{"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":"2026-09-17T08:44:26.36514Z","iopub.execute_input":"2026-09-17T08:44:26.365494Z","iopub.status.idle":"2026-09-17T08:44:26.700946Z","shell.execute_reply.started":"2026-09-17T08:44:26.365467Z","shell.execute_reply":"2026-09-17T08:44:26.699906Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:37.214057Z","iopub.execute_input":"2026-09-17T08:44:37.214364Z","iopub.status.idle":"2026-09-17T08:44:38.217338Z","shell.execute_reply.started":"2026-09-17T08:44:37.214341Z","shell.execute_reply":"2026-09-17T08:44:38.215847Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!uname --all","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:39.356782Z","iopub.execute_input":"2026-09-17T08:44:39.357753Z","iopub.status.idle":"2026-09-17T08:44:40.339938Z","shell.execute_reply.started":"2026-09-17T08:44:39.357712Z","shell.execute_reply":"2026-09-17T08:44:40.339038Z"}},"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":"2026-09-17T08:44:41.287848Z","iopub.execute_input":"2026-09-17T08:44:41.288208Z","iopub.status.idle":"2026-09-17T08:44:52.458031Z","shell.execute_reply.started":"2026-09-17T08:44:41.288178Z","shell.execute_reply":"2026-09-17T08:44:52.457181Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:54.832763Z","iopub.execute_input":"2026-09-17T08:44:54.8336Z","iopub.status.idle":"2026-09-17T08:44:55.834298Z","shell.execute_reply.started":"2026-09-17T08:44:54.833529Z","shell.execute_reply":"2026-09-17T08:44:55.833305Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:44:57.926687Z","iopub.execute_input":"2026-09-17T08:44:57.927295Z","iopub.status.idle":"2026-09-17T08:44:58.938006Z","shell.execute_reply.started":"2026-09-17T08:44:57.927252Z","shell.execute_reply":"2026-09-17T08:44:58.936789Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:01.741831Z","iopub.execute_input":"2026-09-17T08:45:01.742805Z","iopub.status.idle":"2026-09-17T08:45:02.787021Z","shell.execute_reply.started":"2026-09-17T08:45:01.742767Z","shell.execute_reply":"2026-09-17T08:45:02.78593Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:04.239203Z","iopub.execute_input":"2026-09-17T08:45:04.239602Z","iopub.status.idle":"2026-09-17T08:45:05.309757Z","shell.execute_reply.started":"2026-09-17T08:45:04.239527Z","shell.execute_reply":"2026-09-17T08:45:05.308471Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-16T20:28:42.551043Z","iopub.execute_input":"2026-09-16T20:28:42.551414Z","iopub.status.idle":"2026-09-16T20:28:42.555083Z","shell.execute_reply.started":"2026-09-16T20:28:42.551385Z","shell.execute_reply":"2026-09-16T20:28:42.554181Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U train | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:06.168704Z","iopub.execute_input":"2026-09-17T08:45:06.169517Z","iopub.status.idle":"2026-09-17T08:45:07.215261Z","shell.execute_reply.started":"2026-09-17T08:45:06.169481Z","shell.execute_reply":"2026-09-17T08:45:07.214032Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -U test1 | head -n 10","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:09.0773Z","iopub.execute_input":"2026-09-17T08:45:09.07821Z","iopub.status.idle":"2026-09-17T08:45:10.103833Z","shell.execute_reply.started":"2026-09-17T08:45:09.078175Z","shell.execute_reply":"2026-09-17T08:45:10.102915Z"}},"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":"2026-09-17T08:45:12.102797Z","iopub.execute_input":"2026-09-17T08:45:12.103673Z","iopub.status.idle":"2026-09-17T08:45:13.225254Z","shell.execute_reply.started":"2026-09-17T08:45:12.103638Z","shell.execute_reply":"2026-09-17T08:45:13.224276Z"},"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":"2026-09-17T08:45:17.322328Z","iopub.execute_input":"2026-09-17T08:45:17.322645Z","iopub.status.idle":"2026-09-17T08:45:18.378795Z","shell.execute_reply.started":"2026-09-17T08:45:17.322619Z","shell.execute_reply":"2026-09-17T08:45:18.377898Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:45:46.15847Z","iopub.execute_input":"2026-09-17T08:45:46.159208Z","iopub.status.idle":"2026-09-17T08:45:47.133922Z","shell.execute_reply.started":"2026-09-17T08:45:46.159175Z","shell.execute_reply":"2026-09-17T08:45:47.132983Z"}},"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":"2026-09-17T08:45:48.578269Z","iopub.execute_input":"2026-09-17T08:45:48.579273Z","iopub.status.idle":"2026-09-17T08:46:00.922533Z","shell.execute_reply.started":"2026-09-17T08:45:48.579235Z","shell.execute_reply":"2026-09-17T08:46:00.921611Z"}},"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":"2026-09-17T08:46:28.193854Z","iopub.execute_input":"2026-09-17T08:46:28.195187Z","iopub.status.idle":"2026-09-17T08:46:28.200195Z","shell.execute_reply.started":"2026-09-17T08:46:28.195155Z","shell.execute_reply":"2026-09-17T08:46:28.198893Z"},"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":"2026-09-17T08:46:31.529009Z","iopub.execute_input":"2026-09-17T08:46:31.529894Z","iopub.status.idle":"2026-09-17T08:46:31.534127Z","shell.execute_reply.started":"2026-09-17T08:46:31.529865Z","shell.execute_reply":"2026-09-17T08:46:31.533181Z"},"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":"2026-09-17T08:46:32.964315Z","iopub.execute_input":"2026-09-17T08:46:32.965261Z","iopub.status.idle":"2026-09-17T08:46:32.97152Z","shell.execute_reply.started":"2026-09-17T08:46:32.965226Z","shell.execute_reply":"2026-09-17T08:46:32.970587Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:46:34.070934Z","iopub.execute_input":"2026-09-17T08:46:34.071659Z","iopub.status.idle":"2026-09-17T08:46:35.074084Z","shell.execute_reply.started":"2026-09-17T08:46:34.071625Z","shell.execute_reply":"2026-09-17T08:46:35.073092Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:46:36.02523Z","iopub.execute_input":"2026-09-17T08:46:36.025616Z","iopub.status.idle":"2026-09-17T08:46:37.022005Z","shell.execute_reply.started":"2026-09-17T08:46:36.025544Z","shell.execute_reply":"2026-09-17T08:46:37.020958Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test #validation","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:46:38.085687Z","iopub.execute_input":"2026-09-17T08:46:38.08619Z","iopub.status.idle":"2026-09-17T08:46:39.078407Z","shell.execute_reply.started":"2026-09-17T08:46:38.086159Z","shell.execute_reply":"2026-09-17T08:46:39.077422Z"}},"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":"2026-09-17T08:46:40.255368Z","iopub.execute_input":"2026-09-17T08:46:40.255902Z","iopub.status.idle":"2026-09-17T08:46:42.231509Z","shell.execute_reply.started":"2026-09-17T08:46:40.255868Z","shell.execute_reply":"2026-09-17T08:46:42.230418Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:46:45.662366Z","iopub.execute_input":"2026-09-17T08:46:45.663295Z","iopub.status.idle":"2026-09-17T08:46:45.668296Z","shell.execute_reply.started":"2026-09-17T08:46:45.663258Z","shell.execute_reply":"2026-09-17T08:46:45.666998Z"}},"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":"2026-09-17T08:46:46.836188Z","iopub.execute_input":"2026-09-17T08:46:46.836903Z","iopub.status.idle":"2026-09-17T08:46:49.033456Z","shell.execute_reply.started":"2026-09-17T08:46:46.836868Z","shell.execute_reply":"2026-09-17T08:46:49.031908Z"},"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":"2026-09-17T08:46:50.059613Z","iopub.execute_input":"2026-09-17T08:46:50.059974Z","iopub.status.idle":"2026-09-17T08:46:52.09509Z","shell.execute_reply.started":"2026-09-17T08:46:50.059948Z","shell.execute_reply":"2026-09-17T08:46:52.094107Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:46:52.09683Z","iopub.execute_input":"2026-09-17T08:46:52.097138Z","iopub.status.idle":"2026-09-17T08:47:03.403212Z","shell.execute_reply.started":"2026-09-17T08:46:52.097114Z","shell.execute_reply":"2026-09-17T08:47:03.402125Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-09-17T08:47:03.405152Z","iopub.execute_input":"2026-09-17T08:47:03.40554Z","iopub.status.idle":"2026-09-17T08:47:03.421719Z","shell.execute_reply.started":"2026-09-17T08:47:03.405515Z","shell.execute_reply":"2026-09-17T08:47:03.420627Z"},"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":"2026-09-12T13:57:08.5293Z","iopub.execute_input":"2026-09-12T13:57:08.529605Z","iopub.status.idle":"2026-09-12T13:57:08.533803Z","shell.execute_reply.started":"2026-09-12T13:57:08.529582Z","shell.execute_reply":"2026-09-12T13:57:08.532719Z"}},"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":"2026-09-17T08:47:53.114779Z","iopub.execute_input":"2026-09-17T08:47:53.115483Z","iopub.status.idle":"2026-09-17T08:47:53.120895Z","shell.execute_reply.started":"2026-09-17T08:47:53.115451Z","shell.execute_reply":"2026-09-17T08:47:53.119795Z"}},"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":"2026-09-17T08:47:56.00027Z","iopub.execute_input":"2026-09-17T08:47:56.001024Z","iopub.status.idle":"2026-09-17T08:47:56.007121Z","shell.execute_reply.started":"2026-09-17T08:47:56.000987Z","shell.execute_reply":"2026-09-17T08:47:56.006134Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:47:58.84463Z","iopub.execute_input":"2026-09-17T08:47:58.845353Z","iopub.status.idle":"2026-09-17T08:48:00.760911Z","shell.execute_reply.started":"2026-09-17T08:47:58.845323Z","shell.execute_reply":"2026-09-17T08:48:00.760137Z"}},"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":"2026-09-17T08:48:03.336663Z","iopub.execute_input":"2026-09-17T08:48:03.337411Z","iopub.status.idle":"2026-09-17T08:48:03.343602Z","shell.execute_reply.started":"2026-09-17T08:48:03.337374Z","shell.execute_reply":"2026-09-17T08:48:03.342609Z"}},"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":"2026-09-17T08:48:17.250961Z","iopub.execute_input":"2026-09-17T08:48:17.251296Z","iopub.status.idle":"2026-09-17T08:48:17.323902Z","shell.execute_reply.started":"2026-09-17T08:48:17.251274Z","shell.execute_reply":"2026-09-17T08:48:17.323205Z"}},"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":"2026-09-17T08:48:20.971204Z","iopub.execute_input":"2026-09-17T08:48:20.97206Z","iopub.status.idle":"2026-09-17T08:48:21.052731Z","shell.execute_reply.started":"2026-09-17T08:48:20.972027Z","shell.execute_reply":"2026-09-17T08:48:21.051013Z"}},"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":"2026-09-17T08:48:25.616629Z","iopub.execute_input":"2026-09-17T08:48:25.617596Z","iopub.status.idle":"2026-09-17T08:48:25.711679Z","shell.execute_reply.started":"2026-09-17T08:48:25.617526Z","shell.execute_reply":"2026-09-17T08:48:25.708743Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\ntype(datagen)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:48:28.123073Z","iopub.execute_input":"2026-09-17T08:48:28.123418Z","iopub.status.idle":"2026-09-17T08:48:28.130398Z","shell.execute_reply.started":"2026-09-17T08:48:28.123393Z","shell.execute_reply":"2026-09-17T08:48:28.129608Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls dataset_dogs_vs_cats/train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:48:31.116547Z","iopub.execute_input":"2026-09-17T08:48:31.117231Z","iopub.status.idle":"2026-09-17T08:48:32.135121Z","shell.execute_reply.started":"2026-09-17T08:48:31.117195Z","shell.execute_reply":"2026-09-17T08:48:32.134179Z"}},"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":"2026-09-17T08:48:34.207008Z","iopub.execute_input":"2026-09-17T08:48:34.208068Z","iopub.status.idle":"2026-09-17T08:48:34.213527Z","shell.execute_reply.started":"2026-09-17T08:48:34.208018Z","shell.execute_reply":"2026-09-17T08:48:34.212509Z"}},"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":"2026-09-17T08:48:36.085475Z","iopub.execute_input":"2026-09-17T08:48:36.08583Z","iopub.status.idle":"2026-09-17T08:49:08.540165Z","shell.execute_reply.started":"2026-09-17T08:48:36.085804Z","shell.execute_reply":"2026-09-17T08:49:08.539089Z"}},"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":"2026-09-17T08:49:43.598604Z","iopub.execute_input":"2026-09-17T08:49:43.599491Z","iopub.status.idle":"2026-09-17T08:49:43.606632Z","shell.execute_reply.started":"2026-09-17T08:49:43.599457Z","shell.execute_reply":"2026-09-17T08:49:43.605623Z"}},"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":"2026-09-17T08:49:44.881598Z","iopub.execute_input":"2026-09-17T08:49:44.882597Z","iopub.status.idle":"2026-09-17T08:49:44.888259Z","shell.execute_reply.started":"2026-09-17T08:49:44.882524Z","shell.execute_reply":"2026-09-17T08:49:44.887291Z"}},"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":"2026-09-12T13:57:12.39435Z","iopub.status.idle":"2026-09-12T13:57:12.394628Z","shell.execute_reply.started":"2026-09-12T13:57:12.39449Z","shell.execute_reply":"2026-09-12T13:57:12.394505Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\n# summarize_diagnostics(history_1)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T13:57:12.396236Z","iopub.status.idle":"2026-09-12T13:57:12.396611Z","shell.execute_reply.started":"2026-09-12T13:57:12.396387Z","shell.execute_reply":"2026-09-12T13:57:12.396436Z"}},"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":"2026-09-12T13:57:12.39813Z","iopub.status.idle":"2026-09-12T13:57:12.398412Z","shell.execute_reply.started":"2026-09-12T13:57:12.398277Z","shell.execute_reply":"2026-09-12T13:57:12.398291Z"}},"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":"2026-09-17T08:49:49.159955Z","iopub.execute_input":"2026-09-17T08:49:49.160715Z","iopub.status.idle":"2026-09-17T08:49:50.175222Z","shell.execute_reply.started":"2026-09-17T08:49:49.160684Z","shell.execute_reply":"2026-09-17T08:49:50.174294Z"}},"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":"2026-09-17T08:49:53.16911Z","iopub.execute_input":"2026-09-17T08:49:53.169682Z","iopub.status.idle":"2026-09-17T08:49:53.176192Z","shell.execute_reply.started":"2026-09-17T08:49:53.169644Z","shell.execute_reply":"2026-09-17T08:49:53.175079Z"}},"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":"2026-09-12T13:57:12.402795Z","iopub.status.idle":"2026-09-12T13:57:12.403106Z","shell.execute_reply.started":"2026-09-12T13:57:12.402977Z","shell.execute_reply":"2026-09-12T13:57:12.40299Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T13:57:12.405239Z","iopub.status.idle":"2026-09-12T13:57:12.405523Z","shell.execute_reply.started":"2026-09-12T13:57:12.405388Z","shell.execute_reply":"2026-09-12T13:57:12.405402Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T13:57:12.406334Z","iopub.status.idle":"2026-09-12T13:57:12.406639Z","shell.execute_reply.started":"2026-09-12T13:57:12.406502Z","shell.execute_reply":"2026-09-12T13:57:12.406516Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.loc[1]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T13:57:12.4086Z","iopub.status.idle":"2026-09-12T13:57:12.408982Z","shell.execute_reply.started":"2026-09-12T13:57:12.408783Z","shell.execute_reply":"2026-09-12T13:57:12.408799Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# test_df.sample(5)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T13:57:12.410365Z","iopub.status.idle":"2026-09-12T13:57:12.410772Z","shell.execute_reply.started":"2026-09-12T13:57:12.410565Z","shell.execute_reply":"2026-09-12T13:57:12.410585Z"}},"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":"2026-09-12T13:57:12.412045Z","iopub.status.idle":"2026-09-12T13:57:12.412473Z","shell.execute_reply.started":"2026-09-12T13:57:12.412241Z","shell.execute_reply":"2026-09-12T13:57:12.41227Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE, BATCH_SIZE","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-13T03:20:26.206176Z","iopub.execute_input":"2026-09-13T03:20:26.207243Z","iopub.status.idle":"2026-09-13T03:20:26.213388Z","shell.execute_reply.started":"2026-09-13T03:20:26.207187Z","shell.execute_reply":"2026-09-13T03:20:26.212387Z"}},"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":"2026-09-17T08:49:56.348785Z","iopub.execute_input":"2026-09-17T08:49:56.349097Z","iopub.status.idle":"2026-09-17T08:50:07.078796Z","shell.execute_reply.started":"2026-09-17T08:49:56.349076Z","shell.execute_reply":"2026-09-17T08:50:07.078054Z"}},"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":"2026-09-17T08:50:09.156316Z","iopub.execute_input":"2026-09-17T08:50:09.156996Z","iopub.status.idle":"2026-09-17T08:50:09.16301Z","shell.execute_reply.started":"2026-09-17T08:50:09.156958Z","shell.execute_reply":"2026-09-17T08:50:09.162048Z"}},"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":"2026-09-17T08:50:11.876076Z","iopub.execute_input":"2026-09-17T08:50:11.876382Z","iopub.status.idle":"2026-09-17T08:50:21.311972Z","shell.execute_reply.started":"2026-09-17T08:50:11.876359Z","shell.execute_reply":"2026-09-17T08:50:21.310489Z"}},"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":"2026-09-17T08:50:49.374522Z","iopub.execute_input":"2026-09-17T08:50:49.375341Z","iopub.status.idle":"2026-09-17T08:50:59.108299Z","shell.execute_reply.started":"2026-09-17T08:50:49.375308Z","shell.execute_reply":"2026-09-17T08:50:59.106665Z"}},"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":"2026-09-12T13:57:12.422659Z","iopub.status.idle":"2026-09-12T13:57:12.423035Z","shell.execute_reply.started":"2026-09-12T13:57:12.422877Z","shell.execute_reply":"2026-09-12T13:57:12.422893Z"},"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":"2026-09-17T08:51:36.252167Z","iopub.execute_input":"2026-09-17T08:51:36.252944Z","iopub.status.idle":"2026-09-17T08:51:45.588215Z","shell.execute_reply.started":"2026-09-17T08:51:36.252914Z","shell.execute_reply":"2026-09-17T08:51:45.585949Z"}},"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":"2026-09-12T13:57:12.429269Z","iopub.status.idle":"2026-09-12T13:57:12.429599Z","shell.execute_reply.started":"2026-09-12T13:57:12.429448Z","shell.execute_reply":"2026-09-12T13:57:12.429462Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T13:57:12.430613Z","iopub.status.idle":"2026-09-12T13:57:12.430981Z","shell.execute_reply.started":"2026-09-12T13:57:12.430785Z","shell.execute_reply":"2026-09-12T13:57:12.430799Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 2026-09-13\n# Transfer Learning","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:07:33.624129Z","iopub.execute_input":"2026-09-12T14:07:33.625179Z","iopub.status.idle":"2026-09-12T14:07:33.628731Z","shell.execute_reply.started":"2026-09-12T14:07:33.625146Z","shell.execute_reply":"2026-09-12T14:07:33.627721Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it), id(test_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:53:01.437367Z","iopub.execute_input":"2026-09-17T08:53:01.438072Z","iopub.status.idle":"2026-09-17T08:53:01.444754Z","shell.execute_reply.started":"2026-09-17T08:53:01.438037Z","shell.execute_reply":"2026-09-17T08:53:01.443716Z"}},"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":"2026-09-17T08:53:02.766544Z","iopub.execute_input":"2026-09-17T08:53:02.767341Z","iopub.status.idle":"2026-09-17T08:53:03.570364Z","shell.execute_reply.started":"2026-09-17T08:53:02.767311Z","shell.execute_reply":"2026-09-17T08:53:03.569466Z"}},"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":"2026-09-17T08:54:49.194072Z","iopub.execute_input":"2026-09-17T08:54:49.194498Z","iopub.status.idle":"2026-09-17T08:54:54.412867Z","shell.execute_reply.started":"2026-09-17T08:54:49.194468Z","shell.execute_reply":"2026-09-17T08:54:54.411864Z"}},"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":"2026-09-17T08:55:06.842378Z","iopub.execute_input":"2026-09-17T08:55:06.843041Z","iopub.status.idle":"2026-09-17T08:55:07.204014Z","shell.execute_reply.started":"2026-09-17T08:55:06.843008Z","shell.execute_reply":"2026-09-17T08:55:07.203107Z"}},"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":"2026-09-17T08:55:10.49374Z","iopub.execute_input":"2026-09-17T08:55:10.494756Z","iopub.status.idle":"2026-09-17T08:55:10.50103Z","shell.execute_reply.started":"2026-09-17T08:55:10.494711Z","shell.execute_reply":"2026-09-17T08:55:10.499938Z"}},"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":"2026-09-17T08:55:11.582448Z","iopub.execute_input":"2026-09-17T08:55:11.583476Z","iopub.status.idle":"2026-09-17T08:55:11.589528Z","shell.execute_reply.started":"2026-09-17T08:55:11.58344Z","shell.execute_reply":"2026-09-17T08:55:11.588619Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_16_feature_extractor.layers[-1].output","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:55:13.023037Z","iopub.execute_input":"2026-09-17T08:55:13.024557Z","iopub.status.idle":"2026-09-17T08:55:13.03191Z","shell.execute_reply.started":"2026-09-17T08:55:13.024514Z","shell.execute_reply":"2026-09-17T08:55:13.03049Z"}},"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":"2026-09-17T08:55:15.825344Z","iopub.execute_input":"2026-09-17T08:55:15.826342Z","iopub.status.idle":"2026-09-17T08:55:15.836957Z","shell.execute_reply.started":"2026-09-17T08:55:15.826309Z","shell.execute_reply":"2026-09-17T08:55:15.835853Z"}},"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":"2026-09-17T08:55:17.015621Z","iopub.execute_input":"2026-09-17T08:55:17.016661Z","iopub.status.idle":"2026-09-17T08:55:17.033652Z","shell.execute_reply.started":"2026-09-17T08:55:17.016627Z","shell.execute_reply":"2026-09-17T08:55:17.032422Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"output = Dense(1, activation='sigmoid')(class1)\nprint(output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:55:18.044478Z","iopub.execute_input":"2026-09-17T08:55:18.045552Z","iopub.status.idle":"2026-09-17T08:55:18.062134Z","shell.execute_reply.started":"2026-09-17T08:55:18.045493Z","shell.execute_reply":"2026-09-17T08:55:18.061135Z"}},"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":"2026-09-17T08:55:21.852405Z","iopub.execute_input":"2026-09-17T08:55:21.853116Z","iopub.status.idle":"2026-09-17T08:55:21.869937Z","shell.execute_reply.started":"2026-09-17T08:55:21.853084Z","shell.execute_reply":"2026-09-17T08:55:21.869032Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(model_vgg16.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:55:23.927781Z","iopub.execute_input":"2026-09-17T08:55:23.928304Z","iopub.status.idle":"2026-09-17T08:55:23.977686Z","shell.execute_reply.started":"2026-09-17T08:55:23.928277Z","shell.execute_reply":"2026-09-17T08:55:23.974593Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(train_it), id(val_it)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T08:55:26.82158Z","iopub.execute_input":"2026-09-17T08:55:26.821924Z","iopub.status.idle":"2026-09-17T08:55:26.828232Z","shell.execute_reply.started":"2026-09-17T08:55:26.821899Z","shell.execute_reply":"2026-09-17T08:55:26.827205Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":" model_vgg16 = define_model_vgg16()\n print(model_vgg16)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:17:00.028972Z","iopub.execute_input":"2026-09-17T09:17:00.029762Z","iopub.status.idle":"2026-09-17T09:17:00.371309Z","shell.execute_reply.started":"2026-09-17T09:17:00.02973Z","shell.execute_reply":"2026-09-17T09:17:00.370366Z"}},"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":"2026-09-17T09:17:01.774952Z","iopub.execute_input":"2026-09-17T09:17:01.775767Z","iopub.status.idle":"2026-09-17T09:18:34.761391Z","shell.execute_reply.started":"2026-09-17T09:17:01.775735Z","shell.execute_reply":"2026-09-17T09:18:34.760353Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(model_vgg16_history)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:02:45.882694Z","iopub.execute_input":"2026-09-17T09:02:45.883507Z","iopub.status.idle":"2026-09-17T09:02:46.193364Z","shell.execute_reply.started":"2026-09-17T09:02:45.883472Z","shell.execute_reply":"2026-09-17T09:02:46.192514Z"}},"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":"2026-09-17T09:02:48.581864Z","iopub.execute_input":"2026-09-17T09:02:48.582172Z","iopub.status.idle":"2026-09-17T09:03:08.710466Z","shell.execute_reply.started":"2026-09-17T09:02:48.582151Z","shell.execute_reply":"2026-09-17T09:03:08.7095Z"}},"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":"2026-09-17T09:03:36.110523Z","iopub.execute_input":"2026-09-17T09:03:36.111359Z","iopub.status.idle":"2026-09-17T09:04:48.305294Z","shell.execute_reply.started":"2026-09-17T09:03:36.111328Z","shell.execute_reply":"2026-09-17T09:04:48.304218Z"}},"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":"2026-09-17T09:05:18.857137Z","iopub.execute_input":"2026-09-17T09:05:18.858114Z","iopub.status.idle":"2026-09-17T09:05:51.133831Z","shell.execute_reply.started":"2026-09-17T09:05:18.858077Z","shell.execute_reply":"2026-09-17T09:05:51.132631Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probabilities[:20]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:09:11.866746Z","iopub.execute_input":"2026-09-17T09:09:11.867449Z","iopub.status.idle":"2026-09-17T09:09:11.874344Z","shell.execute_reply.started":"2026-09-17T09:09:11.867418Z","shell.execute_reply":"2026-09-17T09:09:11.873384Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"(probabilities[0] > 0.5).astype(int)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:09:12.861791Z","iopub.execute_input":"2026-09-17T09:09:12.862907Z","iopub.status.idle":"2026-09-17T09:09:12.869022Z","shell.execute_reply.started":"2026-09-17T09:09:12.862875Z","shell.execute_reply":"2026-09-17T09:09:12.86812Z"}},"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":"2026-09-17T09:09:14.94782Z","iopub.execute_input":"2026-09-17T09:09:14.948141Z","iopub.status.idle":"2026-09-17T09:09:14.973997Z","shell.execute_reply.started":"2026-09-17T09:09:14.948116Z","shell.execute_reply":"2026-09-17T09:09:14.973112Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"y_true[:10], y_pred[:10]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:09:16.62605Z","iopub.execute_input":"2026-09-17T09:09:16.626652Z","iopub.status.idle":"2026-09-17T09:09:16.633347Z","shell.execute_reply.started":"2026-09-17T09:09:16.626621Z","shell.execute_reply":"2026-09-17T09:09:16.632326Z"}},"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":"2026-09-17T09:09:17.751216Z","iopub.execute_input":"2026-09-17T09:09:17.752143Z","iopub.status.idle":"2026-09-17T09:09:25.758982Z","shell.execute_reply.started":"2026-09-17T09:09:17.752111Z","shell.execute_reply":"2026-09-17T09:09:25.758191Z"}},"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":"2026-09-17T09:14:31.138001Z","iopub.execute_input":"2026-09-17T09:14:31.138941Z","iopub.status.idle":"2026-09-17T09:14:39.18918Z","shell.execute_reply.started":"2026-09-17T09:14:31.138911Z","shell.execute_reply":"2026-09-17T09:14:39.187667Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"stop","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.980765Z","iopub.status.idle":"2026-09-12T14:09:21.981271Z","shell.execute_reply.started":"2026-09-12T14:09:21.981026Z","shell.execute_reply":"2026-09-12T14:09:21.98105Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# InceptionV3","metadata":{}},{"cell_type":"code","source":"from keras.applications.inception_v3 import InceptionV3\n\ndef define_model_inceptionv3():\n    # load model\n    model = InceptionV3(include_top=False, input_shape=(299, 299, 3))\n    # mark loaded layers as not trainable\n    for layer in model.layers:\n        layer.trainable = False\n        # layer.trainable = True #try to test\n    \n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(1024, activation='relu', kernel_initializer='he_uniform')(flat1)\n    class2 = Dense(512, activation='relu', kernel_initializer='he_uniform')(class1)\n    class3 = Dense(256, activation='relu', kernel_initializer='he_uniform')(class2)\n    class4 = Dense(128, activation='relu', kernel_initializer='he_uniform')(class3)\n    # output = Dense(1, activation='sigmoid')(flat1)\n    output = Dense(2, activation='softmax')(class4)\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    # compile model\n    opt = SGD(lr=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:14:55.167262Z","iopub.execute_input":"2026-09-17T09:14:55.168347Z","iopub.status.idle":"2026-09-17T09:14:55.175219Z","shell.execute_reply.started":"2026-09-17T09:14:55.168308Z","shell.execute_reply":"2026-09-17T09:14:55.174056Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"execution":{"iopub.status.busy":"2026-09-17T09:15:00.081014Z","iopub.execute_input":"2026-09-17T09:15:00.081755Z","iopub.status.idle":"2026-09-17T09:15:02.968835Z","shell.execute_reply.started":"2026-09-17T09:15:00.081723Z","shell.execute_reply":"2026-09-17T09:15:02.967947Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras import backend as K\n\ntrainable_params = int(np.sum([K.count_params(w) for w in model_inceptionv3.trainable_weights]))\nprint(trainable_params)\n","metadata":{"trusted":true,"scrolled":true,"execution":{"iopub.status.busy":"2026-09-17T09:15:11.534709Z","iopub.execute_input":"2026-09-17T09:15:11.535602Z","iopub.status.idle":"2026-09-17T09:15:11.541763Z","shell.execute_reply.started":"2026-09-17T09:15:11.535525Z","shell.execute_reply":"2026-09-17T09:15:11.54074Z"}},"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":"2026-09-17T09:15:14.773042Z","iopub.execute_input":"2026-09-17T09:15:14.773806Z","iopub.status.idle":"2026-09-17T09:15:14.779664Z","shell.execute_reply.started":"2026-09-17T09:15:14.773773Z","shell.execute_reply":"2026-09-17T09:15:14.778613Z"}},"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\nmodel_inceptionv3.reset_states()\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it, \n    steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=3, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:15:25.74262Z","iopub.execute_input":"2026-09-17T09:15:25.743348Z","iopub.status.idle":"2026-09-17T09:15:26.863822Z","shell.execute_reply.started":"2026-09-17T09:15:25.743319Z","shell.execute_reply":"2026-09-17T09:15:26.862496Z"}},"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":"2026-09-17T09:15:32.5527Z","iopub.execute_input":"2026-09-17T09:15:32.553082Z","iopub.status.idle":"2026-09-17T09:15:32.560738Z","shell.execute_reply.started":"2026-09-17T09:15:32.553057Z","shell.execute_reply":"2026-09-17T09:15:32.559747Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot_images_with_labels(images, labels, \"Dog-Cat\", \"Training\")","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.993271Z","iopub.status.idle":"2026-09-12T14:09:21.993619Z","shell.execute_reply.started":"2026-09-12T14:09:21.993474Z","shell.execute_reply":"2026-09-12T14:09:21.993489Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model.layers):\n#     print(index, layer.output.shape)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.995318Z","iopub.status.idle":"2026-09-12T14:09:21.995645Z","shell.execute_reply.started":"2026-09-12T14:09:21.995499Z","shell.execute_reply":"2026-09-12T14:09:21.995514Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# # mark loaded layers as not trainable\n# for index, layer in enumerate(model.layers[:15]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = False\n    \n# for index, layer in enumerate(model.layers[15:]):\n#     print(index, layer.name, layer.output_shape)\n#     layer.trainable = True","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:21.996782Z","iopub.status.idle":"2026-09-12T14:09:21.997163Z","shell.execute_reply.started":"2026-09-12T14:09:21.997018Z","shell.execute_reply":"2026-09-12T14:09:21.997034Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_inceptionv3.evaluate(test_it, steps=len(test_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))\n# learning curves\n# summarize_diagnostics(history)\n\n# best_model = 'vgg16_model.hdf5'\n# my_model.save(best_model)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-17T09:15:39.36591Z","iopub.execute_input":"2026-09-17T09:15:39.366849Z","iopub.status.idle":"2026-09-17T09:15:40.501975Z","shell.execute_reply.started":"2026-09-17T09:15:39.366817Z","shell.execute_reply":"2026-09-17T09:15:40.500632Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:22.000259Z","iopub.status.idle":"2026-09-12T14:09:22.000624Z","shell.execute_reply.started":"2026-09-12T14:09:22.00046Z","shell.execute_reply":"2026-09-12T14:09:22.000476Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# 5 first img: 1, 0, 1, 1, 0\nimages_to_predict = images[:5]\nimages_to_predict.shape","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:22.002462Z","iopub.status.idle":"2026-09-12T14:09:22.002786Z","shell.execute_reply.started":"2026-09-12T14:09:22.002641Z","shell.execute_reply":"2026-09-12T14:09:22.002656Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-09-12T14:09:22.004949Z","iopub.status.idle":"2026-09-12T14:09:22.005276Z","shell.execute_reply.started":"2026-09-12T14:09:22.00513Z","shell.execute_reply":"2026-09-12T14:09:22.005145Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}