{"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":"gpu","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":"","metadata":{},"execution_count":null,"outputs":[]},{"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":"2024-01-26T14:50:56.162005Z","iopub.execute_input":"2024-01-26T14:50:56.162397Z","iopub.status.idle":"2024-01-26T14:50:56.577532Z","shell.execute_reply.started":"2024-01-26T14:50:56.162365Z","shell.execute_reply":"2024-01-26T14:50:56.576441Z"},"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":"2024-01-26T14:50:56.579311Z","iopub.execute_input":"2024-01-26T14:50:56.579732Z","iopub.status.idle":"2024-01-26T14:51:12.872831Z","shell.execute_reply.started":"2024-01-26T14:50:56.579703Z","shell.execute_reply":"2024-01-26T14:51:12.871832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# plot dog photos from the dogs vs cats dataset\nfrom matplotlib import pyplot\nfrom matplotlib.image import imread\ntrain_folder = '/kaggle/working/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":"2024-01-26T14:51:12.874229Z","iopub.execute_input":"2024-01-26T14:51:12.874649Z","iopub.status.idle":"2024-01-26T14:51:14.401171Z","shell.execute_reply.started":"2024-01-26T14:51:12.87461Z","shell.execute_reply":"2024-01-26T14:51:14.399952Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# 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\n# define location of dataset\nfolder = 'train/'\nphotos, labels = list(), list()\n# enumerate files in the directory\nfor file in listdir(folder):\n # determine class\n    output = 0.0\n    if file.startswith('dog'):\n        output = 1.0\n # load image\n    photo = load_img(folder + file, target_size=(200, 200))\n # convert to numpy array\n    photo = img_to_array(photo)\n # store\n    photos.append(photo)\n    labels.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":"2024-01-26T14:51:14.403485Z","iopub.execute_input":"2024-01-26T14:51:14.403843Z","iopub.status.idle":"2024-01-26T14:53:01.698171Z","shell.execute_reply.started":"2024-01-26T14:51:14.40381Z","shell.execute_reply":"2024-01-26T14:53:01.696919Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# load and confirm the shape\nfrom numpy import load\nphotos = load('dogs_vs_cats_photos.npy')\nlabels = load('dogs_vs_cats_labels.npy')\nprint(photos.shape, labels.shape)","metadata":{"execution":{"iopub.status.busy":"2024-01-26T14:53:01.700715Z","iopub.execute_input":"2024-01-26T14:53:01.701382Z"},"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":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# block 1\nmodel.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\nmodel.add(MaxPooling2D((2, 2)))\n# block 2\nmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))\n# block 3\nmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\nmodel.add(MaxPooling2D((2, 2)))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define cnn model\ndef define_model():\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_count":null,"outputs":[]},{"cell_type":"code","source":"# define model\nmodel = define_model()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create data generator\ndatagen = ImageDataGenerator(rescale=1.0/255.0)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# fit model\nhistory = model.fit_generator(train_it, steps_per_epoch=len(train_it),\n\tvalidation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# evaluate model\n_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# plot diagnostic learning curves\ndef summarize_diagnostics(history):\n\t# plot loss\n\tpyplot.subplot(211)\n\tpyplot.title('Cross Entropy Loss')\n\tpyplot.plot(history.history['loss'], color='blue', label='train')\n\tpyplot.plot(history.history['val_loss'], color='orange', label='test')\n\t# plot accuracy\n\tpyplot.subplot(212)\n\tpyplot.title('Classification Accuracy')\n\tpyplot.plot(history.history['accuracy'], color='blue', label='train')\n\tpyplot.plot(history.history['val_accuracy'], color='orange', label='test')\n\t# save plot to file\n\tfilename = sys.argv[0].split('/')[-1]\n\tpyplot.savefig(filename + '_plot.png')\n\tpyplot.close()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define cnn model\ndef define_model():\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":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Found 18697 images belonging to 2 classes.\nFound 6303 images belonging to 2 classes.\n> 72.331","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define cnn model\ndef define_model():\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(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\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":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Found 18697 images belonging to 2 classes.\nFound 6303 images belonging to 2 classes.\n> 76.646","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define cnn model\ndef define_model():\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(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\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":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Found 18697 images belonging to 2 classes.\nFound 6303 images belonging to 2 classes.\n> 80.184","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# define cnn model\ndef define_model():\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(Dropout(0.2))\n\tmodel.add(Conv2D(64, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Dropout(0.2))\n\tmodel.add(Conv2D(128, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same'))\n\tmodel.add(MaxPooling2D((2, 2)))\n\tmodel.add(Dropout(0.2))\n\tmodel.add(Flatten())\n\tmodel.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n\tmodel.add(Dropout(0.5))\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":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Found 18697 images belonging to 2 classes.\nFound 6303 images belonging to 2 classes.\n> 81.279","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create data generators\ntrain_datagen = ImageDataGenerator(rescale=1.0/255.0,\n\twidth_shift_range=0.1, height_shift_range=0.1, horizontal_flip=True)\ntest_datagen = ImageDataGenerator(rescale=1.0/255.0)\n# prepare iterators\ntrain_it = train_datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = test_datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\tclass_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{},"execution_count":null,"outputs":[]}]}