{"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":"# 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":"2024-01-22T04:53:57.310237Z","iopub.execute_input":"2024-01-22T04:53:57.310735Z","iopub.status.idle":"2024-01-22T04:53:57.651932Z","shell.execute_reply.started":"2024-01-22T04:53:57.310694Z","shell.execute_reply":"2024-01-22T04:53:57.651068Z"},"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":"2024-01-22T04:53:57.653577Z","iopub.execute_input":"2024-01-22T04:53:57.653951Z","iopub.status.idle":"2024-01-22T04:54:12.425497Z","shell.execute_reply.started":"2024-01-22T04:53:57.653925Z","shell.execute_reply":"2024-01-22T04:54:12.424713Z"},"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":"2024-01-22T04:54:12.426548Z","iopub.execute_input":"2024-01-22T04:54:12.426826Z","iopub.status.idle":"2024-01-22T04:54:13.620964Z","shell.execute_reply.started":"2024-01-22T04:54:12.426802Z","shell.execute_reply":"2024-01-22T04:54:13.620092Z"},"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":"2024-01-22T04:54:13.623387Z","iopub.execute_input":"2024-01-22T04:54:13.624124Z","iopub.status.idle":"2024-01-22T04:54:14.731168Z","shell.execute_reply.started":"2024-01-22T04:54:13.624092Z","shell.execute_reply":"2024-01-22T04:54:14.730214Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_folder","metadata":{"execution":{"iopub.status.busy":"2024-01-22T04:54:14.732309Z","iopub.execute_input":"2024-01-22T04:54:14.732628Z","iopub.status.idle":"2024-01-22T04:54:14.739167Z","shell.execute_reply.started":"2024-01-22T04:54:14.732599Z","shell.execute_reply":"2024-01-22T04:54:14.73828Z"},"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":"2024-01-22T04:54:14.740456Z","iopub.execute_input":"2024-01-22T04:54:14.740747Z","iopub.status.idle":"2024-01-22T04:54:25.645404Z","shell.execute_reply.started":"2024-01-22T04:54:14.740701Z","shell.execute_reply":"2024-01-22T04:54:25.644405Z"},"trusted":true},"execution_count":null,"outputs":[]},{"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#for file in listdir(folder[:5_000]): # select 5_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":"2024-01-13T02:49:22.913849Z","iopub.execute_input":"2024-01-13T02:49:22.914548Z","iopub.status.idle":"2024-01-13T02:50:52.450602Z","shell.execute_reply.started":"2024-01-13T02:49:22.91451Z","shell.execute_reply":"2024-01-13T02:50:52.449246Z"}}},{"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[:10_000]):\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":"2024-01-22T04:54:25.646891Z","iopub.execute_input":"2024-01-22T04:54:25.648102Z","iopub.status.idle":"2024-01-22T04:55:52.077497Z","shell.execute_reply.started":"2024-01-22T04:54:25.648064Z","shell.execute_reply":"2024-01-22T04:55:52.076407Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls -l","metadata":{"execution":{"iopub.status.busy":"2024-01-22T04:55:52.079858Z","iopub.execute_input":"2024-01-22T04:55:52.080155Z","iopub.status.idle":"2024-01-22T04:55:53.408382Z","shell.execute_reply.started":"2024-01-22T04:55:52.080121Z","shell.execute_reply":"2024-01-22T04:55:53.407396Z"},"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":"2024-01-22T05:00:57.379043Z","iopub.execute_input":"2024-01-22T05:00:57.380018Z","iopub.status.idle":"2024-01-22T05:01:53.403777Z","shell.execute_reply.started":"2024-01-22T05:00:57.37998Z","shell.execute_reply":"2024-01-22T05:01:53.402898Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(photos.shape, labels.shape)","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:01:53.406317Z","iopub.execute_input":"2024-01-22T05:01:53.407118Z","iopub.status.idle":"2024-01-22T05:01:53.412027Z","shell.execute_reply.started":"2024-01-22T05:01:53.407076Z","shell.execute_reply":"2024-01-22T05:01:53.410963Z"},"trusted":true},"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":"2024-01-22T05:01:53.413063Z","iopub.execute_input":"2024-01-22T05:01:53.413302Z","iopub.status.idle":"2024-01-22T05:01:53.426393Z","shell.execute_reply.started":"2024-01-22T05:01:53.41328Z","shell.execute_reply":"2024-01-22T05:01:53.425428Z"},"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":"2024-01-22T05:01:53.428501Z","iopub.execute_input":"2024-01-22T05:01:53.42881Z","iopub.status.idle":"2024-01-22T05:02:08.485252Z","shell.execute_reply.started":"2024-01-22T05:01:53.42878Z","shell.execute_reply":"2024-01-22T05:02:08.484432Z"},"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":"2024-01-22T05:02:08.486348Z","iopub.execute_input":"2024-01-22T05:02:08.4866Z","iopub.status.idle":"2024-01-22T05:02:09.672045Z","shell.execute_reply.started":"2024-01-22T05:02:08.486577Z","shell.execute_reply":"2024-01-22T05:02:09.671095Z"},"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":"2024-01-22T05:02:09.673372Z","iopub.execute_input":"2024-01-22T05:02:09.673675Z","iopub.status.idle":"2024-01-22T05:02:10.757425Z","shell.execute_reply.started":"2024-01-22T05:02:09.673645Z","shell.execute_reply":"2024-01-22T05:02:10.756291Z"},"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":"2024-01-22T05:02:10.759194Z","iopub.execute_input":"2024-01-22T05:02:10.760073Z","iopub.status.idle":"2024-01-22T05:02:18.931224Z","shell.execute_reply.started":"2024-01-22T05:02:10.760031Z","shell.execute_reply":"2024-01-22T05:02:18.930191Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install livelossplot -q","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:02:18.932424Z","iopub.execute_input":"2024-01-22T05:02:18.932975Z","iopub.status.idle":"2024-01-22T05:02:33.033275Z","shell.execute_reply.started":"2024-01-22T05:02:18.932945Z","shell.execute_reply":"2024-01-22T05:02:33.031868Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from livelossplot import PlotLossesKeras","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:02:33.034964Z","iopub.execute_input":"2024-01-22T05:02:33.035329Z","iopub.status.idle":"2024-01-22T05:02:33.051269Z","shell.execute_reply.started":"2024-01-22T05:02:33.035297Z","shell.execute_reply":"2024-01-22T05:02:33.050301Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# vgg16 model used for transfer learning on the dogs and cats dataset\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():\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\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(featurewise_center=True)\n\t# specify imagenet mean values for centering\n\tdatagen.mean = [123.68, 116.779, 103.939]\n\t# prepare iterator\n\ttrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n\t\tclass_mode='binary', batch_size=64, target_size=(224, 224))\n\ttest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n\t\tclass_mode='binary', batch_size=64, target_size=(224, 224))\n\t# fit model\n\thistory = model.fit(train_it, \n                        steps_per_epoch=len(train_it),\n                        validation_data=test_it, \n                        validation_steps=len(test_it), \n                        epochs=30, verbose=1,\n                        callbacks=[PlotLossesKeras()]\n                       )\n\t# evaluate model\n\t_, acc = model.evaluate_generator(test_it, steps=len(test_it), verbose=1)\n\tprint('> %.3f' % (acc * 100.0))\n\t# learning curves\n\tsummarize_diagnostics(history)\n\n# entry point, run the test harness\n#run_test_harness()","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:02:33.055098Z","iopub.execute_input":"2024-01-22T05:02:33.055481Z","iopub.status.idle":"2024-01-22T05:02:33.070685Z","shell.execute_reply.started":"2024-01-22T05:02:33.055436Z","shell.execute_reply":"2024-01-22T05:02:33.069776Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = define_model()","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:02:33.072167Z","iopub.execute_input":"2024-01-22T05:02:33.072542Z","iopub.status.idle":"2024-01-22T05:02:34.976062Z","shell.execute_reply.started":"2024-01-22T05:02:33.072508Z","shell.execute_reply":"2024-01-22T05:02:34.975062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.summary()\n","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:02:34.977362Z","iopub.execute_input":"2024-01-22T05:02:34.977742Z","iopub.status.idle":"2024-01-22T05:02:35.026305Z","shell.execute_reply.started":"2024-01-22T05:02:34.97769Z","shell.execute_reply":"2024-01-22T05:02:35.025451Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"run_test_harness()","metadata":{"execution":{"iopub.status.busy":"2024-01-22T05:43:32.980981Z","iopub.execute_input":"2024-01-22T05:43:32.981302Z"},"trusted":true},"execution_count":null,"outputs":[]}]}