{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"# Owner: Shelly Leal\n# Inspirations:\n#https://www.analyticsvidhya.com/blog/2021/06/beginner-friendly-project-cat-and-dog-classification-using-cnn/\n#https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-to-classify-photos-of-dogs-and-cats/\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\ntrain_directory = '../input/d/biaiscience/dogs-vs-cats/train/train/'\ntest_directory = '../input/d/biaiscience/dogs-vs-cats/test/test/'\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":"2022-08-23T21:33:44.636492Z","iopub.execute_input":"2022-08-23T21:33:44.637408Z","iopub.status.idle":"2022-08-23T21:33:44.663468Z","shell.execute_reply.started":"2022-08-23T21:33:44.636847Z","shell.execute_reply":"2022-08-23T21:33:44.662521Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#import os\n#import glob\n\n#files = glob.glob('../train/dogs/*')\n#for f in files:\n#    os.remove(f)\n#os.rmdir('../train/dogs/')","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:33:44.665496Z","iopub.execute_input":"2022-08-23T21:33:44.665873Z","iopub.status.idle":"2022-08-23T21:33:44.669974Z","shell.execute_reply.started":"2022-08-23T21:33:44.66584Z","shell.execute_reply":"2022-08-23T21:33:44.668952Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from distutils.dir_util import copy_tree\ncopy_tree(train_directory, \"train/\")","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:33:44.671391Z","iopub.execute_input":"2022-08-23T21:33:44.672695Z","iopub.status.idle":"2022-08-23T21:37:17.479438Z","shell.execute_reply.started":"2022-08-23T21:33:44.672658Z","shell.execute_reply":"2022-08-23T21:37:17.478471Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"copy_tree(test_directory, \"test/\")","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:37:17.481782Z","iopub.execute_input":"2022-08-23T21:37:17.482376Z","iopub.status.idle":"2022-08-23T21:39:08.91131Z","shell.execute_reply.started":"2022-08-23T21:37:17.482337Z","shell.execute_reply":"2022-08-23T21:39:08.909943Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from matplotlib import pyplot\nfrom matplotlib.image import imread\n# location of dataset in your diretory\nfolder = 'train/'\n# plot images\nfor i in range(3):\n    #subplot\n    pyplot.subplot(330 + 1 + i)\n    #filename - either is .cat or .dog\n    filename = folder + 'dog.' + str(i) + '.jpg'\n    # image pixels\n    image = imread(filename)\n    #raw pixel data\n    pyplot.imshow(image)\n    # show the figure\n    pyplot.show()\n    ","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:39:08.913447Z","iopub.execute_input":"2022-08-23T21:39:08.914234Z","iopub.status.idle":"2022-08-23T21:39:09.425259Z","shell.execute_reply.started":"2022-08-23T21:39:08.914189Z","shell.execute_reply":"2022-08-23T21:39:09.424049Z"},"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    # 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# 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    src = src_directory + '/' + file\n    dst_dir = 'train/'\n    if random() < val_ratio:\n        dst_dir = 'test/'\n    if file.startswith('cat'):\n        dst = dataset_home + dst_dir + 'cats/'  + file\n        copyfile(src, dst)\n    elif file.startswith('dog'):\n        dst = dataset_home + dst_dir + 'dogs/'  + file\n        copyfile(src, dst)","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:39:09.427068Z","iopub.execute_input":"2022-08-23T21:39:09.427397Z","iopub.status.idle":"2022-08-23T21:39:11.891968Z","shell.execute_reply.started":"2022-08-23T21:39:09.427363Z","shell.execute_reply":"2022-08-23T21:39:11.890991Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tensorflow.keras.optimizers import SGD\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Flatten\nfrom keras.layers import Dense\nfrom keras.layers import Dropout\n\n# define cnn model\ndef define_model():\n    model = Sequential()\n    model = Sequential()\n    model.add(Conv2D(32, (3, 3), activation='relu', kernel_initializer='he_uniform', padding='same', input_shape=(200, 200, 3)))\n    model.add(MaxPooling2D((2, 2)))\n    model.add(Flatten())\n    model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))\n    model.add(Dense(1, activation='sigmoid'))\n    # compile model\n    opt = SGD(learning_rate=0.001, momentum=0.9)\n    model.compile(optimizer=opt, loss='binary_crossentropy', metrics=['accuracy'])\n    return model","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:41:31.341597Z","iopub.execute_input":"2022-08-23T21:41:31.342628Z","iopub.status.idle":"2022-08-23T21:41:31.351769Z","shell.execute_reply.started":"2022-08-23T21:41:31.342581Z","shell.execute_reply":"2022-08-23T21:41:31.350396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = define_model()","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:41:37.621811Z","iopub.execute_input":"2022-08-23T21:41:37.622435Z","iopub.status.idle":"2022-08-23T21:41:37.664324Z","shell.execute_reply.started":"2022-08-23T21:41:37.622381Z","shell.execute_reply":"2022-08-23T21:41:37.663448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# create data generator\nfrom keras.preprocessing.image import ImageDataGenerator\ndatagen = ImageDataGenerator(rescale=1.0/255.0)","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:41:40.310746Z","iopub.execute_input":"2022-08-23T21:41:40.31111Z","iopub.status.idle":"2022-08-23T21:41:40.316967Z","shell.execute_reply.started":"2022-08-23T21:41:40.31108Z","shell.execute_reply":"2022-08-23T21:41:40.315577Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# prepare iterators\ntrain_it = datagen.flow_from_directory('dataset_dogs_vs_cats/train/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))\ntest_it = datagen.flow_from_directory('dataset_dogs_vs_cats/test/',\n    class_mode='binary', batch_size=64, target_size=(200, 200))","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:41:49.862248Z","iopub.execute_input":"2022-08-23T21:41:49.863366Z","iopub.status.idle":"2022-08-23T21:41:50.940326Z","shell.execute_reply.started":"2022-08-23T21:41:49.863327Z","shell.execute_reply":"2022-08-23T21:41:50.939432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# fit model\nhistory = model.fit(train_it, steps_per_epoch=len(train_it),\n    validation_data=test_it, validation_steps=len(test_it), epochs=20, verbose=0)","metadata":{"execution":{"iopub.status.busy":"2022-08-23T21:41:50.941944Z","iopub.execute_input":"2022-08-23T21:41:50.942225Z","iopub.status.idle":"2022-08-23T22:06:50.635723Z","shell.execute_reply.started":"2022-08-23T21:41:50.9422Z","shell.execute_reply":"2022-08-23T22:06:50.634701Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# evaluate model\n_, acc = model.evaluate(test_it, steps=len(test_it), verbose=0)\nprint('> %.3f' % (acc * 100.0),'%')","metadata":{"execution":{"iopub.status.busy":"2022-08-23T22:09:26.770131Z","iopub.execute_input":"2022-08-23T22:09:26.770529Z","iopub.status.idle":"2022-08-23T22:09:46.199125Z","shell.execute_reply.started":"2022-08-23T22:09:26.770491Z","shell.execute_reply":"2022-08-23T22:09:46.198095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import os\nos.listdir('dataset_dogs_vs_cats/test/cats')","metadata":{"execution":{"iopub.status.busy":"2022-08-23T22:20:29.073441Z","iopub.execute_input":"2022-08-23T22:20:29.074463Z","iopub.status.idle":"2022-08-23T22:20:29.09871Z","shell.execute_reply.started":"2022-08-23T22:20:29.074394Z","shell.execute_reply":"2022-08-23T22:20:29.097842Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import load_img\nfrom keras.preprocessing.image import img_to_array\n# load and prepare the image\nimg = load_img('dataset_dogs_vs_cats/test/dogs/dog.2163.jpg', target_size=(200, 200))\nimg = img_to_array(img)\nimg = img.reshape(1, 200, 200, 3)\nimg = img.astype('float32')\nimg = img - [123.68, 116.779, 103.939]\nresult = model.predict(img)\nresult","metadata":{"execution":{"iopub.status.busy":"2022-08-23T22:21:13.02474Z","iopub.execute_input":"2022-08-23T22:21:13.025205Z","iopub.status.idle":"2022-08-23T22:21:13.081283Z","shell.execute_reply.started":"2022-08-23T22:21:13.025161Z","shell.execute_reply":"2022-08-23T22:21:13.080316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"img = load_img('dataset_dogs_vs_cats/test/cats/cat.6428.jpg', target_size=(200, 200))\nimg = img_to_array(img)\nimg = img.reshape(1, 200, 200, 3)\nimg = img.astype('float32')\nimg = img - [123.68, 116.779, 103.939]\nresult = model.predict(img)\nresult","metadata":{"execution":{"iopub.status.busy":"2022-08-23T22:21:18.973934Z","iopub.execute_input":"2022-08-23T22:21:18.97429Z","iopub.status.idle":"2022-08-23T22:21:19.030629Z","shell.execute_reply.started":"2022-08-23T22:21:18.97426Z","shell.execute_reply":"2022-08-23T22:21:19.029632Z"},"trusted":true},"execution_count":null,"outputs":[]}]}