{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":3362,"databundleVersionId":31148,"sourceType":"competition"}],"dockerImageVersionId":30627,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\n# import os\n# for dirname, _, filenames in os.walk('/kaggle/input'):\n#     for filename in filenames:\n#         print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2026-09-17T08:42:09.350750Z","iopub.execute_input":"2026-09-17T08:42:09.351228Z","iopub.status.idle":"2026-09-17T08:42:09.356672Z","shell.execute_reply.started":"2026-09-17T08:42:09.351188Z","shell.execute_reply":"2026-09-17T08:42:09.355651Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:42:12.385123Z","iopub.execute_input":"2026-09-17T08:42:12.386010Z","iopub.status.idle":"2026-09-17T08:42:13.428932Z","shell.execute_reply.started":"2026-09-17T08:42:12.385976Z","shell.execute_reply":"2026-09-17T08:42:13.427812Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:48:06.372509Z","iopub.execute_input":"2026-09-17T07:48:06.373014Z","iopub.status.idle":"2026-09-17T07:48:07.480577Z","shell.execute_reply.started":"2026-09-17T07:48:06.372982Z","shell.execute_reply":"2026-09-17T07:48:07.479290Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nprint(os.listdir(\"../input\"))\n\nimport zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:42:16.520807Z","iopub.execute_input":"2026-09-17T08:42:16.521746Z","iopub.status.idle":"2026-09-17T08:42:26.493652Z","shell.execute_reply.started":"2026-09-17T08:42:16.521702Z","shell.execute_reply":"2026-09-17T08:42:26.492845Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:42:29.476189Z","iopub.execute_input":"2026-09-17T08:42:29.476975Z","iopub.status.idle":"2026-09-17T08:42:30.503604Z","shell.execute_reply.started":"2026-09-17T08:42:29.476940Z","shell.execute_reply":"2026-09-17T08:42:30.502555Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:42:33.075776Z","iopub.execute_input":"2026-09-17T08:42:33.076858Z","iopub.status.idle":"2026-09-17T08:42:34.127457Z","shell.execute_reply.started":"2026-09-17T08:42:33.076820Z","shell.execute_reply":"2026-09-17T08:42:34.126396Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:48:22.363868Z","iopub.execute_input":"2026-09-17T07:48:22.364181Z","iopub.status.idle":"2026-09-17T07:48:23.523829Z","shell.execute_reply.started":"2026-09-17T07:48:22.364153Z","shell.execute_reply":"2026-09-17T07:48:23.522599Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:42:36.236178Z","iopub.execute_input":"2026-09-17T08:42:36.236504Z","iopub.status.idle":"2026-09-17T08:42:37.343657Z","shell.execute_reply.started":"2026-09-17T08:42:36.236478Z","shell.execute_reply":"2026-09-17T08:42:37.342587Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:48:24.719052Z","iopub.execute_input":"2026-09-17T07:48:24.719403Z","iopub.status.idle":"2026-09-17T07:48:24.724196Z","shell.execute_reply.started":"2026-09-17T07:48:24.719372Z","shell.execute_reply":"2026-09-17T07:48:24.723280Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:42:38.715922Z","iopub.execute_input":"2026-09-17T08:42:38.716336Z","iopub.status.idle":"2026-09-17T08:42:39.840418Z","shell.execute_reply.started":"2026-09-17T08:42:38.716305Z","shell.execute_reply":"2026-09-17T08:42:39.839111Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:42:42.516998Z","iopub.execute_input":"2026-09-17T08:42:42.517959Z","iopub.status.idle":"2026-09-17T08:42:43.570009Z","shell.execute_reply.started":"2026-09-17T08:42:42.517922Z","shell.execute_reply":"2026-09-17T08:42:43.569053Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\n# from matplotlib import pyplot as plt\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'dog.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:42:46.300807Z","iopub.execute_input":"2026-09-17T08:42:46.301549Z","iopub.status.idle":"2026-09-17T08:42:47.320687Z","shell.execute_reply.started":"2026-09-17T08:42:46.301512Z","shell.execute_reply":"2026-09-17T08:42:47.319617Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot cat photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\n# define location of dataset\nfolder = 'train/'\n# plot first few images\nfor i in range(9):\n\t# define subplot\n\tpyplot.subplot(330 + 1 + i)\n\t# define filename\n\tfilename = folder + 'cat.' + str(i) + '.jpg'\n\t# load image pixels\n\timage = imread(filename)\n\t# plot raw pixel data\n\tpyplot.imshow(image)\n# show the figure\npyplot.show()","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:42:57.596549Z","iopub.execute_input":"2026-09-17T08:42:57.597279Z","iopub.status.idle":"2026-09-17T08:42:58.609651Z","shell.execute_reply.started":"2026-09-17T08:42:57.597245Z","shell.execute_reply":"2026-09-17T08:42:58.608253Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:43:08.076372Z","iopub.execute_input":"2026-09-17T08:43:08.076712Z","iopub.status.idle":"2026-09-17T08:43:09.130702Z","shell.execute_reply.started":"2026-09-17T08:43:08.076686Z","shell.execute_reply":"2026-09-17T08:43:09.129435Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow\nprint(tensorflow.__version__)\n\nimport keras\nprint(keras.__version__)\n\nimport tensorflow.keras\nprint(tensorflow.__version__)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:48:30.548440Z","iopub.execute_input":"2026-09-17T07:48:30.548927Z","iopub.status.idle":"2026-09-17T07:48:49.516520Z","shell.execute_reply.started":"2026-09-17T07:48:30.548884Z","shell.execute_reply":"2026-09-17T07:48:49.515622Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load dogs vs cats dataset, reshape and save to a new file\nfrom os import listdir\nfrom numpy import asarray\nfrom numpy import save\nfrom keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:14.860007Z","iopub.execute_input":"2026-09-17T08:43:14.860778Z","iopub.status.idle":"2026-09-17T08:43:14.866082Z","shell.execute_reply.started":"2026-09-17T08:43:14.860738Z","shell.execute_reply":"2026-09-17T08:43:14.864904Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n\t# determine class\n\toutput = 0.0\n\tif file.startswith('dog'):\n\t\toutput = 1.0\n\t# load image\n\tphoto = load_img(folder + file, target_size=(200, 200))\n\t# convert to numpy array\n\tphoto = img_to_array(photo)\n\t# store\n\tphotos.append(photo)\n\tlabels.append(output)\n# convert to a numpy arrays\nphotos = asarray(photos)\nlabels = asarray(labels)\nprint(photos.shape, labels.shape)\n# save the reshaped photos\nsave('dogs_vs_cats_photos.npy', photos)\nsave('dogs_vs_cats_labels.npy', labels)","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:15.416611Z","iopub.execute_input":"2024-01-27T03:36:15.417128Z","iopub.status.idle":"2024-01-27T03:36:38.886396Z","shell.execute_reply.started":"2024-01-27T03:36:15.417101Z","shell.execute_reply":"2024-01-27T03:36:38.883149Z"}}},{"cell_type":"markdown","source":"# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')","metadata":{"execution":{"iopub.status.busy":"2024-01-27T03:36:38.88711Z","iopub.status.idle":"2024-01-27T03:36:38.887458Z","shell.execute_reply.started":"2024-01-27T03:36:38.887281Z","shell.execute_reply":"2024-01-27T03:36:38.887296Z"}}},{"cell_type":"code","source":"# organize dataset into a useful structure\nfrom os import makedirs\nfrom os import listdir\nfrom shutil import copyfile\nfrom random import seed\nfrom random import random","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:22.175463Z","iopub.execute_input":"2026-09-17T08:43:22.176366Z","iopub.status.idle":"2026-09-17T08:43:22.180547Z","shell.execute_reply.started":"2026-09-17T08:43:22.176332Z","shell.execute_reply":"2026-09-17T08:43:22.179467Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/'] #test==>validation\nfor subdir in subdirs:\n    # create label subdirectories\n    labeldirs = ['dogs/', 'cats/']\n    for labldir in labeldirs:\n        newdir = dataset_home + subdir + labldir       \n        makedirs(newdir, exist_ok=True)\n        print(newdir)","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:25.222645Z","iopub.execute_input":"2026-09-17T08:43:25.222971Z","iopub.status.idle":"2026-09-17T08:43:25.230195Z","shell.execute_reply.started":"2026-09-17T08:43:25.222946Z","shell.execute_reply":"2026-09-17T08:43:25.229091Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:43:32.274194Z","iopub.execute_input":"2026-09-17T08:43:32.274517Z","iopub.status.idle":"2026-09-17T08:43:33.283988Z","shell.execute_reply.started":"2026-09-17T08:43:32.274490Z","shell.execute_reply":"2026-09-17T08:43:33.282982Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:43:35.033859Z","iopub.execute_input":"2026-09-17T08:43:35.034896Z","iopub.status.idle":"2026-09-17T08:43:36.048894Z","shell.execute_reply.started":"2026-09-17T08:43:35.034858Z","shell.execute_reply":"2026-09-17T08:43:36.047660Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:43:38.266997Z","iopub.execute_input":"2026-09-17T08:43:38.268012Z","iopub.status.idle":"2026-09-17T08:43:39.321941Z","shell.execute_reply.started":"2026-09-17T08:43:38.267972Z","shell.execute_reply":"2026-09-17T08:43:39.320847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# seed random number generator\nseed(1337)\n# define ratio of pictures to use for validation\nval_ratio = 0.25 #changable\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\n\nfor file in listdir(src_directory):\n\tsrc = src_directory + '/' + file\n\tdst_dir = 'train/'\n\tif random() < val_ratio:\n\t\tdst_dir = 'test/'\n\tif file.startswith('cat'):\n\t\tdst = dataset_home + dst_dir + 'cats/'  + file\n\t\tcopyfile(src, dst)\n\telif file.startswith('dog'):\n\t\tdst = dataset_home + dst_dir + 'dogs/'  + file\n\t\tcopyfile(src, dst)","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:41.041525Z","iopub.execute_input":"2026-09-17T08:43:41.042097Z","iopub.status.idle":"2026-09-17T08:43:43.076079Z","shell.execute_reply.started":"2026-09-17T08:43:41.042048Z","shell.execute_reply":"2026-09-17T08:43:43.074912Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:43:44.528156Z","iopub.execute_input":"2026-09-17T08:43:44.529145Z","iopub.status.idle":"2026-09-17T08:43:44.533791Z","shell.execute_reply.started":"2026-09-17T08:43:44.529100Z","shell.execute_reply":"2026-09-17T08:43:44.532692Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:47.426329Z","iopub.execute_input":"2026-09-17T08:43:47.426654Z","iopub.status.idle":"2026-09-17T08:43:49.681763Z","shell.execute_reply.started":"2026-09-17T08:43:47.426627Z","shell.execute_reply":"2026-09-17T08:43:49.680766Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#validation set\n!ls -l dataset_dogs_vs_cats/test/dogs | wc -l\n!ls -l dataset_dogs_vs_cats/test/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:49.708293Z","iopub.execute_input":"2026-09-17T08:43:49.708652Z","iopub.status.idle":"2026-09-17T08:43:51.927261Z","shell.execute_reply.started":"2026-09-17T08:43:49.708624Z","shell.execute_reply":"2026-09-17T08:43:51.926239Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:43:52.852648Z","iopub.execute_input":"2026-09-17T08:43:52.853587Z","iopub.status.idle":"2026-09-17T08:44:03.237708Z","shell.execute_reply.started":"2026-09-17T08:43:52.853549Z","shell.execute_reply":"2026-09-17T08:44:03.236145Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:44:06.737147Z","iopub.execute_input":"2026-09-17T08:44:06.738193Z","iopub.status.idle":"2026-09-17T08:44:06.754262Z","shell.execute_reply.started":"2026-09-17T08:44:06.738154Z","shell.execute_reply":"2026-09-17T08:44:06.753215Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:49:12.340206Z","iopub.execute_input":"2026-09-17T07:49:12.340637Z","iopub.status.idle":"2026-09-17T07:49:12.346496Z","shell.execute_reply.started":"2026-09-17T07:49:12.340597Z","shell.execute_reply":"2026-09-17T07:49:12.345782Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# baseline model for the dogs vs cats dataset\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:13.935981Z","iopub.execute_input":"2026-09-17T08:44:13.937083Z","iopub.status.idle":"2026-09-17T08:44:13.941973Z","shell.execute_reply.started":"2026-09-17T08:44:13.937006Z","shell.execute_reply":"2026-09-17T08:44:13.941073Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\n\tmodel = Sequential()\n\tmodel.add(Conv2D(32, (3, 3), activation='relu',\n                     kernel_initializer='he_uniform',\n                     padding='same',\n                     input_shape=(200, 200, 3))\n             )\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:16.290515Z","iopub.execute_input":"2026-09-17T08:44:16.291539Z","iopub.status.idle":"2026-09-17T08:44:16.299049Z","shell.execute_reply.started":"2026-09-17T08:44:16.291497Z","shell.execute_reply":"2026-09-17T08:44:16.298082Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:19.276850Z","iopub.execute_input":"2026-09-17T08:44:19.277613Z","iopub.status.idle":"2026-09-17T08:44:19.361770Z","shell.execute_reply.started":"2026-09-17T08:44:19.277577Z","shell.execute_reply":"2026-09-17T08:44:19.360847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot diagnostic learning curves\ndef summarize_diagnostics(history):\n    # plot loss\n    pyplot.subplot(211)\n    pyplot.title('Cross Entropy Loss')\n    pyplot.plot(history.history['loss'], color='blue', label='train')\n    pyplot.plot(history.history['val_loss'], color='orange', label='test')\n    # plot accuracy\n    pyplot.subplot(212)\n    pyplot.title('Classification Accuracy')\n    pyplot.plot(history.history['accuracy'], color='blue', label='train')\n    pyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n    pyplot.show()\n    \n    # save plot to file\n    filename = sys.argv[0].split('/')[-1]\n    pyplot.savefig(filename + '_plot.png') \n    pyplot.close()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:22.090578Z","iopub.execute_input":"2026-09-17T08:44:22.090937Z","iopub.status.idle":"2026-09-17T08:44:22.097797Z","shell.execute_reply.started":"2026-09-17T08:44:22.090907Z","shell.execute_reply":"2026-09-17T08:44:22.096786Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(32,\n                 (3, 3),\n                 activation='relu',\n                 input_shape=(200, 200, 3)\n                )\n         )\n\nmodel.add(MaxPooling2D((2, 2)))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128, activation='relu'))\n\nmodel.add(Dense(2, activation='softmax'))\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:24.317520Z","iopub.execute_input":"2026-09-17T08:44:24.318215Z","iopub.status.idle":"2026-09-17T08:44:24.382851Z","shell.execute_reply.started":"2026-09-17T08:44:24.318182Z","shell.execute_reply":"2026-09-17T08:44:24.382057Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:28.974676Z","iopub.execute_input":"2026-09-17T08:44:28.975669Z","iopub.status.idle":"2026-09-17T08:44:29.054496Z","shell.execute_reply.started":"2026-09-17T08:44:28.975630Z","shell.execute_reply":"2026-09-17T08:44:29.053625Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# The Functional API - new cell\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Input, Conv2D, MaxPooling2D, Flatten, Dense\n\n# explicitly define the input tensor topology\nmy_inputs = Input(shape=(200, 200, 3))\n\n# Construct the forward pass of the computational graph\nx1 = Conv2D(32, (3, 3), activation='relu')(my_inputs)\n\nx1 = Conv2D(64, (3, 3), activation='relu')(x1)\n\nx2 = MaxPooling2D((2, 2))(x1)\n\nx3 = Flatten()(x2)\n\nx5 = Dense(256, activation='relu')(x3)\n\nx4 = Dense(128, activation='relu')(x5)\n\n# Define the output tensor with the target objective function representation\nmy_outputs = Dense(2, activation='softmax')(x4)\n\n# Instantiate the formal model architecture\nmodel = Model(inputs=my_inputs, outputs=my_outputs)\n\nprint(model.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:31.735835Z","iopub.execute_input":"2026-09-17T08:44:31.736220Z","iopub.status.idle":"2026-09-17T08:44:31.827154Z","shell.execute_reply.started":"2026-09-17T08:44:31.736189Z","shell.execute_reply":"2026-09-17T08:44:31.826118Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:37.552444Z","iopub.execute_input":"2026-09-17T08:44:37.552769Z","iopub.status.idle":"2026-09-17T08:44:37.559231Z","shell.execute_reply.started":"2026-09-17T08:44:37.552736Z","shell.execute_reply":"2026-09-17T08:44:37.558359Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:49:15.044662Z","iopub.execute_input":"2026-09-17T07:49:15.044893Z","iopub.status.idle":"2026-09-17T07:49:16.170971Z","shell.execute_reply.started":"2026-09-17T07:49:15.044872Z","shell.execute_reply":"2026-09-17T07:49:16.169844Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = 224 #for vgg16\nBATCH_SIZE = 64\nEPOCHS = 30","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:41.690825Z","iopub.execute_input":"2026-09-17T08:44:41.691609Z","iopub.status.idle":"2026-09-17T08:44:41.695836Z","shell.execute_reply.started":"2026-09-17T08:44:41.691572Z","shell.execute_reply":"2026-09-17T08:44:41.694817Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use another dataset\n\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# 1. Instantiate the generator with the validation_split ratio\ndatagen = ImageDataGenerator(\n    rescale=1.0/255.0,\n    horizontal_flip=True,\n    validation_split=0.2  # Defined here at initialization\n)\n\ntrain_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/train'\n\n# 2. Extract the training subset (80% of data)\ntrain_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='training',     # Explicitly request the training partition\n    shuffle=True           # Stochastic sampling is standard for training\n)\n\n# 3. Extract the validation subset (20% of data)\nval_it = datagen.flow_from_directory(\n    train_path,\n    class_mode='binary',\n    batch_size=BATCH_SIZE,\n    target_size=(IMAGE_SIZE, IMAGE_SIZE),\n    subset='validation',   # Explicitly request the validation partition\n    shuffle=False          # Disable shuffle to maintain index alignment for metrics\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:43.685435Z","iopub.execute_input":"2026-09-17T08:44:43.685784Z","iopub.status.idle":"2026-09-17T08:44:59.721227Z","shell.execute_reply.started":"2026-09-17T08:44:43.685757Z","shell.execute_reply":"2026-09-17T08:44:59.720134Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(train_it), len(train_it.classes), train_it.classes[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:08.777452Z","iopub.execute_input":"2026-09-17T08:45:08.777906Z","iopub.status.idle":"2026-09-17T08:45:08.784789Z","shell.execute_reply.started":"2026-09-17T08:45:08.777874Z","shell.execute_reply":"2026-09-17T08:45:08.783683Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"len(val_it), len(val_it.classes), val_it.classes[-10:]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:10.326406Z","iopub.execute_input":"2026-09-17T08:45:10.327311Z","iopub.status.idle":"2026-09-17T08:45:10.333859Z","shell.execute_reply.started":"2026-09-17T08:45:10.327275Z","shell.execute_reply":"2026-09-17T08:45:10.332643Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\n# model_1.reset_states()\n# history_1 = model_1.fit(\n#     train_it,\n#     steps_per_epoch=len(train_it),\n#     validation_data=val_it,\n#     validation_steps=len(val_it),\n#     epochs=EPOCHS,\n#     verbose=2,\n#     callbacks = [PlotLossesKeras()]\n#     )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:11.359310Z","iopub.execute_input":"2026-09-17T07:50:11.359722Z","iopub.status.idle":"2026-09-17T07:50:11.369644Z","shell.execute_reply.started":"2026-09-17T07:50:11.359684Z","shell.execute_reply":"2026-09-17T07:50:11.368505Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:11.371174Z","iopub.execute_input":"2026-09-17T07:50:11.371652Z","iopub.status.idle":"2026-09-17T07:50:11.379577Z","shell.execute_reply.started":"2026-09-17T07:50:11.371595Z","shell.execute_reply":"2026-09-17T07:50:11.378349Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n# _, acc = model_1.evaluate(val_it, steps=len(val_it), verbose=1)\n# print('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:11.380849Z","iopub.execute_input":"2026-09-17T07:50:11.381215Z","iopub.status.idle":"2026-09-17T07:50:11.390359Z","shell.execute_reply.started":"2026-09-17T07:50:11.381180Z","shell.execute_reply":"2026-09-17T07:50:11.389588Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"## Create test datagenerator from 308-456 Dogs vs Cats ","metadata":{}},{"cell_type":"code","source":"ls /kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:13.784603Z","iopub.execute_input":"2026-09-17T08:45:13.785332Z","iopub.status.idle":"2026-09-17T08:45:14.805658Z","shell.execute_reply.started":"2026-09-17T08:45:13.785297Z","shell.execute_reply":"2026-09-17T08:45:14.804608Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\nimport pandas as pd\nfrom glob import glob\n\n# Define the image folder path\ntest_path = '/kaggle/input/datasets/kasikrit/308-456-dogs-vs-cats-dataset/dataset_dogs_vs_cats/test'\n\nprint(test_path)\n# # List all .jpg files in the directory (adjust the pattern if needed)\n# image_files = glob(os.path.join(image_folder, '*.jpg'))\n\n# # Check if images were found\n# if not image_files:\n#     print(\"No images found. Please verify the directory and file extensions.\")\n    \n# # Create a DataFrame with the file paths\n# test_df = pd.DataFrame({'filename': image_files})\n\n# If your use-case doesn't require labels (for example, during testing), you can leave out the label column.\n# Otherwise, if you need a dummy label, you can add one:\n# df['class'] = 'dummy_label'\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:16.520997Z","iopub.execute_input":"2026-09-17T08:45:16.521913Z","iopub.status.idle":"2026-09-17T08:45:16.527748Z","shell.execute_reply.started":"2026-09-17T08:45:16.521877Z","shell.execute_reply":"2026-09-17T08:45:16.526618Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.columns","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:12.568893Z","iopub.execute_input":"2026-09-17T07:50:12.569269Z","iopub.status.idle":"2026-09-17T07:50:12.583801Z","shell.execute_reply.started":"2026-09-17T07:50:12.569231Z","shell.execute_reply":"2026-09-17T07:50:12.582918Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:12.585293Z","iopub.execute_input":"2026-09-17T07:50:12.585728Z","iopub.status.idle":"2026-09-17T07:50:12.593625Z","shell.execute_reply.started":"2026-09-17T07:50:12.585697Z","shell.execute_reply":"2026-09-17T07:50:12.592720Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:12.594918Z","iopub.execute_input":"2026-09-17T07:50:12.595253Z","iopub.status.idle":"2026-09-17T07:50:12.605846Z","shell.execute_reply.started":"2026-09-17T07:50:12.595211Z","shell.execute_reply":"2026-09-17T07:50:12.604902Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:12.607658Z","iopub.execute_input":"2026-09-17T07:50:12.607988Z","iopub.status.idle":"2026-09-17T07:50:12.616217Z","shell.execute_reply.started":"2026-09-17T07:50:12.607960Z","shell.execute_reply":"2026-09-17T07:50:12.615398Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:12.617865Z","iopub.execute_input":"2026-09-17T07:50:12.618315Z","iopub.status.idle":"2026-09-17T07:50:12.630165Z","shell.execute_reply.started":"2026-09-17T07:50:12.618286Z","shell.execute_reply":"2026-09-17T07:50:12.629231Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # Create test data generator\n# from tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# # Initialize your ImageDataGenerator (modify parameters as needed)\n# datagen_test = ImageDataGenerator(rescale=1./255,\n#                                  vertical_flip=True)\n\n# # Create the data generator using the DataFrame\n# test_it = datagen_test.flow_from_dataframe(\n#     dataframe=test_df,\n#     x_col='filename',\n#     y_col=None,            # No labels for testing, so set to None\n#     target_size=IMAGE_SIZE,\n#     batch_size=BATCH_SIZE,\n#     class_mode=None,       # Since there are no labels\n#     # shuffle=True,         # Usually testing data should not be shuffled\n#     shuffle=False,\n# )\n\n# type(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:12.631648Z","iopub.execute_input":"2026-09-17T07:50:12.632090Z","iopub.status.idle":"2026-09-17T07:50:12.645360Z","shell.execute_reply.started":"2026-09-17T07:50:12.632027Z","shell.execute_reply":"2026-09-17T07:50:12.644395Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:26.006806Z","iopub.execute_input":"2026-09-17T08:45:26.007475Z","iopub.status.idle":"2026-09-17T08:45:26.014087Z","shell.execute_reply.started":"2026-09-17T08:45:26.007440Z","shell.execute_reply":"2026-09-17T08:45:26.013100Z"}},"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":"2026-09-17T08:45:28.356115Z","iopub.execute_input":"2026-09-17T08:45:28.356517Z","iopub.status.idle":"2026-09-17T08:45:33.373916Z","shell.execute_reply.started":"2026-09-17T08:45:28.356486Z","shell.execute_reply":"2026-09-17T08:45:33.373189Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_exmaple(images, labels):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(labels[i]))  # Fixed: set_title instead of title\n            # ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n            ax.axis(\"on\")\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:36.247606Z","iopub.execute_input":"2026-09-17T08:45:36.247921Z","iopub.status.idle":"2026-09-17T08:45:36.254221Z","shell.execute_reply.started":"2026-09-17T08:45:36.247896Z","shell.execute_reply":"2026-09-17T08:45:36.253197Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_images, train_labels = train_it.__next__()\nprint(train_images.shape, len(train_labels))\nplot_exmaple(train_images, train_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:28.179504Z","iopub.execute_input":"2026-09-17T07:50:28.179848Z","iopub.status.idle":"2026-09-17T07:50:39.359203Z","shell.execute_reply.started":"2026-09-17T07:50:28.179823Z","shell.execute_reply":"2026-09-17T07:50:39.357510Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_images, val_labels = val_it.__next__()\nval_images.shape\nplot_exmaple(val_images, val_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:41.879884Z","iopub.execute_input":"2026-09-17T08:45:41.880361Z","iopub.status.idle":"2026-09-17T08:45:51.468361Z","shell.execute_reply.started":"2026-09-17T08:45:41.880327Z","shell.execute_reply":"2026-09-17T08:45:51.467328Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def plot_exmaple_test(images, indices):\n    # Assuming images shape is (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a 1D array for easy iteration\n\n    for i, ax in enumerate(axes):\n        if i < len(images):\n            ax.imshow(images[i])\n            ax.set_title(str(indices[i]))  # ตั้งค่า title ด้วย index จาก list/array indices\n            ax.axis(\"off\")  # Turn off axis ticks/labels for clarity\n        else:\n            ax.axis(\"off\")  # Hide unused subplots if images < 64\n\n    plt.tight_layout()\n    plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:50:50.523634Z","iopub.execute_input":"2026-09-17T07:50:50.524339Z","iopub.status.idle":"2026-09-17T07:50:50.532469Z","shell.execute_reply.started":"2026-09-17T07:50:50.524299Z","shell.execute_reply":"2026-09-17T07:50:50.531248Z"},"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images, test_labels = test_it.__next__()  # หรือ next(test_it)\nprint(f\"{test_images.shape=}, {test_labels.shape}\")\n\n# สร้าง list เลขดัชนีตามจำนวนภาพที่มี\nindices = list(range(len(test_images)))\n\nplot_exmaple(test_images, test_labels)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:46:23.404378Z","iopub.execute_input":"2026-09-17T08:46:23.405257Z","iopub.status.idle":"2026-09-17T08:46:33.097474Z","shell.execute_reply.started":"2026-09-17T08:46:23.405221Z","shell.execute_reply":"2026-09-17T08:46:33.095791Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# import numpy as np\n\n\n# # 1. สุ่ม index มา 10 ตัวจากชุดข้อมูล\n# sample_indices = np.random.choice(len(test_images), size=10, replace=False)\n# sample_images = test_images[sample_indices]\n\n# # 2. Predict \n# predictions = model_1.predict(sample_images)\n# predicted_classes = np.argmax(predictions, axis=1)  # ดึง class ที่ได้คะแนนสูงสุด\n\n# # 3. แสดงผล 10 ภาพ (ปรับเป็น grid 2x5)\n# fig, axes = plt.subplots(2, 5, figsize=(15, 6))\n# axes = axes.flatten()\n\n# for i, ax in enumerate(axes):\n#     ax.imshow(sample_images[i])\n#     # แสดง Index เดิม และ Class ที่ทายได้\n#     ax.set_title(f\"Idx: {sample_indices[i]}\\nPred: {predicted_classes[i]}\")\n#     ax.axis(\"off\")\n\n# plt.tight_layout()\n# plt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:51:01.679202Z","iopub.execute_input":"2026-09-17T07:51:01.679698Z","iopub.status.idle":"2026-09-17T07:51:01.686040Z","shell.execute_reply.started":"2026-09-17T07:51:01.679658Z","shell.execute_reply":"2026-09-17T07:51:01.684875Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 2026-09-13\n# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T07:51:01.687467Z","iopub.execute_input":"2026-09-17T07:51:01.688085Z","iopub.status.idle":"2026-09-17T07:51:01.706138Z","shell.execute_reply.started":"2026-09-17T07:51:01.688047Z","shell.execute_reply":"2026-09-17T07:51:01.703855Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:03.786410Z","iopub.execute_input":"2026-09-17T08:47:03.787363Z","iopub.status.idle":"2026-09-17T08:47:03.793950Z","shell.execute_reply.started":"2026-09-17T08:47:03.787323Z","shell.execute_reply":"2026-09-17T08:47:03.792792Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#Create transfer learning model for VGG16\nimport sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.vgg16 import VGG16\nfrom keras.models import Model\nfrom keras.layers import Dense\nfrom keras.layers import Flatten\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\n\n# Hyperparameter => changable\nIMAGE_SIZE = 224\nBATCH_SIE = 64\nEPOCHS = 20\n\n# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))\n\t# mark loaded layers as not trainable\n\tfor layer in model.layers:\n\t\tlayer.trainable = False\n\t# add new classifier layers\n\tflat1 = Flatten()(model.layers[-1].output)\n\tclass1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n\toutput = Dense(1, activation='sigmoid')(class1)\n\t# define new model\n\tmodel = Model(inputs=model.inputs, outputs=output)\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model\n\nvgg16 = define_model_vgg16()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:05.602279Z","iopub.execute_input":"2026-09-17T08:47:05.603237Z","iopub.status.idle":"2026-09-17T08:47:08.094528Z","shell.execute_reply.started":"2026-09-17T08:47:05.603185Z","shell.execute_reply":"2026-09-17T08:47:08.093791Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_vgg16_top = VGG16(include_top=True,\n                        input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n                       )\nmodel_vgg16_top.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:18.638635Z","iopub.execute_input":"2026-09-17T08:47:18.639268Z","iopub.status.idle":"2026-09-17T08:47:34.539073Z","shell.execute_reply.started":"2026-09-17T08:47:18.639235Z","shell.execute_reply":"2026-09-17T08:47:34.537616Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Load model\nmodel_16_feature_extractor = VGG16(include_top=False,\n                                   input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3)\n                                  )\nmodel_16_feature_extractor.summary() #feature extractor as a backbone","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:38.352558Z","iopub.execute_input":"2026-09-17T08:47:38.353387Z","iopub.status.idle":"2026-09-17T08:47:38.698949Z","shell.execute_reply.started":"2026-09-17T08:47:38.353353Z","shell.execute_reply":"2026-09-17T08:47:38.696538Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n\t\tprint(index, layer.trainable, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:42.485187Z","iopub.execute_input":"2026-09-17T08:47:42.485672Z","iopub.status.idle":"2026-09-17T08:47:42.492305Z","shell.execute_reply.started":"2026-09-17T08:47:42.485640Z","shell.execute_reply":"2026-09-17T08:47:42.491173Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model_16_feature_extractor.layers):\n    if index <= 15:\n        layer.trainable = False\n\nfor index, layer in enumerate(model_16_feature_extractor.layers):\n    print(index, layer.name, layer.trainable)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:45.772526Z","iopub.execute_input":"2026-09-17T08:47:45.773485Z","iopub.status.idle":"2026-09-17T08:47:45.780468Z","shell.execute_reply.started":"2026-09-17T08:47:45.773449Z","shell.execute_reply":"2026-09-17T08:47:45.778845Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-17T08:12:08.438Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Use functional API\nflat1 = Flatten()(model_16_feature_extractor.layers[-1].output)\nprint(flat1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:48.580442Z","iopub.execute_input":"2026-09-17T08:47:48.580773Z","iopub.status.idle":"2026-09-17T08:47:48.590820Z","shell.execute_reply.started":"2026-09-17T08:47:48.580748Z","shell.execute_reply":"2026-09-17T08:47:48.589687Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\nprint(class1.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:50.801165Z","iopub.execute_input":"2026-09-17T08:47:50.801940Z","iopub.status.idle":"2026-09-17T08:47:50.819003Z","shell.execute_reply.started":"2026-09-17T08:47:50.801903Z","shell.execute_reply":"2026-09-17T08:47:50.818278Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:52.951852Z","iopub.execute_input":"2026-09-17T08:47:52.952625Z","iopub.status.idle":"2026-09-17T08:47:52.969483Z","shell.execute_reply.started":"2026-09-17T08:47:52.952589Z","shell.execute_reply":"2026-09-17T08:47:52.968489Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define new model to be trained\nmodel_vgg16 = Model(inputs=model_16_feature_extractor.inputs, outputs=output)\n# compile model\nopt = SGD(lr=0.001, momentum=0.9)\n\nmodel_vgg16.compile(optimizer=opt,\n                    loss='binary_crossentropy',\n                    metrics=['accuracy']\n                   )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:54.537626Z","iopub.execute_input":"2026-09-17T08:47:54.538560Z","iopub.status.idle":"2026-09-17T08:47:54.555278Z","shell.execute_reply.started":"2026-09-17T08:47:54.538525Z","shell.execute_reply":"2026-09-17T08:47:54.554539Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:58.641631Z","iopub.execute_input":"2026-09-17T08:47:58.642265Z","iopub.status.idle":"2026-09-17T08:47:58.693159Z","shell.execute_reply.started":"2026-09-17T08:47:58.642231Z","shell.execute_reply":"2026-09-17T08:47:58.692155Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:48:01.072939Z","iopub.execute_input":"2026-09-17T08:48:01.073778Z","iopub.status.idle":"2026-09-17T08:48:01.079622Z","shell.execute_reply.started":"2026-09-17T08:48:01.073741Z","shell.execute_reply":"2026-09-17T08:48:01.078658Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# model_vgg16 = define_model_vgg16()\n# print(model_vgg16)","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-17T08:12:08.438Z"}},"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=1, \n            verbose=1,\n            callbacks=[PlotLossesKeras()]\n        )\nelse:\n    print(\"WARNING: No GPU detected. Execution will proceed on the CPU, which will be significantly slower.\")\n    # Fallback to standard execution\n    model_vgg16_history = model_vgg16.fit(\n        train_it, \n        steps_per_epoch=len(train_it),\n        validation_data=val_it,\n        validation_steps=len(val_it),\n        epochs=1, \n        verbose=1,\n        callbacks=[PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:48:04.364412Z","iopub.execute_input":"2026-09-17T08:48:04.364727Z","iopub.status.idle":"2026-09-17T08:50:12.879595Z","shell.execute_reply.started":"2026-09-17T08:48:04.364704Z","shell.execute_reply":"2026-09-17T08:50:12.878541Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:50:26.125201Z","iopub.execute_input":"2026-09-17T08:50:26.125937Z","iopub.status.idle":"2026-09-17T08:50:26.414699Z","shell.execute_reply.started":"2026-09-17T08:50:26.125902Z","shell.execute_reply":"2026-09-17T08:50:26.413903Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_vgg16.evaluate(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:50:31.976120Z","iopub.execute_input":"2026-09-17T08:50:31.976599Z","iopub.status.idle":"2026-09-17T08:50:49.926601Z","shell.execute_reply.started":"2026-09-17T08:50:31.976551Z","shell.execute_reply":"2026-09-17T08:50:49.925744Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model for the test set\n_, test_acc = model_vgg16.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (test_acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:50:52.240441Z","iopub.execute_input":"2026-09-17T08:50:52.241287Z","iopub.status.idle":"2026-09-17T08:51:30.746378Z","shell.execute_reply.started":"2026-09-17T08:50:52.241252Z","shell.execute_reply":"2026-09-17T08:51:30.745549Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom sklearn.metrics import classification_report\n\n# 1. Reset the generator state to ensure alignment from index 0\ntest_it.reset()\n\n# 2. Extract the ordered ground truth labels from the generator\ny_true = test_it.classes\nprint(y_true.shape)\n\n# 3. Execute the forward pass over the entire test dataset\n# Calculate exact steps to prevent infinite looping or partial evaluation\nsteps = np.ceil(test_it.samples / test_it.batch_size)\nprobabilities = model_vgg16.predict(test_it, steps=steps, verbose=1).squeeze()\nprint(probabilities.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:51:33.158273Z","iopub.execute_input":"2026-09-17T08:51:33.159125Z","iopub.status.idle":"2026-09-17T08:52:02.276759Z","shell.execute_reply.started":"2026-09-17T08:51:33.159087Z","shell.execute_reply":"2026-09-17T08:52:02.275833Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:52:15.265653Z","iopub.execute_input":"2026-09-17T08:52:15.266570Z","iopub.status.idle":"2026-09-17T08:52:15.273586Z","shell.execute_reply.started":"2026-09-17T08:52:15.266532Z","shell.execute_reply":"2026-09-17T08:52:15.272578Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:52:16.785184Z","iopub.execute_input":"2026-09-17T08:52:16.785828Z","iopub.status.idle":"2026-09-17T08:52:16.791847Z","shell.execute_reply.started":"2026-09-17T08:52:16.785795Z","shell.execute_reply":"2026-09-17T08:52:16.790731Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 4. Discretize continuous logistic probabilities into binary class predictions\ny_pred = (probabilities > 0.5).astype(int)\nprint(y_pred.shape)\n\n# 5. Extract dynamic class labels mapping (e.g., {'cats': 0, 'dogs': 1})\n# This ensures the report correctly maps index 0 and 1 to your string labels\ntarget_names = list(test_it.class_indices.keys())\n\n# 6. Compute and output the classification report\nreport = classification_report(y_true, y_pred, target_names=target_names)\nprint(report)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:52:18.295924Z","iopub.execute_input":"2026-09-17T08:52:18.296695Z","iopub.status.idle":"2026-09-17T08:52:18.317246Z","shell.execute_reply.started":"2026-09-17T08:52:18.296660Z","shell.execute_reply":"2026-09-17T08:52:18.316437Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:52:19.894898Z","iopub.execute_input":"2026-09-17T08:52:19.895247Z","iopub.status.idle":"2026-09-17T08:52:19.901598Z","shell.execute_reply.started":"2026-09-17T08:52:19.895218Z","shell.execute_reply":"2026-09-17T08:52:19.900604Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Predict\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# 1. Aggregate sufficient samples from the iterator\nimages_list = []\nlabels_list = []\n\n# Fetch 2 batches (2 * 64 = 128 samples) to ensure we have pool > 100\nfor _ in range(2):\n    batch_images, batch_labels = next(test_it)\n    images_list.append(batch_images)\n    labels_list.append(batch_labels)\n\n# Concatenate into a single tensor\nall_images = np.concatenate(images_list, axis=0)\nall_labels = np.concatenate(labels_list, axis=0)\n\n# 2. Stochastically sample 100 unique indices\nnp.random.seed(42) # For reproducibility\nrandom_indices = np.random.choice(all_images.shape[0], size=100, replace=False)\n\nsample_images = all_images[random_indices]\nsample_labels = all_labels[random_indices]\n\n# 3. Execute the forward pass\n# Squeeze is used to convert shape (100, 1) to (100,)\nprobabilities = model_vgg16.predict(sample_images).squeeze()\n\n# 4. Thresholding (Assuming standard mapping: 0 = Cat, 1 = Dog)\npredictions = (probabilities > 0.5).astype(int)\nclass_mapping = {0: 'Cat', 1: 'Dog'}\n\nprint(\"Done.\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:52:21.235911Z","iopub.execute_input":"2026-09-17T08:52:21.236259Z","iopub.status.idle":"2026-09-17T08:52:28.867354Z","shell.execute_reply.started":"2026-09-17T08:52:21.236232Z","shell.execute_reply":"2026-09-17T08:52:28.866052Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Initialize a 10x10 matrix visualization\nfig, axes = plt.subplots(10, 10, figsize=(20, 22))\naxes = axes.flatten()\n\nfor i in range(100):\n    ax = axes[i]\n    \n    # Isolate image tensor. \n    # NOTE: If your VGG16 preprocessor applies mean-centering (caffe style) \n    # instead of standard [0,1] scaling, you must reverse it here for correct plt.imshow() rendering.\n    # We assume standard [0, 1] or [0, 255] spatial tensors below.\n    img = sample_images[i]\n    if img.max() > 1.0 or img.min() < 0:\n        # Simple normalization for display purposes\n        img = (img - img.min()) / (img.max() - img.min())\n        \n    ax.imshow(img)\n    ax.axis('off')\n    \n    # Extract structural labels\n    gt_class = class_mapping[int(sample_labels[i])]\n    pred_class = class_mapping[predictions[i]]\n    prob = probabilities[i]\n    \n    # Apply conditional color coding (Green for True Positives/Negatives, Red for False Positives/Negatives)\n    text_color = 'darkgreen' if gt_class == pred_class else 'darkred'\n    \n    title_str = f\"GT: {gt_class}\\nPred: {pred_class}\\nProb: {prob:.3f}\"\n    ax.set_title(title_str, color=text_color, fontsize=9, pad=4)\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:52:32.775796Z","iopub.execute_input":"2026-09-17T08:52:32.776532Z","iopub.status.idle":"2026-09-17T08:52:41.442714Z","shell.execute_reply.started":"2026-09-17T08:52:32.776486Z","shell.execute_reply":"2026-09-17T08:52:41.441589Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-17T08:12:08.438Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:08:59.194089Z","iopub.execute_input":"2026-09-17T10:08:59.194898Z","iopub.status.idle":"2026-09-17T10:08:59.201495Z","shell.execute_reply.started":"2026-09-17T10:08:59.194860Z","shell.execute_reply":"2026-09-17T10:08:59.200559Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# How to Classify Photos of Dogs and Cats (Transfer Learning)","metadata":{}},{"cell_type":"code","source":"from tensorflow.keras.applications import InceptionV3\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, GlobalAveragePooling2D\nfrom tensorflow.keras.optimizers import SGD\n\ndef define_model_inceptionv3():\n    base_model = InceptionV3(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), weights='imagenet')\n    \n    for layer in base_model.layers:\n        layer.trainable = False\n        \n    x = GlobalAveragePooling2D()(base_model.output)\n    x = Dense(128, activation='relu', kernel_initializer='he_uniform')(x)\n    output = Dense(1, activation='sigmoid')(x)\n    \n    model = Model(inputs=base_model.inputs, outputs=output)\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:16:16.561580Z","iopub.execute_input":"2026-09-17T10:16:16.562242Z","iopub.status.idle":"2026-09-17T10:16:16.568124Z","shell.execute_reply.started":"2026-09-17T10:16:16.562207Z","shell.execute_reply":"2026-09-17T10:16:16.567279Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:22:18.165667Z","iopub.execute_input":"2026-09-17T10:22:18.166429Z","iopub.status.idle":"2026-09-17T10:22:20.449948Z","shell.execute_reply.started":"2026-09-17T10:22:18.166395Z","shell.execute_reply":"2026-09-17T10:22:20.449097Z"}},"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,"execution":{"iopub.status.busy":"2026-09-17T10:23:25.445534Z","iopub.execute_input":"2026-09-17T10:23:25.446136Z","iopub.status.idle":"2026-09-17T10:23:25.453554Z","shell.execute_reply.started":"2026-09-17T10:23:25.446096Z","shell.execute_reply":"2026-09-17T10:23:25.452549Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_inceptionv3 = define_model_inceptionv3()\n\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, \n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:59:07.307540Z","iopub.execute_input":"2026-09-17T09:59:07.308331Z","iopub.status.idle":"2026-09-17T10:02:33.657804Z","shell.execute_reply.started":"2026-09-17T09:59:07.308295Z","shell.execute_reply":"2026-09-17T10:02:33.657090Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import classification_report\n\nprint(\"=== Classification Report: Model 1 (InceptionV3) ===\")\nval_it.reset()\npred_1 = model_inceptionv3.predict(val_it, steps=len(val_it))\nprint(classification_report(val_it.classes, (pred_1 > 0.5).astype(int), target_names=['Cat', 'Dog']))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:04:48.194869Z","iopub.execute_input":"2026-09-17T10:04:48.195570Z","iopub.status.idle":"2026-09-17T10:05:02.549260Z","shell.execute_reply.started":"2026-09-17T10:04:48.195532Z","shell.execute_reply":"2026-09-17T10:05:02.548186Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:30:56.886119Z","iopub.execute_input":"2026-09-17T09:30:56.887143Z","iopub.status.idle":"2026-09-17T09:30:56.893824Z","shell.execute_reply.started":"2026-09-17T09:30:56.887097Z","shell.execute_reply":"2026-09-17T09:30:56.892972Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications import ResNet50V2\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, GlobalAveragePooling2D\nfrom tensorflow.keras.optimizers import SGD\n\ndef define_model_resnet50v2():\n    base_model = ResNet50V2(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), weights='imagenet')\n    \n    for layer in base_model.layers:\n        layer.trainable = False\n        \n    x = GlobalAveragePooling2D()(base_model.output)\n    x = Dense(128, activation='relu', kernel_initializer='he_uniform')(x)\n    output = Dense(1, activation='sigmoid')(x)\n    \n    model = Model(inputs=base_model.inputs, outputs=output)\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:16:51.239534Z","iopub.execute_input":"2026-09-17T10:16:51.240002Z","iopub.status.idle":"2026-09-17T10:16:51.246176Z","shell.execute_reply.started":"2026-09-17T10:16:51.239969Z","shell.execute_reply":"2026-09-17T10:16:51.245268Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_resnet50v2 = define_model_resnet50v2()\n\nhistory_resnet50v2 = model_resnet50v2.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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:31:17.407801Z","iopub.execute_input":"2026-09-17T09:31:17.408465Z","iopub.status.idle":"2026-09-17T09:37:04.883951Z","shell.execute_reply.started":"2026-09-17T09:31:17.408427Z","shell.execute_reply":"2026-09-17T09:37:04.882803Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import classification_report\n\nprint(\"=== Classification Report: Model 2 (ResNet50V2) ===\")\nval_it.reset()\npred_2 = model_resnet50v2.predict(val_it, steps=len(val_it))\nprint(classification_report(val_it.classes, (pred_2 > 0.5).astype(int), target_names=['Cat', 'Dog']))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:17:09.409380Z","iopub.execute_input":"2026-09-17T10:17:09.410535Z","iopub.status.idle":"2026-09-17T10:17:23.556483Z","shell.execute_reply.started":"2026-09-17T10:17:09.410495Z","shell.execute_reply":"2026-09-17T10:17:23.555608Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications import MobileNetV2\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, GlobalAveragePooling2D\nfrom tensorflow.keras.optimizers import SGD\n\ndef define_model_mobilenetv2():\n    base_model = MobileNetV2(include_top=False, input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3), weights='imagenet')\n    \n    for layer in base_model.layers:\n        layer.trainable = False\n        \n    x = GlobalAveragePooling2D()(base_model.output)\n    x = Dense(128, activation='relu', kernel_initializer='he_uniform')(x)\n    output = Dense(1, activation='sigmoid')(x)\n    \n    model = Model(inputs=base_model.inputs, outputs=output)\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    \n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:17:40.005401Z","iopub.execute_input":"2026-09-17T10:17:40.005709Z","iopub.status.idle":"2026-09-17T10:17:40.011816Z","shell.execute_reply.started":"2026-09-17T10:17:40.005685Z","shell.execute_reply":"2026-09-17T10:17:40.010887Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_mobilenetv2 = define_model_mobilenetv2()\n\nhistory_mobilenetv2 = model_mobilenetv2.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)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:45:24.319811Z","iopub.execute_input":"2026-09-17T09:45:24.320135Z","iopub.status.idle":"2026-09-17T09:50:50.166971Z","shell.execute_reply.started":"2026-09-17T09:45:24.320109Z","shell.execute_reply":"2026-09-17T09:50:50.165785Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from sklearn.metrics import classification_report\n\nprint(\"=== Classification Report: Model 3 (MobileNetV2) ===\")\nval_it.reset()\npred_3 = model_mobilenetv2.predict(val_it, steps=len(val_it))\nprint(classification_report(val_it.classes, (pred_3 > 0.5).astype(int), target_names=['Cat', 'Dog']))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T10:24:22.715458Z","iopub.execute_input":"2026-09-17T10:24:22.716548Z","iopub.status.idle":"2026-09-17T10:24:35.981986Z","shell.execute_reply.started":"2026-09-17T10:24:22.716511Z","shell.execute_reply":"2026-09-17T10:24:35.981089Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras import backend as K\n\nfor w in model_inceptionv3.trainable_weights:\n    print(w.name, K.count_params(w))\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:02:56.309760Z","iopub.execute_input":"2026-09-17T09:02:56.310645Z","iopub.status.idle":"2026-09-17T09:02:56.316441Z","shell.execute_reply.started":"2026-09-17T09:02:56.310610Z","shell.execute_reply":"2026-09-17T09:02:56.315356Z"}},"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":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\ndef plot_images_with_labels(images, labels, train_log, set_label, save=False):\n    \"\"\"\n    Plots a grid of images with their corresponding labels and saves the figure.\n    \n    Args:\n    - images (list or np.array): List of images to be displayed.\n    - labels (np.array): Array of one-hot encoded labels.\n    - train_log (str): The directory or log name to save the plot.\n    - set_label (str): The specific set label (e.g., \"train\", \"validation\", etc.).\n    - config (dict): Configuration dictionary containing image dimensions.\n    \n    Returns:\n    - None: Displays and saves the plot.\n    \"\"\"\n    # Convert one-hot encoded labels to class indices\n    class_indices = labels\n\n    # Create subplots\n    fig, axes = plt.subplots(3, 4, figsize=(14, 10), dpi=120)\n    axes = axes.flatten()\n\n    for img, label_idx, ax in zip(images, class_indices, axes):\n        # Undo any preprocessing (like rescaling for pre-trained models)\n        if np.max(img) == 1:\n            img = img * 255\n\n        # Display the image\n        img_shape = (224, 224, 3)\n        ax.imshow(img.astype(\"uint8\"))\n        # ax.imshow(img)\n\n        # Set the title to the corresponding class label\n        ax.set_title(f\"Label: {label_idx}\", fontsize=18)\n        ax.axis('on')\n\n    # Set the overall title for the figure\n    plot_title = f\"{train_log}-{set_label}\"\n    plt.suptitle(plot_title, fontsize=18)\n\n    # Show the plot\n    plt.show()\n\n    # Save the figure\n    if save:\n        plot_file = os.path.join(train_log, f\"{plot_title}.png\")\n        fig.savefig(plot_file, dpi=120)\n        print(f'Saved {plot_file}')\n","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:23:55.925421Z","iopub.execute_input":"2026-09-17T09:23:55.925934Z","iopub.status.idle":"2026-09-17T09:23:55.934489Z","shell.execute_reply.started":"2026-09-17T09:23:55.925901Z","shell.execute_reply":"2026-09-17T09:23:55.933355Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-17T08:12:08.438Z"}},"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":{"execution_failed":"2026-09-17T08:12:08.438Z"}},"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":{"execution_failed":"2026-09-17T08:12:08.438Z"}},"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":{"execution_failed":"2026-09-17T08:12:08.439Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-17T08:12:08.439Z"}},"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":{"execution_failed":"2026-09-17T08:12:08.439Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true,"execution":{"execution_failed":"2026-09-17T08:12:08.439Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}