{"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":[{"sourceType":"competition","sourceId":3362,"databundleVersionId":31148}],"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\nimport os\nfor 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":"2026-02-23T15:27:38.973811Z","iopub.execute_input":"2026-02-23T15:27:38.974544Z","iopub.status.idle":"2026-02-23T15:27:38.982836Z","shell.execute_reply.started":"2026-02-23T15:27:38.97451Z","shell.execute_reply":"2026-02-23T15:27:38.982039Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!python --version","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:38.984252Z","iopub.execute_input":"2026-02-23T15:27:38.984492Z","iopub.status.idle":"2026-02-23T15:27:39.9932Z","shell.execute_reply.started":"2026-02-23T15:27:38.984471Z","shell.execute_reply":"2026-02-23T15:27:39.992256Z"}},"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":"2026-02-23T15:27:39.994926Z","iopub.execute_input":"2026-02-23T15:27:39.995319Z","iopub.status.idle":"2026-02-23T15:27:48.509933Z","shell.execute_reply.started":"2026-02-23T15:27:39.995283Z","shell.execute_reply":"2026-02-23T15:27:48.509186Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:48.512092Z","iopub.execute_input":"2026-02-23T15:27:48.512974Z","iopub.status.idle":"2026-02-23T15:27:49.52181Z","shell.execute_reply.started":"2026-02-23T15:27:48.512948Z","shell.execute_reply":"2026-02-23T15:27:49.520908Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:49.523464Z","iopub.execute_input":"2026-02-23T15:27:49.523762Z","iopub.status.idle":"2026-02-23T15:27:50.542627Z","shell.execute_reply.started":"2026-02-23T15:27:49.523735Z","shell.execute_reply":"2026-02-23T15:27:50.541556Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls test1/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:50.544037Z","iopub.execute_input":"2026-02-23T15:27:50.544328Z","iopub.status.idle":"2026-02-23T15:27:51.584952Z","shell.execute_reply.started":"2026-02-23T15:27:50.544301Z","shell.execute_reply":"2026-02-23T15:27:51.584013Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls train/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:51.586256Z","iopub.execute_input":"2026-02-23T15:27:51.586554Z","iopub.status.idle":"2026-02-23T15:27:52.668939Z","shell.execute_reply.started":"2026-02-23T15:27:51.586521Z","shell.execute_reply":"2026-02-23T15:27:52.668056Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#ls train/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:52.670275Z","iopub.execute_input":"2026-02-23T15:27:52.670534Z","iopub.status.idle":"2026-02-23T15:27:52.674738Z","shell.execute_reply.started":"2026-02-23T15:27:52.670511Z","shell.execute_reply":"2026-02-23T15:27:52.6739Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# plot dog 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 + '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":"2026-02-23T15:27:52.678983Z","iopub.execute_input":"2026-02-23T15:27:52.679221Z","iopub.status.idle":"2026-02-23T15:27:54.032739Z","shell.execute_reply.started":"2026-02-23T15:27:52.679201Z","shell.execute_reply":"2026-02-23T15:27:54.031909Z"},"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":"2026-02-23T15:27:54.033882Z","iopub.execute_input":"2026-02-23T15:27:54.03415Z","iopub.status.idle":"2026-02-23T15:27:54.963716Z","shell.execute_reply.started":"2026-02-23T15:27:54.034126Z","shell.execute_reply":"2026-02-23T15:27:54.962898Z"},"trusted":true},"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":"2026-02-23T15:27:54.965066Z","iopub.execute_input":"2026-02-23T15:27:54.965431Z","iopub.status.idle":"2026-02-23T15:27:54.971295Z","shell.execute_reply.started":"2026-02-23T15:27:54.965397Z","shell.execute_reply":"2026-02-23T15:27:54.970456Z"}},"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":"2026-02-23T15:27:54.972205Z","iopub.execute_input":"2026-02-23T15:27:54.972421Z","iopub.status.idle":"2026-02-23T15:27:54.981602Z","shell.execute_reply.started":"2026-02-23T15:27:54.972401Z","shell.execute_reply":"2026-02-23T15:27:54.98081Z"},"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":"2026-02-23T15:27:54.982604Z","iopub.execute_input":"2026-02-23T15:27:54.982837Z","iopub.status.idle":"2026-02-23T15:27:54.991717Z","shell.execute_reply.started":"2026-02-23T15:27:54.982816Z","shell.execute_reply":"2026-02-23T15:27:54.990895Z"},"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":"2026-02-23T15:27:54.99278Z","iopub.execute_input":"2026-02-23T15:27:54.99317Z","iopub.status.idle":"2026-02-23T15:27:55.003191Z","shell.execute_reply.started":"2026-02-23T15:27:54.993148Z","shell.execute_reply":"2026-02-23T15:27:55.002501Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train/dogs/ | wc -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:55.004051Z","iopub.execute_input":"2026-02-23T15:27:55.004268Z","iopub.status.idle":"2026-02-23T15:27:56.082723Z","shell.execute_reply.started":"2026-02-23T15:27:55.004247Z","shell.execute_reply":"2026-02-23T15:27:56.081841Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:56.084436Z","iopub.execute_input":"2026-02-23T15:27:56.084833Z","iopub.status.idle":"2026-02-23T15:27:57.100768Z","shell.execute_reply.started":"2026-02-23T15:27:56.084786Z","shell.execute_reply":"2026-02-23T15:27:57.099912Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/train","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:57.102441Z","iopub.execute_input":"2026-02-23T15:27:57.102831Z","iopub.status.idle":"2026-02-23T15:27:58.103499Z","shell.execute_reply.started":"2026-02-23T15:27:57.102784Z","shell.execute_reply":"2026-02-23T15:27:58.102585Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls -l dataset_dogs_vs_cats/test","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:27:58.105017Z","iopub.execute_input":"2026-02-23T15:27:58.105314Z","iopub.status.idle":"2026-02-23T15:27:59.110785Z","shell.execute_reply.started":"2026-02-23T15:27:58.105284Z","shell.execute_reply":"2026-02-23T15:27:59.109697Z"}},"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":"2026-02-23T15:27:59.112317Z","iopub.execute_input":"2026-02-23T15:27:59.112616Z","iopub.status.idle":"2026-02-23T15:28:01.949986Z","shell.execute_reply.started":"2026-02-23T15:27:59.112587Z","shell.execute_reply":"2026-02-23T15:28:01.94925Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(src)\nprint(dst)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:01.951263Z","iopub.execute_input":"2026-02-23T15:28:01.951526Z","iopub.status.idle":"2026-02-23T15:28:01.956002Z","shell.execute_reply.started":"2026-02-23T15:28:01.951501Z","shell.execute_reply":"2026-02-23T15:28:01.955119Z"}},"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":"2026-02-23T15:28:01.957303Z","iopub.execute_input":"2026-02-23T15:28:01.957561Z","iopub.status.idle":"2026-02-23T15:28:04.110554Z","shell.execute_reply.started":"2026-02-23T15:28:01.957535Z","shell.execute_reply":"2026-02-23T15:28:04.109571Z"},"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":"2026-02-23T15:28:04.112175Z","iopub.execute_input":"2026-02-23T15:28:04.112542Z","iopub.status.idle":"2026-02-23T15:28:06.193159Z","shell.execute_reply.started":"2026-02-23T15:28:04.112508Z","shell.execute_reply":"2026-02-23T15:28:06.192013Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"!pip -q install livelossplot==0.5.5","metadata":{"execution":{"iopub.status.busy":"2026-02-23T15:28:06.194778Z","iopub.execute_input":"2026-02-23T15:28:06.195681Z","iopub.status.idle":"2026-02-23T15:28:14.364104Z","shell.execute_reply.started":"2026-02-23T15:28:06.195642Z","shell.execute_reply":"2026-02-23T15:28:14.362765Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2026-02-23T15:28:14.371575Z","iopub.execute_input":"2026-02-23T15:28:14.371884Z","iopub.status.idle":"2026-02-23T15:28:14.37644Z","shell.execute_reply.started":"2026-02-23T15:28:14.371857Z","shell.execute_reply":"2026-02-23T15:28:14.375546Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Prepare Final Dataset","metadata":{}},{"cell_type":"markdown","source":"# Start tutorial\n# Develop a Baseline CNN Model","metadata":{}},{"cell_type":"code","source":"# https://keras.io/api/applications/","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:14.377615Z","iopub.execute_input":"2026-02-23T15:28:14.377823Z","iopub.status.idle":"2026-02-23T15:28:14.387287Z","shell.execute_reply.started":"2026-02-23T15:28:14.377805Z","shell.execute_reply":"2026-02-23T15:28:14.386475Z"}},"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":"2026-02-23T15:28:14.38849Z","iopub.execute_input":"2026-02-23T15:28:14.389074Z","iopub.status.idle":"2026-02-23T15:28:14.399367Z","shell.execute_reply.started":"2026-02-23T15:28:14.389051Z","shell.execute_reply":"2026-02-23T15:28:14.398564Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# define cnn model\ndef define_model_1():\n\tmodel = Sequential()\n\tmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dense(1, activation='sigmoid'))\n\t# compile model\n\topt = SGD(lr=0.001, momentum=0.9)\n\tmodel.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n\treturn model","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:14.400357Z","iopub.execute_input":"2026-02-23T15:28:14.400575Z","iopub.status.idle":"2026-02-23T15:28:14.408672Z","shell.execute_reply.started":"2026-02-23T15:28:14.400555Z","shell.execute_reply":"2026-02-23T15:28:14.408083Z"}},"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":"2026-02-23T15:28:14.409604Z","iopub.execute_input":"2026-02-23T15:28:14.409836Z","iopub.status.idle":"2026-02-23T15:28:14.421088Z","shell.execute_reply.started":"2026-02-23T15:28:14.409816Z","shell.execute_reply":"2026-02-23T15:28:14.420281Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# run the test harness for evaluating a model, not recommend to call this function\ndef run_test_harness():\n\t# define model\n\tmodel = define_model()\n\t# create data generator\n\tdatagen = ImageDataGenerator(rescale=1.0/255.0)\n\t# prepare iterators\n\ttrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\ttest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\t\tclass_mode='binary', batch_size=64, target_size=(200, 200))\n\t# fit model\n\thistory = model.fit_generator(train_it, steps_per_epoch=len(train_it),\n\t\tvalidation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)\n\t# evaluate model\n\t_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\n\tprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:14.422146Z","iopub.execute_input":"2026-02-23T15:28:14.42236Z","iopub.status.idle":"2026-02-23T15:28:14.437304Z","shell.execute_reply.started":"2026-02-23T15:28:14.42234Z","shell.execute_reply":"2026-02-23T15:28:14.436722Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_1 = define_model_1()\nprint(model_1.summary())","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:14.43833Z","iopub.execute_input":"2026-02-23T15:28:14.43859Z","iopub.status.idle":"2026-02-23T15:28:14.509386Z","shell.execute_reply.started":"2026-02-23T15:28:14.438568Z","shell.execute_reply":"2026-02-23T15:28:14.508512Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1.0/255.0)\n\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))\n\nval_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:14.510458Z","iopub.execute_input":"2026-02-23T15:28:14.511018Z","iopub.status.idle":"2026-02-23T15:28:15.151617Z","shell.execute_reply.started":"2026-02-23T15:28:14.510987Z","shell.execute_reply":"2026-02-23T15:28:15.150734Z"}},"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":"2026-02-23T15:28:15.152815Z","iopub.execute_input":"2026-02-23T15:28:15.153456Z","iopub.status.idle":"2026-02-23T15:28:15.159715Z","shell.execute_reply.started":"2026-02-23T15:28:15.15342Z","shell.execute_reply":"2026-02-23T15:28:15.158914Z"}},"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":"2026-02-23T15:28:15.160925Z","iopub.execute_input":"2026-02-23T15:28:15.161607Z","iopub.status.idle":"2026-02-23T15:28:15.171463Z","shell.execute_reply.started":"2026-02-23T15:28:15.161584Z","shell.execute_reply":"2026-02-23T15:28:15.170603Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras\n\nhistory_1 = model_1.fit(\n    train_it,\n    validation_data=val_it,\n    epochs=1,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:28:15.172376Z","iopub.execute_input":"2026-02-23T15:28:15.17261Z","iopub.status.idle":"2026-02-23T15:29:00.085501Z","shell.execute_reply.started":"2026-02-23T15:28:15.17259Z","shell.execute_reply":"2026-02-23T15:29:00.084498Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nmodel_1.reset_states()\nhistory_1 = model_1.fit_generator(\n    train_it, steps_per_epoch=len(train_it),\n    validation_data=val_it,\n    validation_steps=len(val_it),\n    epochs=1, verbose=1,\n    callbacks = [PlotLossesKeras()]\n    )","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2026-02-23T15:29:00.086686Z","iopub.execute_input":"2026-02-23T15:29:00.086991Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(history_1)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# evaluate model\n_, acc = model_1.evaluate_generator(val_it, steps=len(val_it), verbose=1)\nprint('> %.3f' % (acc * 100.0))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"ls ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"pwd","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"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\nimage_folder = '/kaggle/working/test1'\n\n# List all .jpg files in the directory (adjust the pattern if needed)\nimage_files = glob(os.path.join(image_folder, '*.jpg'))\n\n# Check if images were found\nif not image_files:\n    print(\"No images found. Please verify the directory and file extensions.\")\n    \n# Create a DataFrame with the file paths\ndf = 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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"image_files[:5], type(image_files), len(image_files)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.describe()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.loc[1]","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df.sample(5)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df['filename']","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"IMAGE_SIZE = (224, 224)\n\ndatagen = ImageDataGenerator(rescale=1.0/255.0,\n                            horizontal_flip=True,)\nprint(IMAGE_SIZE)\n# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=IMAGE_SIZE )\n\nval_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=IMAGE_SIZE )\n\n# Prediction\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n# Initialize your ImageDataGenerator (modify parameters as needed)\ndatagen_test = ImageDataGenerator(rescale=1./255,\n                                 horizontal_flip=True)\n\n# Create the data generator using the DataFrame\ntest_it = datagen_test.flow_from_dataframe(\n    dataframe=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=64,\n    class_mode=None,       # Since there are no labels\n    # shuffle=True,         # Usually testing data should not be shuffled\n    shuffle=False,\n)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\ndef plot_exmaple(images):\n    # Assuming test_images is a numpy array with shape (64, height, width, channels)\n    fig, axes = plt.subplots(8, 8, figsize=(16, 16))\n    axes = axes.flatten()  # Flatten the 8x8 grid into a list for easy iteration\n    \n    for i, ax in enumerate(axes):\n        # Ensure there are enough images in the batch before plotting\n        if i < images.shape[0]:\n            ax.imshow(images[i])\n        #ax.axis('off')  # Turn off axis ticks/labels for clarity\n        ax.axis('on')  # Turn off axis ticks/labels for clarity\n    \n    plt.tight_layout()\nplt.show()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_images, train_labels = train_it.__next__()\ntrain_images.shape\nplot_exmaple(train_images)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"val_images, val_labels = val_it.__next__()\nval_images.shape\nplot_exmaple(val_images)\nval_labels[:8]","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"test_images = test_it.__next__()\ntest_images.shape\nplot_exmaple(test_images)","metadata":{"trusted":true},"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# define cnn model\ndef define_model_vgg16():\n\t# load model\n\tmodel = VGG16(include_top=False, input_shape=(224, 224, 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","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\nmodel = VGG16(include_top=False, input_shape=(224, 224, 3))\n# mark loaded layers as not trainable\nfor layer in model.layers:\n    layer.trainable = False\n\nprint(model.layers[-1].output)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\n# model_16_feature_extractor = VGG16(include_top=False, input_shape=(224, 224, 3))\n# model_16_feature_extractor.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(model_16_feature_extractor.layers):\n# \t\tprint(index, layer.trainable)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# load model\n# model_16_top = VGG16(include_top=True, input_shape=(224, 224, 3))\n# model_16_top.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"vgg16_model = define_model_vgg16()\nvgg16_model.summary()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers):\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers[-7:]):\n#     print(index, layer.name, layer.trainable)\n    ","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers[-7:]):\n#     layer.trainable = True\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# for index, layer in enumerate(vgg16_model.layers):\n#     if index >= 15:\n#         layer.trainable = True\n\n# for index, layer in enumerate(vgg16_model.layers):\n#     print(index, layer.name, layer.trainable)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"id(vgg16_model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import tensorflow as tf\nfor layer in vgg16_model.layers[-4:]:\n    layer.trainable = True\n\nvgg16_model.compile(\n    optimizer=tf.keras.optimizers.Adam(1e-5),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"history_2 = vgg16_model.fit(\n    train_it,\n    validation_data=val_it,\n    epochs=6,\n    callbacks=[PlotLossesKeras()],\n    verbose=1\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# learning curves\nsummarize_diagnostics(vgg16_model_history)\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(val_it, steps=len(val_it), verbose=1)\nprint('Val: > %.3f' % (acc * 100.0))\n\n# evaluate model\n_, acc = vgg16_model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\nprint('Test: > %.3f' % (acc * 100.0))","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":"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"model_inceptionv3 = define_model_inceptionv3()\nprint(id(model_inceptionv3))\n# model_inceptionv3.summary()","metadata":{"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},"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications import InceptionV3\nfrom tensorflow.keras.models import Model\nfrom tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout\nfrom tensorflow.keras.optimizers import Adam\n\nbase_model = InceptionV3(\n    weights='imagenet',\n    include_top=False,\n    input_shape=(224,224,3)\n)\n\nbase_model.trainable = False\n\nx = base_model.output\nx = GlobalAveragePooling2D()(x)\nx = Dense(256, activation='relu')(x)\nx = Dropout(0.5)(x)\noutput = Dense(1, activation='sigmoid')(x)\n\nmodel_inceptionv3 = Model(base_model.input, output)\n\nmodel_inceptionv3.compile(\n    optimizer=Adam(1e-4),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# fit model\nfrom livelossplot import PlotLossesKeras\n\nhistory_inceptionv3 = model_inceptionv3.fit(\n    train_it,\n    validation_data=val_it,\n    epochs=10,\n    verbose=1,\n    callbacks=[PlotLossesKeras()]\n)","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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"for index, layer in enumerate(model.layers):\n  print(index, layer.output.shape)","metadata":{"trusted":true},"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},"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_m#odel = 'vgg16_model.hdf5'\n# my_mo#del.save(best_model)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"images = test_it.__next__()\nimages.shape","metadata":{"trusted":true},"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},"outputs":[],"execution_count":null},{"cell_type":"code","source":"probs = model_inceptionv3.predict(images_to_predict, verbose=1)\nprobs","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from tensorflow.keras.applications import Xception\n\nbase_model = Xception(weights='imagenet', include_top=False, input_shape=(224,224,3))\nbase_model.trainable = False\n\nmodel_xcp = Sequential([\n    base_model,\n    GlobalAveragePooling2D(),\n    Dense(256, activation='relu'),\n    Dropout(0.5),\n    Dense(1, activation='sigmoid')\n])\n\nmodel_xcp.compile(\n    optimizer='adam',\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras\n\nhistory_xcp = model_xcp.fit(\n    train_it,\n    validation_data=val_it,\n    epochs=10,\n    verbose=1\n)","metadata":{"trusted":true,"jupyter":{"source_hidden":true}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"Make Prediction","metadata":{}},{"cell_type":"code","source":"import os\n\nprint(os.listdir())","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"dst_dir = 'test/'\nclasses = ['cats', 'dogs']\n\nplt.figure(figsize=(12,6))\nidx = 1\n\nfor cls in classes:\n    cls_path = os.path.join(test_dir, cls)\n    images = random.sample(os.listdir(test1), 5) \n    for img_name in images:\n        img_path = os.path.join(cls_path, img_name)\n\n        # load & preprocess image\n        img = image.load_img(img_path, target_size=(224,224))\n        img_arr = image.img_to_array(img)\n        img_arr = np.expand_dims(img_arr, axis=0)\n        img_arr = preprocess_input(img_arr)\n\n        # prediction\n        pred = model_xcp.predict(img_arr)[0][0]\n        pred_label = 'dog' if pred > 0.5 else 'cat'\n\n        # plot\n        plt.subplot(2,5,idx)\n        plt.imshow(img)\n        plt.title(f\"True: {cls}\\nPred: {pred_label}\\nProb: {pred:.2f}\")\n        plt.axis('off')\n        idx += 1\n\nplt.tight_layout()\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"dst_dir = 'test/'","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}