{"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":"","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":"2024-02-07T08:17:44.031987Z","iopub.execute_input":"2024-02-07T08:17:44.032387Z","iopub.status.idle":"2024-02-07T08:17:44.388001Z","shell.execute_reply.started":"2024-02-07T08:17:44.032353Z","shell.execute_reply":"2024-02-07T08:17:44.387067Z"},"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":"2024-02-07T08:17:44.389644Z","iopub.execute_input":"2024-02-07T08:17:44.390092Z","iopub.status.idle":"2024-02-07T08:18:00.340045Z","shell.execute_reply.started":"2024-02-07T08:17:44.390057Z","shell.execute_reply":"2024-02-07T08:18:00.338804Z"},"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":"2024-02-07T08:18:00.341486Z","iopub.execute_input":"2024-02-07T08:18:00.341888Z","iopub.status.idle":"2024-02-07T08:18:01.557746Z","shell.execute_reply.started":"2024-02-07T08:18:00.341849Z","shell.execute_reply":"2024-02-07T08:18:01.556869Z"},"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":"2024-02-07T08:18:01.559938Z","iopub.execute_input":"2024-02-07T08:18:01.560222Z","iopub.status.idle":"2024-02-07T08:18:02.739089Z","shell.execute_reply.started":"2024-02-07T08:18:01.560196Z","shell.execute_reply":"2024-02-07T08:18:02.738306Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_folder","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:18:02.740409Z","iopub.execute_input":"2024-02-07T08:18:02.740722Z","iopub.status.idle":"2024-02-07T08:18:02.746613Z","shell.execute_reply.started":"2024-02-07T08:18:02.740685Z","shell.execute_reply":"2024-02-07T08:18:02.745654Z"},"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":"2024-02-07T08:18:02.747845Z","iopub.execute_input":"2024-02-07T08:18:02.748127Z","iopub.status.idle":"2024-02-07T08:18:14.295863Z","shell.execute_reply.started":"2024-02-07T08:18:02.748103Z","shell.execute_reply":"2024-02-07T08:18:14.294823Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:18:14.297124Z","iopub.execute_input":"2024-02-07T08:18:14.297839Z","iopub.status.idle":"2024-02-07T08:18:15.282530Z","shell.execute_reply.started":"2024-02-07T08:18:14.297801Z","shell.execute_reply":"2024-02-07T08:18:15.281322Z"},"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":"2024-02-07T08:18:15.284499Z","iopub.execute_input":"2024-02-07T08:18:15.284875Z","iopub.status.idle":"2024-02-07T08:19:43.047590Z","shell.execute_reply.started":"2024-02-07T08:18:15.284837Z","shell.execute_reply":"2024-02-07T08:19:43.046627Z"},"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":"2024-02-07T08:20:34.140582Z","iopub.execute_input":"2024-02-07T08:20:34.140996Z","iopub.status.idle":"2024-02-07T08:21:28.326897Z","shell.execute_reply.started":"2024-02-07T08:20:34.140964Z","shell.execute_reply":"2024-02-07T08:21:28.326041Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(photos.shape, labels.shape)","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:21:28.335157Z","iopub.execute_input":"2024-02-07T08:21:28.335560Z","iopub.status.idle":"2024-02-07T08:21:28.345777Z","shell.execute_reply.started":"2024-02-07T08:21:28.335503Z","shell.execute_reply":"2024-02-07T08:21:28.344879Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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')\nprint(photos.shape, labels.shape)","metadata":{"execution":{"iopub.status.busy":"2024-01-13T04:07:54.758244Z","iopub.execute_input":"2024-01-13T04:07:54.758579Z"}}},{"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":"2024-02-07T08:21:48.962078Z","iopub.execute_input":"2024-02-07T08:21:48.962452Z","iopub.status.idle":"2024-02-07T08:21:48.968945Z","shell.execute_reply.started":"2024-02-07T08:21:48.962421Z","shell.execute_reply":"2024-02-07T08:21:48.967965Z"},"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":"2024-02-07T08:21:51.314015Z","iopub.execute_input":"2024-02-07T08:21:51.314411Z","iopub.status.idle":"2024-02-07T08:22:07.898679Z","shell.execute_reply.started":"2024-02-07T08:21:51.314377Z","shell.execute_reply":"2024-02-07T08:22:07.897577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l test1 | wc ","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:22:07.900833Z","iopub.execute_input":"2024-02-07T08:22:07.901774Z","iopub.status.idle":"2024-02-07T08:22:09.167578Z","shell.execute_reply.started":"2024-02-07T08:22:07.901735Z","shell.execute_reply":"2024-02-07T08:22:09.166349Z"},"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":"2024-02-07T08:22:09.169037Z","iopub.execute_input":"2024-02-07T08:22:09.169385Z","iopub.status.idle":"2024-02-07T08:22:10.268589Z","shell.execute_reply.started":"2024-02-07T08:22:09.169354Z","shell.execute_reply":"2024-02-07T08:22:10.267465Z"},"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":"2024-02-07T08:22:10.271432Z","iopub.execute_input":"2024-02-07T08:22:10.272295Z","iopub.status.idle":"2024-02-07T08:22:11.380600Z","shell.execute_reply.started":"2024-02-07T08:22:10.272231Z","shell.execute_reply":"2024-02-07T08:22:11.379495Z"},"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":"# 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\n\n# 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\n\n# 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()\n\n# run the test harness for evaluating a model\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=1)\n\t# evaluate model\n\t_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=0)\n\tprint('> %.3f' % (acc * 100.0))\n\t# learning curves\n\tsummarize_diagnostics(history)\n\n","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:22:19.946233Z","iopub.execute_input":"2024-02-07T08:22:19.947136Z","iopub.status.idle":"2024-02-07T08:22:29.009264Z","shell.execute_reply.started":"2024-02-07T08:22:19.947097Z","shell.execute_reply":"2024-02-07T08:22:29.008304Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install livelossplot -q","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:22:29.011224Z","iopub.execute_input":"2024-02-07T08:22:29.012354Z","iopub.status.idle":"2024-02-07T08:22:42.622646Z","shell.execute_reply.started":"2024-02-07T08:22:29.012288Z","shell.execute_reply":"2024-02-07T08:22:42.621213Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:22:42.624242Z","iopub.execute_input":"2024-02-07T08:22:42.624643Z","iopub.status.idle":"2024-02-07T08:22:42.640678Z","shell.execute_reply.started":"2024-02-07T08:22:42.624610Z","shell.execute_reply":"2024-02-07T08:22:42.639849Z"},"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.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():\n    # load model\n    model = VGG16(include_top=False, input_shape=(224, 224, 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=64, target_size=(224, 224))\n    test_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n        class_mode='binary', batch_size=64, target_size=(224, 224))\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":"2024-02-07T08:44:17.420968Z","iopub.execute_input":"2024-02-07T08:44:17.421939Z","iopub.status.idle":"2024-02-07T08:44:17.438239Z","shell.execute_reply.started":"2024-02-07T08:44:17.421901Z","shell.execute_reply":"2024-02-07T08:44:17.437326Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = define_model()","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:44:20.821063Z","iopub.execute_input":"2024-02-07T08:44:20.821775Z","iopub.status.idle":"2024-02-07T08:44:22.848926Z","shell.execute_reply.started":"2024-02-07T08:44:20.821739Z","shell.execute_reply":"2024-02-07T08:44:22.848143Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = define_model()","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:44:25.085251Z","iopub.execute_input":"2024-02-07T08:44:25.085651Z","iopub.status.idle":"2024-02-07T08:44:25.446335Z","shell.execute_reply.started":"2024-02-07T08:44:25.085620Z","shell.execute_reply":"2024-02-07T08:44:25.445210Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:44:27.150024Z","iopub.execute_input":"2024-02-07T08:44:27.150913Z","iopub.status.idle":"2024-02-07T08:44:27.199978Z","shell.execute_reply.started":"2024-02-07T08:44:27.150874Z","shell.execute_reply":"2024-02-07T08:44:27.199098Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run_test_harness()","metadata":{"execution":{"iopub.status.busy":"2024-02-07T08:44:30.292689Z","iopub.execute_input":"2024-02-07T08:44:30.293097Z","iopub.status.idle":"2024-02-07T09:48:57.218543Z","shell.execute_reply.started":"2024-02-07T08:44:30.293065Z","shell.execute_reply":"2024-02-07T09:48:57.217478Z"},"trusted":true},"execution_count":null,"outputs":[]}]}