{"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\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":"2024-02-09T06:57:14.978795Z","iopub.execute_input":"2024-02-09T06:57:14.979176Z","iopub.status.idle":"2024-02-09T06:57:14.987254Z","shell.execute_reply.started":"2024-02-09T06:57:14.979145Z","shell.execute_reply":"2024-02-09T06:57:14.985948Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-09T06:57:14.989225Z","iopub.execute_input":"2024-02-09T06:57:14.989542Z","iopub.status.idle":"2024-02-09T06:57:31.945241Z","shell.execute_reply.started":"2024-02-09T06:57:14.989516Z","shell.execute_reply":"2024-02-09T06:57:31.944326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"!ls train","metadata":{"execution":{"iopub.status.busy":"2024-01-08T06:57:18.293035Z","iopub.execute_input":"2024-01-08T06:57:18.293457Z","iopub.status.idle":"2024-01-08T06:57:19.311078Z","shell.execute_reply.started":"2024-01-08T06:57:18.293422Z","shell.execute_reply":"2024-01-08T06:57:19.309969Z"}}},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\ntrain_folder = 'train/'\n\n# define location of dataset\nfolder = train_folder\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":"2024-02-09T06:57:31.947128Z","iopub.execute_input":"2024-02-09T06:57:31.947438Z","iopub.status.idle":"2024-02-09T06:57:33.168708Z","shell.execute_reply.started":"2024-02-09T06:57:31.947413Z","shell.execute_reply":"2024-02-09T06:57:33.167829Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# 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":"2024-02-09T06:57:33.169889Z","iopub.execute_input":"2024-02-09T06:57:33.170209Z","iopub.status.idle":"2024-02-09T06:57:34.267537Z","shell.execute_reply.started":"2024-02-09T06:57:33.170184Z","shell.execute_reply":"2024-02-09T06:57:34.266530Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_folder","metadata":{"execution":{"iopub.status.busy":"2024-02-09T06:57:34.269551Z","iopub.execute_input":"2024-02-09T06:57:34.269857Z","iopub.status.idle":"2024-02-09T06:57:34.276258Z","shell.execute_reply.started":"2024-02-09T06:57:34.269830Z","shell.execute_reply":"2024-02-09T06:57:34.275273Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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":"2024-02-09T06:57:34.277390Z","iopub.execute_input":"2024-02-09T06:57:34.277969Z","iopub.status.idle":"2024-02-09T06:57:34.286555Z","shell.execute_reply.started":"2024-02-09T06:57:34.277933Z","shell.execute_reply":"2024-02-09T06:57:34.285692Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n#for file in listdir(folder[:10_000]): # select 10_000 images\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":"2024-02-09T06:57:34.287782Z","iopub.execute_input":"2024-02-09T06:57:34.288059Z","iopub.status.idle":"2024-02-09T06:59:05.117504Z","shell.execute_reply.started":"2024-02-09T06:57:34.288034Z","shell.execute_reply":"2024-02-09T06:59:05.116401Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l","metadata":{"execution":{"iopub.status.busy":"2024-02-09T06:59:05.120070Z","iopub.execute_input":"2024-02-09T06:59:05.120448Z","iopub.status.idle":"2024-02-09T06:59:06.540845Z","shell.execute_reply.started":"2024-02-09T06:59:05.120413Z","shell.execute_reply":"2024-02-09T06:59:06.539810Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","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":"2024-02-09T06:59:06.542401Z","iopub.execute_input":"2024-02-09T06:59:06.542735Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(photos.shape, labels.shape)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create directories\nimport os\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\nfor subdir in subdirs:\n\t# create label subdirectories\n\tlabeldirs = ['dogs/', 'cats/']\n\tfor labldir in labeldirs:\n\t\tnewdir = dataset_home + subdir + labldir\n\t\tos.makedirs(newdir, exist_ok=True)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:01:58.971397Z","iopub.execute_input":"2024-02-09T07:01:58.972146Z","iopub.status.idle":"2024-02-09T07:01:58.978540Z","shell.execute_reply.started":"2024-02-09T07:01:58.972106Z","shell.execute_reply":"2024-02-09T07:01:58.977535Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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\n# create directories\ndataset_home = 'dataset_dogs_vs_cats/'\nsubdirs = ['train/', 'test/']\nfor subdir in subdirs:\n\t# create label subdirectories\n\tlabeldirs = ['dogs/', 'cats/']\n\tfor labldir in labeldirs:\n\t\tnewdir = dataset_home + subdir + labldir\n\t\tmakedirs(newdir, exist_ok=True)\n# seed random number generator\nseed(1)\n# define ratio of pictures to use for validation\nval_ratio = 0.25\n# copy training dataset images into subdirectories\nsrc_directory = 'train/'\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":"2024-02-09T07:01:59.689559Z","iopub.execute_input":"2024-02-09T07:01:59.689924Z","iopub.status.idle":"2024-02-09T07:02:13.732301Z","shell.execute_reply.started":"2024-02-09T07:01:59.689897Z","shell.execute_reply":"2024-02-09T07:02:13.731190Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/dogs | wc -l","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:02:13.734073Z","iopub.execute_input":"2024-02-09T07:02:13.734356Z","iopub.status.idle":"2024-02-09T07:02:14.834700Z","shell.execute_reply.started":"2024-02-09T07:02:13.734333Z","shell.execute_reply":"2024-02-09T07:02:14.833683Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l dataset_dogs_vs_cats/train/cats | wc -l","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:02:14.836216Z","iopub.execute_input":"2024-02-09T07:02:14.836538Z","iopub.status.idle":"2024-02-09T07:02:15.871826Z","shell.execute_reply.started":"2024-02-09T07:02:14.836507Z","shell.execute_reply":"2024-02-09T07:02:15.870701Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"!ls test1\n","metadata":{"execution":{"iopub.status.busy":"2024-01-13T03:01:48.472037Z","iopub.execute_input":"2024-01-13T03:01:48.473336Z","iopub.status.idle":"2024-01-13T03:01:49.583287Z","shell.execute_reply.started":"2024-01-13T03:01:48.47329Z","shell.execute_reply":"2024-01-13T03:01:49.58225Z"}}},{"cell_type":"markdown","source":"# Develop a Baseline CNN Model","metadata":{}},{"cell_type":"code","source":"!pip install livelossplot -q","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:02:19.970728Z","iopub.execute_input":"2024-02-09T07:02:19.971725Z","iopub.status.idle":"2024-02-09T07:02:33.873773Z","shell.execute_reply.started":"2024-02-09T07:02:19.971674Z","shell.execute_reply":"2024-02-09T07:02:33.872473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:02:33.876064Z","iopub.execute_input":"2024-02-09T07:02:33.876947Z","iopub.status.idle":"2024-02-09T07:02:33.892080Z","shell.execute_reply.started":"2024-02-09T07:02:33.876902Z","shell.execute_reply":"2024-02-09T07:02:33.891153Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import sys\nfrom matplotlib import pyplot\nfrom keras.utils import to_categorical\nfrom keras.applications.inception_v3 import InceptionV3\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():\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[:15]:\n        layer.trainable = False\n    # add new classifier layers\n    flat1 = Flatten()(model.layers[-1].output)\n    class1 = Dense(128, activation='relu', kernel_initializer='he_uniform')(flat1)\n    output = Dense(1, activation='sigmoid')(class1)\n    # define new model\n    model = Model(inputs=model.inputs, outputs=output)\n    # compile model\n    opt = SGD(lr=0.0001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model\n\n# 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    # save plot to file\n    filename = sys.argv[0].split('/')[-1]\n    pyplot.savefig(filename + '_plot.png')\n    pyplot.close()\n\n# run the test harness for evaluating a model\ndef run_test_harness():\n# define model\n    model = define_model()\n    # create data generator\n    datagen = ImageDataGenerator(\n    rescale=1./255,\n    rotation_range=40,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    fill_mode='nearest'\n    )\n    # prepare iterator\n    train_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=128, target_size=(299, 299))\n    test_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=128, target_size=(299, 299))\n    # fit model\n    history = model.fit(train_it,\n    steps_per_epoch=len(train_it),\n    validation_data=test_it,\n    validation_steps=len(test_it),\n    epochs=10, verbose=1,\n    callbacks=[PlotLossesKeras()])\n    # evaluate model\n    _, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\n    print('> %.3f' % (acc * 100.0))\n    # learning curves\n    summarize_diagnostics(history)","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:07:45.799724Z","iopub.execute_input":"2024-02-09T07:07:45.800445Z","iopub.status.idle":"2024-02-09T07:07:45.818143Z","shell.execute_reply.started":"2024-02-09T07:07:45.800409Z","shell.execute_reply":"2024-02-09T07:07:45.817319Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run_test_harness()","metadata":{"execution":{"iopub.status.busy":"2024-02-09T07:07:46.203419Z","iopub.execute_input":"2024-02-09T07:07:46.204432Z","iopub.status.idle":"2024-02-09T08:36:03.052541Z","shell.execute_reply.started":"2024-02-09T07:07:46.204391Z","shell.execute_reply":"2024-02-09T08:36:03.051671Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}