{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"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)\nimport zipfile\nfrom shutil import copyfile\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\n\nwith zipfile.ZipFile('../input/dogs-vs-cats/train.zip','r') as zip_ref:\n    zip_ref.extractall('./')\n    \n#with zipfile.ZipFile('../input/dogs-vs-cats/test1.zip','r') as zip_ref:\n#    zip_ref.extractall('./')\n\n\nimport keras,os\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, MaxPool2D , Flatten, Dropout, BatchNormalization\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport random\nfrom tqdm import tqdm\n\nprint(os.listdir())\n\nHOME = './'\nsubdirs = ['training/', 'testing/']\n\nfor subdir in subdirs:\n    labeldirs = ['dogs/', 'cats/']\n    for labeldir in labeldirs:\n        newdir = HOME + subdir + labeldir\n        os.makedirs(newdir, exist_ok = True)\n        \nSRC_PATH = './train/'\n\nrandom.seed(1)\nval_ratio = .1\nfor file in tqdm(os.listdir(SRC_PATH)):\n    src = SRC_PATH + file\n    \n    dest_dir = './training/'\n    if random.random() < val_ratio:\n        dest_dir = './testing/'\n    \n    if file.startswith('cat'):\n        dest = dest_dir + 'cats/' + file\n        copyfile(src, dest)\n    else:\n        dest = dest_dir + 'dogs/' + file\n        copyfile(src, dest)   \n        \n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\ndef plot_loss_history(history):     \n  hist = pd.DataFrame(history.history)\n  hist['epoch'] = history.epoch\n\n  plt.figure()\n  plt.xlabel('Epoch')\n  plt.ylabel('Loss')\n  plt.plot(hist['epoch'], hist['loss'],'r--',\n           label='Training Error')\n  plt.plot(hist['epoch'], hist['val_loss'],'b',\n           label = 'Validation Error')\n  plt.ylim([0,1])\n  plt.legend()\n  plt.show()\n    \ndef plot_acc_history(history):     \n  hist = pd.DataFrame(history.history)\n  hist['epoch'] = history.epoch\n\n  plt.figure()\n  plt.xlabel('Epoch')\n  plt.ylabel('Accuracy')\n  plt.plot(hist['epoch'], hist['accuracy'],'r--',\n           label='Training Error')\n  plt.plot(hist['epoch'], hist['val_accuracy'],'b',\n           label = 'Validation Error')\n  plt.ylim([0,1])\n  plt.legend()\n  plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_PATH = './training/'\nTEST_PATH = './testing'\n\n\n\n\n\ntraindata = ImageDataGenerator(rescale = 1./255,\n                                   shear_range = 0.2,\n                                   zoom_range = 0.2,\n                                   horizontal_flip = True)\n\ntestdata = ImageDataGenerator(rescale = 1./255)\n\ntraining_set = traindata.flow_from_directory(TRAIN_PATH,\n                                                target_size = (150, 150),\n                                                batch_size = 20,\n                                                class_mode = 'binary')\n\ntest_set = testdata.flow_from_directory(TEST_PATH,\n                                            target_size = (150, 150),\n                                            batch_size = 20,\n                                            class_mode = 'binary')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras,os\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, MaxPooling2D , Flatten, Dropout, BatchNormalization\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport random\nfrom tqdm import tqdm\n\nmodel = Sequential()\nmodel.add(Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(MaxPooling2D(2, 2))\nmodel.add(Conv2D(64, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(128, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(128, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dense(1, activation='sigmoid'))\n\n\n# compile model\nfrom keras.optimizers import SGD\nopt = SGD(lr=0.001, momentum=0.9)\nmodel.compile(\n    optimizer=opt,\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras,os\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, MaxPooling2D , Flatten, Dropout, BatchNormalization\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport random\nfrom tqdm import tqdm\n\nmodel = Sequential()\nmodel.add(Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(MaxPooling2D(2, 2))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(64, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(128, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Dropout(0.25))\nmodel.add(Conv2D(128, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Dropout(0.25))\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))\n\n\n# compile model\nfrom keras.optimizers import SGD\nopt = SGD(lr=0.001, momentum=0.9)\nmodel.compile(\n    optimizer=opt,\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n\n\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import keras,os\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Conv2D, MaxPooling2D , Flatten, Dropout, BatchNormalization\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport random\nfrom tqdm import tqdm\n\nmodel = Sequential()\nmodel.add(Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)))\nmodel.add(MaxPooling2D(2, 2))\nmodel.add(Conv2D(64, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(128, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Conv2D(128, (3,3), activation='relu'))\nmodel.add(MaxPooling2D(2,2))\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dense(1, activation='sigmoid'))\n\n\n# compile model\nfrom keras.optimizers import SGD\nopt = SGD(lr=0.001, momentum=0.9)\nmodel.compile(\n    optimizer=opt,\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.applications import VGG16\n\npre_trained_model = VGG16(input_shape = (150, 150, 3), \n                                include_top = False, \n                                weights = 'imagenet')\n\nfor layer in pre_trained_model.layers:\n  layer.trainable = False\n\n\npre_trained_model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras import Model\n\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense\n\nmodel = Sequential()\nmodel.add(pre_trained_model)\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))\n\nfrom keras.optimizers import SGD\nopt = SGD(lr=0.001, momentum=0.9)\nmodel.compile(\n    optimizer=opt,\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 20\n\n# Generator.n // batch_size \n\nsteps_per_epoch = training_set.n // batch_size\nvalidation_steps = test_set.n // batch_size\n\nprint(steps_per_epoch)\n# >> 1120\nprint(validation_steps)\n# >> 129\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\nhist = model.fit_generator(\n    steps_per_epoch=steps_per_epoch,\n    generator=training_set,\n    validation_data= test_set,\n    validation_steps=validation_steps,\n    epochs=80,\n)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nprint(hist.history.keys())\ndsfdf\n# >> dict_keys(['loss', 'accuracy', 'val_loss', 'val_accuracy'])\nplot_loss_history(hist)\nplot_acc_history(hist)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing import image\nimg = image.load_img('../input/kafkasample/kafkasample.png', target_size=(150, 150))\nx=image.img_to_array(img)\nimage=np.expand_dims(x, axis=0)  \n\nclasses = model.predict(image)\n\nplt.imshow(img)\nplt.show()\n\nif classes> 0:\n    print(\"Es un Perro\")\nelse:\n    print(\"Es un gato\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing import image\nimg = image.load_img('../input/othercat/149323.jpg', target_size=(150, 150))\nx=image.img_to_array(img)\nimage=np.expand_dims(x, axis=0)  \n\nclasses = model.predict(image)\n\nplt.imshow(img)\nplt.show()\n\nif classes> 0:\n    print(\"Es un Perro\")\nelse:\n    print(\"Es un gato\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing import image\nprint(os.listdir('./testing/dogs')[:25])\nimg = image.load_img('./testing/dogs/dog.1244.jpg', target_size=(150, 150))\nx=image.img_to_array(img)\nimage=np.expand_dims(x, axis=0)  \n\nclasses = model.predict(image)\nprint(classes[0])\nplt.imshow(img)\nplt.show()\n\nif classes == 1:\n    print(\"Es un Perro\")\nelif classes == 0:\n    print(\"Es un gato\")\nelse:\n    print(\"No tngo idea\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"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":4,"nbformat_minor":4}