)\n# convert to a numpy arrays\nphotos = asarray(photos)\nlabels = asarray(labels)\nprint(photos.shape, labels.shape)\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:15.416611Z","iopub.execute_input":"2024-01-27T03:36:15.417128Z","iopub.status.idle":"2024-01-27T03:36:38.886396Z","shell.execute_reply.started":"2024-01-27T03:36:15.417101Z","shell.execute_reply":"2024-01-27T03:36:38.883149Z"}}},{"cell_type":"markdown","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:38.88711Z","iopub.status.idle":"2024-01-27T03:36:38.887458Z","shell.execute_reply.started":"2024-01-27T03:36:38.887281Z","shell.execute_reply":"2024-01-27T03:36:38.887296Z"}}},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:29.590341Z","iopub.execute_input":"2026-10-03T11:57:29.590667Z","iopub.status.idle":"2026-10-03T11:57:29.599499Z","shell.execute_reply.started":"2026-10-03T11:57:29.590633Z","shell.execute_reply":"2026-10-03T11:57:29.598631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/'] #test==>validation\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir       \n        makedirs(newdir, exist_ok=True)\n        print(newdir)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:29.600748Z","iopub.execute_input":"2026-10-03T11:57:29.601075Z","iopub.status.idle":"2026-10-03T11:57:29.612414Z","shell.execute_reply.started":"2026-10-03T11:57:29.601043Z","shell.execute_reply":"2026-10-03T11:57:29.611458Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:29.613636Z","iopub.execute_input":"2026-10-03T11:57:29.613963Z","iopub.status.idle":"2026-10-03T11:57:30.63862Z","shell.execute_reply.started":"2026-10-03T11:57:29.613941Z","shell.execute_reply":"2026-10-03T11:57:30.637638Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:30.640458Z","iopub.execute_input":"2026-10-03T11:57:30.640774Z","iopub.status.idle":"2026-10-03T11:57:31.684362Z","shell.execute_reply.started":"2026-10-03T11:57:30.640746Z","shell.execute_reply":"2026-10-03T11:57:31.683398Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:31.68613Z","iopub.execute_input":"2026-10-03T11:57:31.686501Z","iopub.status.idle":"2026-10-03T11:57:32.710436Z","shell.execute_reply.started":"2026-10-03T11:57:31.686464Z","shell.execute_reply":"2026-10-03T11:57:32.709373Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1337)\n# define ratio of pictures to use for validation\nval_ratio = 0.25 #changable\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\n\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:32.711972Z","iopub.execute_input":"2026-10-03T11:57:32.712292Z","iopub.status.idle":"2026-10-03T11:57:36.023744Z","shell.execute_reply.started":"2026-10-03T11:57:32.712265Z","shell.execute_reply":"2026-10-03T11:57:36.022618Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:36.024972Z","iopub.execute_input":"2026-10-03T11:57:36.025256Z","iopub.status.idle":"2026-10-03T11:57:36.030451Z","shell.execute_reply.started":"2026-10-03T11:57:36.025229Z","shell.execute_reply":"2026-10-03T11:57:36.029638Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:36.031847Z","iopub.execute_input":"2026-10-03T11:57:36.032176Z","iopub.status.idle":"2026-10-03T11:57:38.216013Z","shell.execute_reply.started":"2026-10-03T11:57:36.032144Z","shell.execute_reply":"2026-10-03T11:57:38.215119Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#validation set\n!ls -l dataset_dogs_vs_cats/test/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/test/cats | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:38.217886Z","iopub.execute_input":"2026-10-03T11:57:38.218299Z","iopub.status.idle":"2026-10-03T11:57:40.433252Z","shell.execute_reply.started":"2026-10-03T11:57:38.218261Z","shell.execute_reply":"2026-10-03T11:57:40.431772Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:40.435185Z","iopub.execute_input":"2026-10-03T11:57:40.435643Z","iopub.status.idle":"2026-10-03T11:57:48.88761Z","shell.execute_reply.started":"2026-10-03T11:57:40.435604Z","shell.execute_reply":"2026-10-03T11:57:48.886362Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:48.889511Z","iopub.execute_input":"2026-10-03T11:57:48.889908Z","iopub.status.idle":"2026-10-03T11:57:48.894978Z","shell.execute_reply.started":"2026-10-03T11:57:48.889871Z","shell.execute_reply":"2026-10-03T11:57:48.894057Z"}},"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":"2026-10-03T11:57:48.896253Z","iopub.execute_input":"2026-10-03T11:57:48.896657Z","iopub.status.idle":"2026-10-03T11:57:48.906214Z","shell.execute_reply.started":"2026-10-03T11:57:48.896632Z","shell.execute_reply":"2026-10-03T11:57:48.905235Z"}},"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":"2026-10-03T11:57:48.91342Z","iopub.execute_input":"2026-10-03T11:57:48.9144Z","iopub.status.idle":"2026-10-03T11:57:48.919305Z","shell.execute_reply.started":"2026-10-03T11:57:48.914375Z","shell.execute_reply":"2026-10-03T11:57:48.918458Z"}},"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":"2026-10-03T11:57:48.92049Z","iopub.execute_input":"2026-10-03T11:57:48.920967Z","iopub.status.idle":"2026-10-03T11:57:48.930476Z","shell.execute_reply.started":"2026-10-03T11:57:48.920943Z","shell.execute_reply":"2026-10-03T11:57:48.929766Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:48.931525Z","iopub.execute_input":"2026-10-03T11:57:48.93274Z","iopub.status.idle":"2026-10-03T11:57:49.009548Z","shell.execute_reply.started":"2026-10-03T11:57:48.932715Z","shell.execute_reply":"2026-10-03T11:57:49.00853Z"}},"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":"2026-10-03T11:57:49.011928Z","iopub.execute_input":"2026-10-03T11:57:49.012216Z","iopub.status.idle":"2026-10-03T11:57:49.018291Z","shell.execute_reply.started":"2026-10-03T11:57:49.012192Z","shell.execute_reply":"2026-10-03T11:57:49.017354Z"}},"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":"2026-10-03T11:57:49.019406Z","iopub.execute_input":"2026-10-03T11:57:49.019758Z","iopub.status.idle":"2026-10-03T11:57:49.088967Z","shell.execute_reply.started":"2026-10-03T11:57:49.019735Z","shell.execute_reply":"2026-10-03T11:57:49.08791Z"}},"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":"2026-10-03T11:57:49.090096Z","iopub.execute_input":"2026-10-03T11:57:49.09037Z","iopub.status.idle":"2026-10-03T11:57:49.16338Z","shell.execute_reply.started":"2026-10-03T11:57:49.090347Z","shell.execute_reply":"2026-10-03T11:57:49.16235Z"}},"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":"2026-10-03T11:57:49.16466Z","iopub.execute_input":"2026-10-03T11:57:49.165344Z","iopub.status.idle":"2026-10-03T11:57:49.258284Z","shell.execute_reply.started":"2026-10-03T11:57:49.16531Z","shell.execute_reply":"2026-10-03T11:57:49.257361Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:49.259432Z","iopub.execute_input":"2026-10-03T11:57:49.259988Z","iopub.status.idle":"2026-10-03T11:57:49.26581Z","shell.execute_reply.started":"2026-10-03T11:57:49.259961Z","shell.execute_reply":"2026-10-03T11:57:49.265023Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:57:49.266814Z","iopub.execute_input":"2026-10-03T11:57:49.267082Z","iopub.status.idle":"2026-10-03T11:57:50.303307Z","shell.execute_reply.started":"2026-10-03T11:57:49.26706Z","shell.execute_reply":"2026-10-03T11:57:50.302281Z"}},"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":"2026-10-03T11:57:50.305082Z","iopub.execute_input":"2026-10-03T11:57:50.305479Z","iopub.status.idle":"2026-10-03T11:57:50.311759Z","shell.execute_reply.started":"2026-10-03T11:57:50.305442Z","shell.execute_reply":"2026-10-03T11:57:50.310862Z"}},"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":"2026-10-03T11:57:50.312895Z","iopub.execute_input":"2026-10-03T11:57:50.313383Z","iopub.status.idle":"2026-10-03T11:58:01.920436Z","shell.execute_reply.started":"2026-10-03T11:57:50.31336Z","shell.execute_reply":"2026-10-03T11:58:01.919633Z"}},"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       = 'full'   # '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":"2026-10-03T11:58:01.922004Z","iopub.execute_input":"2026-10-03T11:58:01.922358Z","iopub.status.idle":"2026-10-03T11:58:02.472834Z","shell.execute_reply.started":"2026-10-03T11:58:01.922324Z","shell.execute_reply":"2026-10-03T11:58:02.471913Z"}},"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":"2026-10-03T11:58:02.473896Z","iopub.execute_input":"2026-10-03T11:58:02.474177Z","iopub.status.idle":"2026-10-03T11:58:02.481325Z","shell.execute_reply.started":"2026-10-03T11:58:02.474155Z","shell.execute_reply":"2026-10-03T11:58:02.480315Z"}},"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":"2026-10-03T11:58:02.482639Z","iopub.execute_input":"2026-10-03T11:58:02.483044Z","iopub.status.idle":"2026-10-03T11:58:02.499851Z","shell.execute_reply.started":"2026-10-03T11:58:02.483018Z","shell.execute_reply":"2026-10-03T11:58:02.49896Z"}},"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":"2026-10-03T11:58:02.50112Z","iopub.execute_input":"2026-10-03T11:58:02.501428Z","iopub.status.idle":"2026-10-03T11:58:02.507613Z","shell.execute_reply.started":"2026-10-03T11:58:02.5014Z","shell.execute_reply":"2026-10-03T11:58:02.506789Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:02.508759Z","iopub.execute_input":"2026-10-03T11:58:02.509319Z","iopub.status.idle":"2026-10-03T11:58:02.523465Z","shell.execute_reply.started":"2026-10-03T11:58:02.509292Z","shell.execute_reply":"2026-10-03T11:58:02.522734Z"}},"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":"2026-10-03T11:58:02.524785Z","iopub.execute_input":"2026-10-03T11:58:02.52544Z","iopub.status.idle":"2026-10-03T11:58:02.534639Z","shell.execute_reply.started":"2026-10-03T11:58:02.525417Z","shell.execute_reply":"2026-10-03T11:58:02.533839Z"}},"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":"2026-10-03T11:58:02.536835Z","iopub.execute_input":"2026-10-03T11:58:02.537094Z","iopub.status.idle":"2026-10-03T11:58:03.561108Z","shell.execute_reply.started":"2026-10-03T11:58:02.537073Z","shell.execute_reply":"2026-10-03T11:58:03.560101Z"}},"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":"2026-10-03T11:58:03.562962Z","iopub.execute_input":"2026-10-03T11:58:03.563873Z","iopub.status.idle":"2026-10-03T11:58:03.569723Z","shell.execute_reply.started":"2026-10-03T11:58:03.563833Z","shell.execute_reply":"2026-10-03T11:58:03.568784Z"}},"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":"2026-10-03T11:58:03.571009Z","iopub.execute_input":"2026-10-03T11:58:03.571327Z","iopub.status.idle":"2026-10-03T11:58:03.582713Z","shell.execute_reply.started":"2026-10-03T11:58:03.571297Z","shell.execute_reply":"2026-10-03T11:58:03.581798Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:03.58382Z","iopub.execute_input":"2026-10-03T11:58:03.58415Z","iopub.status.idle":"2026-10-03T11:58:03.594107Z","shell.execute_reply.started":"2026-10-03T11:58:03.584129Z","shell.execute_reply":"2026-10-03T11:58:03.59334Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:03.595254Z","iopub.execute_input":"2026-10-03T11:58:03.595596Z","iopub.status.idle":"2026-10-03T11:58:03.605245Z","shell.execute_reply.started":"2026-10-03T11:58:03.595545Z","shell.execute_reply":"2026-10-03T11:58:03.60422Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:03.606522Z","iopub.execute_input":"2026-10-03T11:58:03.606903Z","iopub.status.idle":"2026-10-03T11:58:03.611863Z","shell.execute_reply.started":"2026-10-03T11:58:03.60688Z","shell.execute_reply":"2026-10-03T11:58:03.610702Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:03.612972Z","iopub.execute_input":"2026-10-03T11:58:03.613763Z","iopub.status.idle":"2026-10-03T11:58:03.623143Z","shell.execute_reply.started":"2026-10-03T11:58:03.613731Z","shell.execute_reply":"2026-10-03T11:58:03.622441Z"}},"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":"2026-10-03T11:58:03.624321Z","iopub.execute_input":"2026-10-03T11:58:03.624653Z","iopub.status.idle":"2026-10-03T11:58:03.635179Z","shell.execute_reply.started":"2026-10-03T11:58:03.624624Z","shell.execute_reply":"2026-10-03T11:58:03.634403Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:03.636184Z","iopub.execute_input":"2026-10-03T11:58:03.636491Z","iopub.status.idle":"2026-10-03T11:58:03.649635Z","shell.execute_reply.started":"2026-10-03T11:58:03.636469Z","shell.execute_reply":"2026-10-03T11:58:03.648731Z"}},"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    shuffle=False\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:03.650862Z","iopub.execute_input":"2026-10-03T11:58:03.651199Z","iopub.status.idle":"2026-10-03T11:58:07.941422Z","shell.execute_reply.started":"2026-10-03T11:58:03.651169Z","shell.execute_reply":"2026-10-03T11:58:07.940722Z"}},"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":"2026-10-03T11:58:07.942522Z","iopub.execute_input":"2026-10-03T11:58:07.942951Z","iopub.status.idle":"2026-10-03T11:58:07.948779Z","shell.execute_reply.started":"2026-10-03T11:58:07.942925Z","shell.execute_reply":"2026-10-03T11:58:07.947789Z"}},"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":"2026-10-03T11:58:07.950184Z","iopub.execute_input":"2026-10-03T11:58:07.950769Z","iopub.status.idle":"2026-10-03T11:58:13.730273Z","shell.execute_reply.started":"2026-10-03T11:58:07.950734Z","shell.execute_reply":"2026-10-03T11:58:13.729244Z"}},"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":"2026-10-03T11:58:13.731524Z","iopub.execute_input":"2026-10-03T11:58:13.73193Z","iopub.status.idle":"2026-10-03T11:58:18.845185Z","shell.execute_reply.started":"2026-10-03T11:58:13.731905Z","shell.execute_reply":"2026-10-03T11:58:18.844277Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_exmaple_test(images, indices):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(indices[i]))  # ตั้งค่า title ด้วย index จาก list/array indices\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true,"jupyter":{"source_hidden":true},"execution":{"iopub.status.busy":"2026-10-03T11:58:18.846403Z","iopub.execute_input":"2026-10-03T11:58:18.846872Z","iopub.status.idle":"2026-10-03T11:58:18.852519Z","shell.execute_reply.started":"2026-10-03T11:58:18.846847Z","shell.execute_reply":"2026-10-03T11:58:18.851479Z"}},"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":"2026-10-03T11:58:18.853896Z","iopub.execute_input":"2026-10-03T11:58:18.854395Z","iopub.status.idle":"2026-10-03T11:58:24.630506Z","shell.execute_reply.started":"2026-10-03T11:58:18.85437Z","shell.execute_reply":"2026-10-03T11:58:24.629634Z"}},"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":"2026-10-03T11:58:24.631899Z","iopub.execute_input":"2026-10-03T11:58:24.63222Z","iopub.status.idle":"2026-10-03T11:58:24.637217Z","shell.execute_reply.started":"2026-10-03T11:58:24.632192Z","shell.execute_reply":"2026-10-03T11:58:24.636361Z"}},"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":"2026-10-03T11:58:24.638467Z","iopub.execute_input":"2026-10-03T11:58:24.638833Z","iopub.status.idle":"2026-10-03T11:58:24.653116Z","shell.execute_reply.started":"2026-10-03T11:58:24.638803Z","shell.execute_reply":"2026-10-03T11:58:24.652207Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:24.654247Z","iopub.execute_input":"2026-10-03T11:58:24.654817Z","iopub.status.idle":"2026-10-03T11:58:24.665909Z","shell.execute_reply.started":"2026-10-03T11:58:24.654793Z","shell.execute_reply":"2026-10-03T11:58:24.664991Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import 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, GlobalAveragePooling2D, Dropout \nfrom keras.optimizers import Adam\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# Hyperparameter => changable\nIMAGE_SIZE = 224\nBATCH_SIZE = 64\nEPOCHS = 20\n\n# define cnn model\ndef define_model_vgg16():\n    # 1. โหลด Base Model\n    base_model_vgg = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\n    \n    # 2. ปลดล็อค Base Model ให้เทรนได้ (Fine-Tuning)\n    base_model_vgg.trainable = True\n    \n    # แช่แข็งเลเยอร์ตั้งแต่แรก แต่ \"เปิด\" ไว้เฉพาะ 4 เลเยอร์สุดท้าย (Block 5)\n    for layer in base_model_vgg.layers[:-4]:\n        layer.trainable = False\n        \n    # 3. สร้างชั้น Classifier ใหม่\n    x = GlobalAveragePooling2D()(base_model_vgg.output)\n    x = Dropout(0.5)(x) # กัน Overfitting\n    output_vgg = Dense(1, activation='sigmoid')(x)\n    \n    # 4. ประกอบร่างโมเดล\n    model = Model(inputs=base_model_vgg.inputs, outputs=output_vgg)\n    \n    # 5. Compile ใช้ Learning Rate ต่ำมาก (0.00005) เพื่อไม่ให้น้ำหนักเดิมพัง\n    opt = Adam(learning_rate=0.00005)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\nmodel_vgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:24.6672Z","iopub.execute_input":"2026-10-03T11:58:24.667593Z","iopub.status.idle":"2026-10-03T11:58:25.016394Z","shell.execute_reply.started":"2026-10-03T11:58:24.667543Z","shell.execute_reply":"2026-10-03T11:58:25.015261Z"}},"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":"2026-10-03T11:58:25.017771Z","iopub.execute_input":"2026-10-03T11:58:25.018142Z","iopub.status.idle":"2026-10-03T11:58:27.340147Z","shell.execute_reply.started":"2026-10-03T11:58:25.018116Z","shell.execute_reply":"2026-10-03T11:58:27.339305Z"}},"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":"2026-10-03T11:58:27.341707Z","iopub.execute_input":"2026-10-03T11:58:27.342071Z","iopub.status.idle":"2026-10-03T11:58:27.701415Z","shell.execute_reply.started":"2026-10-03T11:58:27.342037Z","shell.execute_reply":"2026-10-03T11:58:27.698231Z"}},"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":"2026-10-03T11:58:27.705522Z","iopub.execute_input":"2026-10-03T11:58:27.70594Z","iopub.status.idle":"2026-10-03T11:58:27.711328Z","shell.execute_reply.started":"2026-10-03T11:58:27.705913Z","shell.execute_reply":"2026-10-03T11:58:27.710254Z"}},"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":"2026-10-03T11:58:27.712692Z","iopub.execute_input":"2026-10-03T11:58:27.713455Z","iopub.status.idle":"2026-10-03T11:58:27.720604Z","shell.execute_reply.started":"2026-10-03T11:58:27.713431Z","shell.execute_reply":"2026-10-03T11:58:27.71962Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.721785Z","iopub.execute_input":"2026-10-03T11:58:27.722102Z","iopub.status.idle":"2026-10-03T11:58:27.733173Z","shell.execute_reply.started":"2026-10-03T11:58:27.722073Z","shell.execute_reply":"2026-10-03T11:58:27.73229Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use functional API\n#flat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\n#print(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.734499Z","iopub.execute_input":"2026-10-03T11:58:27.734878Z","iopub.status.idle":"2026-10-03T11:58:27.744066Z","shell.execute_reply.started":"2026-10-03T11:58:27.734845Z","shell.execute_reply":"2026-10-03T11:58:27.743111Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#layer1 = Dense(256, activation='relu', kernel_initializer='he_uniform')(flat1)\n#print(layer1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.74501Z","iopub.execute_input":"2026-10-03T11:58:27.745217Z","iopub.status.idle":"2026-10-03T11:58:27.754114Z","shell.execute_reply.started":"2026-10-03T11:58:27.745199Z","shell.execute_reply":"2026-10-03T11:58:27.753355Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#layer2 = Dense(128, activation='relu', kernel_initializer='he_uniform')(layer1)\n#print(layer2.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.755304Z","iopub.execute_input":"2026-10-03T11:58:27.755752Z","iopub.status.idle":"2026-10-03T11:58:27.764934Z","shell.execute_reply.started":"2026-10-03T11:58:27.755721Z","shell.execute_reply":"2026-10-03T11:58:27.763994Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#output1 = Dense(2, activation='softmax')(layer2)\n#print(f\"{output1.shape=}\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.766066Z","iopub.execute_input":"2026-10-03T11:58:27.766345Z","iopub.status.idle":"2026-10-03T11:58:27.775813Z","shell.execute_reply.started":"2026-10-03T11:58:27.766309Z","shell.execute_reply":"2026-10-03T11:58:27.774808Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#output2 = Dense(1, activation='sigmoid')(layer2)\n#print(output2.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.777991Z","iopub.execute_input":"2026-10-03T11:58:27.778448Z","iopub.status.idle":"2026-10-03T11:58:27.782972Z","shell.execute_reply.started":"2026-10-03T11:58:27.778425Z","shell.execute_reply":"2026-10-03T11:58:27.7821Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define new model to be trained\n#model_vgg16 = Model(inputs=model_16_feature_extractor.inputs, outputs=output2)\n# compile model\n#opt = SGD(lr=0.001, momentum=0.9)\n\n#model_vgg16.compile(optimizer=opt,\n #                   loss='binary_crossentropy',\n #                   metrics=['accuracy']\n  #                 )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.783897Z","iopub.execute_input":"2026-10-03T11:58:27.785041Z","iopub.status.idle":"2026-10-03T11:58:27.793858Z","shell.execute_reply.started":"2026-10-03T11:58:27.784993Z","shell.execute_reply":"2026-10-03T11:58:27.793081Z"}},"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":"2026-10-03T11:58:27.795092Z","iopub.execute_input":"2026-10-03T11:58:27.795808Z","iopub.status.idle":"2026-10-03T11:58:27.803408Z","shell.execute_reply.started":"2026-10-03T11:58:27.795785Z","shell.execute_reply":"2026-10-03T11:58:27.802622Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.804481Z","iopub.execute_input":"2026-10-03T11:58:27.805332Z","iopub.status.idle":"2026-10-03T11:58:27.814202Z","shell.execute_reply.started":"2026-10-03T11:58:27.805298Z","shell.execute_reply":"2026-10-03T11:58:27.813233Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.815166Z","iopub.execute_input":"2026-10-03T11:58:27.815733Z","iopub.status.idle":"2026-10-03T11:58:27.825415Z","shell.execute_reply.started":"2026-10-03T11:58:27.815683Z","shell.execute_reply":"2026-10-03T11:58:27.8245Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# del ตัวแปร #ลบตัวแปรออกจากหน่วยความจำ","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.826435Z","iopub.execute_input":"2026-10-03T11:58:27.827455Z","iopub.status.idle":"2026-10-03T11:58:27.834286Z","shell.execute_reply.started":"2026-10-03T11:58:27.827432Z","shell.execute_reply":"2026-10-03T11:58:27.833348Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T11:58:27.83526Z","iopub.execute_input":"2026-10-03T11:58:27.83551Z","iopub.status.idle":"2026-10-03T11:58:27.844507Z","shell.execute_reply.started":"2026-10-03T11:58:27.835489Z","shell.execute_reply":"2026-10-03T11:58:27.843537Z"}},"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        \n        model_vgg16_history = model_vgg16.fit(\n            train_it, \n            steps_per_epoch=len(train_it),\n            validation_data=val_it,\n            validation_steps=len(val_it),\n            epochs=5, \n            verbose=1,\n            callbacks=[PlotLossesKeras()]\n        )\nelse:\n    print(\"WARNING: No GPU detected. Execution will proceed on the CPU, which will be significantly slower.\")\n    # Fallback to standard execution\n    model_vgg16_history = model_vgg16.fit(\n        train_it, \n        steps_per_epoch=len(train_it),\n        validation_data=val_it,\n        validation_steps=len(val_it),\n        epochs=2, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T12:58:16.439547Z","iopub.execute_input":"2026-10-03T12:58:16.440071Z","iopub.status.idle":"2026-10-03T13:07:07.696938Z","shell.execute_reply.started":"2026-10-03T12:58:16.440041Z","shell.execute_reply":"2026-10-03T13:07:07.695847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:08:10.635558Z","iopub.execute_input":"2026-10-03T13:08:10.636187Z","iopub.status.idle":"2026-10-03T13:08:10.941182Z","shell.execute_reply.started":"2026-10-03T13:08:10.636153Z","shell.execute_reply":"2026-10-03T13:08:10.940062Z"}},"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":"2026-10-03T13:08:17.462783Z","iopub.execute_input":"2026-10-03T13:08:17.463281Z","iopub.status.idle":"2026-10-03T13:08:35.434611Z","shell.execute_reply.started":"2026-10-03T13:08:17.463249Z","shell.execute_reply":"2026-10-03T13:08:35.433543Z"}},"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":"2026-10-03T13:08:38.559756Z","iopub.execute_input":"2026-10-03T13:08:38.560471Z","iopub.status.idle":"2026-10-03T13:09:10.497264Z","shell.execute_reply.started":"2026-10-03T13:08:38.56044Z","shell.execute_reply":"2026-10-03T13:09:10.496429Z"}},"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":"2026-10-03T13:09:15.42934Z","iopub.execute_input":"2026-10-03T13:09:15.429803Z","iopub.status.idle":"2026-10-03T13:09:44.574731Z","shell.execute_reply.started":"2026-10-03T13:09:15.429771Z","shell.execute_reply":"2026-10-03T13:09:44.573858Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:11:00.13136Z","iopub.execute_input":"2026-10-03T13:11:00.132011Z","iopub.status.idle":"2026-10-03T13:11:00.140364Z","shell.execute_reply.started":"2026-10-03T13:11:00.131982Z","shell.execute_reply":"2026-10-03T13:11:00.1395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:11:04.407724Z","iopub.execute_input":"2026-10-03T13:11:04.408439Z","iopub.status.idle":"2026-10-03T13:11:04.414014Z","shell.execute_reply.started":"2026-10-03T13:11:04.40841Z","shell.execute_reply":"2026-10-03T13:11:04.41309Z"}},"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":"2026-10-03T13:11:08.708347Z","iopub.execute_input":"2026-10-03T13:11:08.709338Z","iopub.status.idle":"2026-10-03T13:11:08.727482Z","shell.execute_reply.started":"2026-10-03T13:11:08.709302Z","shell.execute_reply":"2026-10-03T13:11:08.726721Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:11:13.895591Z","iopub.execute_input":"2026-10-03T13:11:13.895894Z","iopub.status.idle":"2026-10-03T13:11:13.902902Z","shell.execute_reply.started":"2026-10-03T13:11:13.89587Z","shell.execute_reply":"2026-10-03T13:11:13.901893Z"}},"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":"2026-10-03T13:11:16.746059Z","iopub.execute_input":"2026-10-03T13:11:16.74672Z","iopub.status.idle":"2026-10-03T13:11:17.749987Z","shell.execute_reply.started":"2026-10-03T13:11:16.746688Z","shell.execute_reply":"2026-10-03T13:11:17.749096Z"}},"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":"2026-10-03T13:11:32.176368Z","iopub.execute_input":"2026-10-03T13:11:32.177312Z","iopub.status.idle":"2026-10-03T13:11:40.359254Z","shell.execute_reply.started":"2026-10-03T13:11:32.17727Z","shell.execute_reply":"2026-10-03T13:11:40.35591Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"cell_type":"code","source":"from keras.applications.vgg19 import VGG19\nfrom keras.models import Model\nfrom keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom keras.optimizers import Adam\nfrom livelossplot import PlotLossesKeras\n\n# 1. โหลด Base Model\nbase_model_vgg19 = VGG19(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\n\n# 2. ปลดล็อค Base Model (Fine-Tuning เลเยอร์ท้ายๆ เหมือน VGG16)\nbase_model_vgg19.trainable = True\nfor layer in base_model_vgg19.layers[:-4]:\n    layer.trainable = False\n        \n# 3. สร้าง Classifier\nx = GlobalAveragePooling2D()(base_model_vgg19.output)\nx = Dropout(0.5)(x) \noutput_vgg19 = Dense(1, activation='sigmoid')(x)\n    \nmodel_vgg19 = Model(inputs=base_model_vgg19.inputs, outputs=output_vgg19)\n\n# 4. Compile (ใช้ Learning Rate 0.00005)\nmodel_vgg19.compile(optimizer=Adam(learning_rate=0.00005), loss='binary_crossentropy', metrics=['accuracy'])\n\nprint(\"กำลัง Train VGG19...\")\nhistory_vgg19 = model_vgg19.fit(\n    train_it, steps_per_epoch=len(train_it),\n    validation_data=val_it, validation_steps=len(val_it),\n    epochs=5, callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:46:00.38175Z","iopub.execute_input":"2026-10-03T13:46:00.382436Z","iopub.status.idle":"2026-10-03T13:56:26.207645Z","shell.execute_reply.started":"2026-10-03T13:46:00.382407Z","shell.execute_reply":"2026-10-03T13:56:26.206943Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#model_inceptionv3 = define_model_inceptionv3()\n#print(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T12:55:52.071841Z","iopub.execute_input":"2026-10-03T12:55:52.072125Z","iopub.status.idle":"2026-10-03T12:55:52.076366Z","shell.execute_reply.started":"2026-10-03T12:55:52.0721Z","shell.execute_reply":"2026-10-03T12:55:52.075622Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#import numpy as np\n#from tensorflow.keras import backend as K\n\n#trainable_params = int(np.sum([K.count_params(w) for w in model_inceptionv3.trainable_weights]))\n#print(trainable_params)\n","metadata":{"trusted":true,"scrolled":true,"execution":{"iopub.status.busy":"2026-10-03T12:55:52.078293Z","iopub.execute_input":"2026-10-03T12:55:52.078668Z","iopub.status.idle":"2026-10-03T12:55:52.106626Z","shell.execute_reply.started":"2026-10-03T12:55:52.078632Z","shell.execute_reply":"2026-10-03T12:55:52.105638Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#from tensorflow.keras import backend as K\n\n#for w in model_inceptionv3.trainable_weights:\n #   print(w.name, K.count_params(w))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T12:55:52.107716Z","iopub.execute_input":"2026-10-03T12:55:52.108017Z","iopub.status.idle":"2026-10-03T12:55:52.123343Z","shell.execute_reply.started":"2026-10-03T12:55:52.107994Z","shell.execute_reply":"2026-10-03T12:55:52.122424Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\n#model_inceptionv3.reset_states()\n#history_inceptionv3 = model_inceptionv3.fit(\n #   train_it, \n  #  steps_per_epoch=len(train_it),\n  #  validation_data=val_it,\n# validation_steps=len(val_it),\n #   epochs=3, verbose=1,\n #   callbacks = [PlotLossesKeras()]\n  #  )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T12:55:52.124376Z","iopub.execute_input":"2026-10-03T12:55:52.124705Z","iopub.status.idle":"2026-10-03T12:55:52.139292Z","shell.execute_reply.started":"2026-10-03T12:55:52.124683Z","shell.execute_reply":"2026-10-03T12:55:52.138341Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_images_with_labels(images, labels, train_log, set_label, save=False):\n    \"\"\"\n    Plots a grid of images with their corresponding labels and saves the figure.\n    \n    Args:\n    - images (list or np.array): List of images to be displayed.\n    - labels (np.array): Array of one-hot encoded labels.\n    - train_log (str): The directory or log name to save the plot.\n    - set_label (str): The specific set label (e.g., \"train\", \"validation\", etc.).\n    - config (dict): Configuration dictionary containing image dimensions.\n    \n    Returns:\n    - None: Displays and saves the plot.\n    \"\"\"\n    # Convert one-hot encoded labels to class indices\n    class_indices = labels\n\n    # Create subplots\n    fig, axes = plt.subplots(3, 4, figsize=(14, 10), dpi=120)\n    axes = axes.flatten()\n\n    for img, label_idx, ax in zip(images, class_indices, axes):\n        # Undo any preprocessing (like rescaling for pre-trained models)\n        if np.max(img) == 1:\n            img = img * 255\n\n        # Display the image\n        img_shape = (224, 224, 3)\n        ax.imshow(img.astype(\"uint8\"))\n        # ax.imshow(img)\n\n        # Set the title to the corresponding class label\n        ax.set_title(f\"Label: {label_idx}\", fontsize=18)\n        ax.axis('on')\n\n    # Set the overall title for the figure\n    plot_title = f\"{train_log}-{set_label}\"\n    plt.suptitle(plot_title, fontsize=18)\n\n    # Show the plot\n    plt.show()\n\n    # Save the figure\n    if save:\n        plot_file = os.path.join(train_log, f\"{plot_title}.png\")\n        fig.savefig(plot_file, dpi=120)\n        print(f'Saved {plot_file}')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:23:32.94497Z","iopub.execute_input":"2026-10-03T13:23:32.945642Z","iopub.status.idle":"2026-10-03T13:23:32.952872Z","shell.execute_reply.started":"2026-10-03T13:23:32.9456Z","shell.execute_reply":"2026-10-03T13:23:32.951868Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T12:55:52.158108Z","iopub.execute_input":"2026-10-03T12:55:52.158644Z","iopub.status.idle":"2026-10-03T12:55:52.167936Z","shell.execute_reply.started":"2026-10-03T12:55:52.158594Z","shell.execute_reply":"2026-10-03T12:55:52.16721Z"}},"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":"2026-10-03T12:55:52.168912Z","iopub.execute_input":"2026-10-03T12:55:52.169206Z","iopub.status.idle":"2026-10-03T12:55:52.179152Z","shell.execute_reply.started":"2026-10-03T12:55:52.169184Z","shell.execute_reply":"2026-10-03T12:55:52.178447Z"}},"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":"2026-10-03T12:55:52.180224Z","iopub.execute_input":"2026-10-03T12:55:52.181026Z","iopub.status.idle":"2026-10-03T12:55:52.186398Z","shell.execute_reply.started":"2026-10-03T12:55:52.180992Z","shell.execute_reply":"2026-10-03T12:55:52.185488Z"}},"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":"2026-10-03T13:23:41.086314Z","iopub.execute_input":"2026-10-03T13:23:41.087038Z","iopub.status.idle":"2026-10-03T13:23:41.091886Z","shell.execute_reply.started":"2026-10-03T13:23:41.087007Z","shell.execute_reply":"2026-10-03T13:23:41.090947Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images, labels = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:23:48.106364Z","iopub.execute_input":"2026-10-03T13:23:48.106937Z","iopub.status.idle":"2026-10-03T13:23:48.236021Z","shell.execute_reply.started":"2026-10-03T13:23:48.106895Z","shell.execute_reply":"2026-10-03T13:23:48.234938Z"}},"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":"2026-10-03T13:23:51.25538Z","iopub.execute_input":"2026-10-03T13:23:51.256168Z","iopub.status.idle":"2026-10-03T13:23:51.262088Z","shell.execute_reply.started":"2026-10-03T13:23:51.256131Z","shell.execute_reply":"2026-10-03T13:23:51.261105Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#probs = model_inceptionv3.predict(images_to_predict, verbose=1)\n#probs","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T12:55:52.313204Z","iopub.execute_input":"2026-10-03T12:55:52.313477Z","iopub.status.idle":"2026-10-03T12:55:52.322857Z","shell.execute_reply.started":"2026-10-03T12:55:52.313434Z","shell.execute_reply":"2026-10-03T12:55:52.322044Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"from keras.applications.densenet import DenseNet121\nfrom keras.models import Model\nfrom keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom keras.optimizers import Adam\nfrom livelossplot import PlotLossesKeras\n\nbase_model_dense = DenseNet121(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\nbase_model_dense.trainable = False\n\nx = GlobalAveragePooling2D()(base_model_dense.output)\nx = Dropout(0.4)(x)\noutput_dense = Dense(1, activation='sigmoid')(x)\n    \nmodel_dense = Model(inputs=base_model_dense.inputs, outputs=output_dense)\n\nmodel_dense.compile(optimizer=Adam(learning_rate=0.001), loss='binary_crossentropy', metrics=['accuracy'])\n\nprint(\"กำลัง Train DenseNet121...\")\nhistory_dense = model_dense.fit(\n    train_it, steps_per_epoch=len(train_it),\n    validation_data=val_it, validation_steps=len(val_it),\n    epochs=10, callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:23:57.544327Z","iopub.execute_input":"2026-10-03T13:23:57.544799Z","iopub.status.idle":"2026-10-03T13:34:34.237506Z","shell.execute_reply.started":"2026-10-03T13:23:57.54477Z","shell.execute_reply":"2026-10-03T13:34:34.236645Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\nbest_model = model_vgg16 \n\ntest_it.reset()\ny_true = test_it.classes\n\nprint(\"กำลังประเมินบน Test Set...\")\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobabilities = best_model.predict(test_it, steps=steps, verbose=1).squeeze()\ny_pred = (probabilities > 0.5).astype(int)\n\ntarget_names = list(test_it.class_indices.keys())\nreport = classification_report(y_true, y_pred, target_names=target_names, digits=4)\n\nprint(\"\\n=== Classification Report ===\")\nprint(report)","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2026-10-03T13:57:06.686468Z","iopub.execute_input":"2026-10-03T13:57:06.687243Z","iopub.status.idle":"2026-10-03T13:57:45.675667Z","shell.execute_reply.started":"2026-10-03T13:57:06.687211Z","shell.execute_reply":"2026-10-03T13:57:45.674785Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}