{"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)\n\n\nimport pickle \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        \ndef savepickle(obj,name):\n    with open(name+'.pkl','wb') as k:\n        pickle.dump(obj,k)\n\n\n# You can write up to 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense,Dropout,Activation,Conv2D,MaxPooling2D,Flatten\nfrom tensorflow.keras.callbacks import TensorBoard\nimport matplotlib.pyplot as plt\nimport kerastuner as kt\nimport cv2\nimport numpy as np\nimport zipfile \nimport datetime, os\nimport time\nos.getcwd()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir('../input'))\n\nwith zipfile.ZipFile(\"../input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")\n\nwith zipfile.ZipFile(\"../input/dogs-vs-cats/test1.zip\",\"r\") as z:\n    z.extractall(\".\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"main_dir = \"/kaggle/working/\"\ntrain_dir = \"train\"\npath = os.path.join(main_dir,train_dir)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = []\ny = []\nconvert = lambda category : int(category == 'dog')\ndef create_test_data(path):\n    for p in os.listdir(path):\n        category = p.split(\".\")[0]\n        category = convert(category)\n        img_array = cv2.imread(os.path.join(path,p),cv2.IMREAD_GRAYSCALE)\n        new_img_array = cv2.resize(img_array, dsize=(80, 80))\n        X.append(new_img_array)\n        y.append(category)\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"create_test_data(path)\nX = np.array(X).reshape(-1, 80,80,1)\ny = np.array(y)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X/255\nX=X[:128]\ny=y[:128]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"        \n\ndef bui_mod(hp):\n    NAME=\"cats_vs_dogs_{}\".format(int(time.time()))\n    tensorboard=TensorBoard(log_dir='logs\\{}'.format(NAME))\n\n    model=Sequential()                                              ######Start creating the model \n    model.add(Conv2D(hp.Int('Filter_per_conv',64,256,64),(3,3),input_shape=X.shape[1:],padding='same'))      #####Conv2D network\n    model.add(Activation('relu'))\n    model.add(MaxPooling2D(pool_size=(2,2)))\n\n    for covs in range(hp.Int('num_of_layers',1,4,1)):\n        model.add(Conv2D(hp.Int('Filter_per_conv',64,256,64),(3,3),padding='same'))  #####Conv2D network\n        model.add(Activation('relu'))\n        model.add(MaxPooling2D(pool_size=(2,2)))\n        model.add(Dropout(hp.Choice('Dropout Prob',values=[0.05,0.08,0.1,0.13,0.16,0.20])))\n\n    model.add(Flatten())\n\n    for lays in range(hp.Int('Dense_layers_number',0,2,1)):                \n        model.add(Dense(hp.Int('Dense_layer_size',64,256,64)))\n        model.add(Activation('relu'))\n        model.add(Dropout(hp.Choice('Dropout Prob',values=[0.05,0.08,0.1,0.13,0.16,0.20])))\n\n    model.add(Dense(1))\n    model.add(Activation('sigmoid'))\n\n    ###########################################\n    ###############  Model Compilation  #######\n\n    model.compile(loss='binary_crossentropy',\n                  optimizer='adam',\n                  metrics=['accuracy'])\n    return model \n\n\n        \ntuner = kt.RandomSearch(bui_mod,\n                     objective=\"val_accuracy\",\n                     max_trials=1,\n                     executions_per_trial=1,\n                     directory='keras_testing' \n                    )\n\nprint('1')\ntuner.search(x=X,\n             y=y,\n             epochs=1,\n             batch_size=64,\n             validation_split=0.15)\n\nprint('2')\nprint(tuner.results_summary())\n\nprint('3')\nmodels = tuner.get_best_models(num_models=1)[0]\nprint('4')\n\ntrain_dir = \"test1\"\npath = os.path.join(main_dir,train_dir)\n#os.listdir(path)\nprint('5')\nX_test = []\nprint('6')\nid_line = []\ndef create_test1_data(path):\n    for p in os.listdir(path):\n        id_line.append(p.split(\".\")[0])\n        img_array = cv2.imread(os.path.join(path,p),cv2.IMREAD_GRAYSCALE)\n        new_img_array = cv2.resize(img_array, dsize=(80, 80))\n        X_test.append(new_img_array)\ncreate_test1_data(path)\nX_test = np.array(X_test).reshape(-1,80,80,1)\nX_test = X_test/255\n\n\n\npredictions = models.predict(X_test)\n\npredicted_val = [int(round(p[0])) for p in predictions]\n\nsubmission_df = pd.DataFrame({'id':id_line, 'label':predicted_val})\n\nsavepickle(submission_df,'submissionspickle')\n\nsubmission_df.to_csv(\"./submission.csv\", index=False)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}