{"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# 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 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":"#from tensorflow.python.keras.applications import ResNet50\nfrom tensorflow.python.keras.models import Sequential\nfrom tensorflow.python.keras.layers import Dense, Flatten, GlobalAveragePooling2D, Activation, Flatten, Dropout, BatchNormalization\n\nimport h5py\nimport numpy as np\nimport pandas as pd\nimport numpy as np\nimport seaborn as sns\nimport matplotlib\nimport os\nfrom shutil import copyfile\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport os\nfrom keras.models import Model, Sequential\nfrom keras.layers import Input, Flatten, Dense, Conv2D, MaxPooling2D, Dropout\nfrom keras.utils import layer_utils\nfrom keras import backend as K\nfrom keras.optimizers import RMSprop, SGD, Adam\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint, TensorBoard, CSVLogger\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import log_loss, accuracy_score\nfrom keras.preprocessing import image\nfrom keras.applications.vgg16 import VGG16\nfrom keras.applications.resnet50 import ResNet50\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Convolution2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Flatten\nfrom keras.layers import Dense\nfrom keras.layers import Conv2D,Dropout\nfrom keras.preprocessing.image import ImageDataGenerator\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport os\nfrom keras.models import Model, Sequential\nfrom keras.layers import Input, Flatten, Dense, Conv2D, MaxPooling2D, Dropout\nfrom keras.utils import layer_utils\nfrom keras import backend as K\nfrom keras.optimizers import RMSprop, SGD, Adam\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint, TensorBoard, CSVLogger\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import log_loss, accuracy_score\nfrom keras.preprocessing import image\nfrom keras.applications.vgg16 import VGG16\nfrom keras.applications.resnet50 import ResNet50\nfrom keras.applications import xception\nfrom keras.applications import inception_v3\nfrom keras.applications.vgg16 import preprocess_input, decode_predictions\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications import xception\nfrom keras.applications import inception_v3\nfrom keras.applications.vgg16 import preprocess_input, decode_predictions\nfrom keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.applications.resnet50 import preprocess_input\nfrom tensorflow.python.keras.preprocessing.image import ImageDataGenerator\n\nimage_size = 224\ndatagen = ImageDataGenerator(preprocessing_function=preprocess_input, \n                             rescale=1./255.,\n                             horizontal_flip=True,\n                             width_shift_range = 0.2,\n                             height_shift_range = 0.2,\n                             validation_split=0.2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = pd.read_csv('/kaggle/input/dog-breed-identification/labels.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels_dict = {i:j for i,j in zip(labels['id'],labels['breed'])}\nclasses = set(labels_dict.values())\nimages = [f for f in os.listdir('/kaggle/input/dog-breed-identification/train')]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if  not os.path.exists('/kaggle/training_images'):\n        os.makedirs('/kaggle/training_images')\n\nif  not os.path.exists('/kaggle/validation_images'):\n    os.makedirs('/kaggle/validation_images')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nos.chdir('/kaggle/training_images')\nfor curClass in classes:    \n    if  not os.path.exists(curClass):\n        os.makedirs(curClass)\n        #os.rmdir(curClass)\n\nos.chdir('../validation_images')\nfor curClass in classes:    \n    if  not os.path.exists(curClass):\n        os.makedirs(curClass)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.chdir('..')\ncount = 0 \ndestination_directory = 'training_images/'\nfor item in images:\n    if count >7999:\n        destination_directory = 'validation_images/'\n    filekey = os.path.splitext(item)[0]\n    if  not os.path.exists(destination_directory+labels_dict[filekey]+'/'+item):\n        copyfile('input/dog-breed-identification/train/'+item, destination_directory+labels_dict[filekey]+'/'+item)\n    print(labels_dict[filekey])\n    count +=1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n        rescale=1./255,\n        shear_range=0.2,\n        zoom_range=0.2,\n        horizontal_flip=True)\n\ntest_datagen = ImageDataGenerator(rescale=1./255)\n#check class_mode in keras documentation https://keras.io/preprocessing/image/\ntraining_set = train_datagen.flow_from_directory(\n        'training_images',\n        target_size=(224, 224),\n        batch_size=20,\n        class_mode='categorical')\n\ntest_set = test_datagen.flow_from_directory(\n        'validation_images',\n        target_size=(224, 224),\n        batch_size=22,\n        class_mode='categorical')\n\"\"\"\nhist=main_model.fit_generator(\n        training_set,\n        steps_per_epoch=400,\n        epochs=25,\n        validation_data=test_set,\n        validation_steps=101,callbacks=callbacks_list)\"\"\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def cnnmodel():\n    model = Sequential()\n    model.add(Conv2D(60, (5, 5), input_shape=(224, 224,1), activation='relu'))\n    model.add(Conv2D(60, (5, 5), activation='relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\n    \"\"\"\n    model.add(Conv2D(30, (3, 3), activation='relu'))\n    model.add(Conv2D(30, (3, 3), activation='relu'))\n    model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))\"\"\"\n    model.add(Flatten())\n    model.add(Dense(600, activation='relu'))\n    model.add(Dropout(0.5))\n    model.add(Dense(120, activation='softmax'))\n    model.compile(Adam(lr = 0.0001), loss='categorical_crossentropy', metrics=['accuracy'])\n    return  model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model=cnnmodel()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#model=cnnmodel()\nmodel.fit_generator(generator=training_set ,\n                    steps_per_epoch=200,\n                    validation_data=test_set,\n                    validation_steps=101,\n                    epochs=45)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import model_from_json\nmodel_json = model.to_json()\nwith open(\"./model.json\", \"w\") as json_file:\n    json_file.write(model_json)\nmodel.save_weights(\"model.h5\")\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'model.h5')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nfrom IPython.display import FileLink\nFileLink(r'./model.json')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls output\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"json_file = open('model.json', 'r')\nloaded_model_json = json_file.read()\njson_file.close()\nloaded_model = model_from_json(loaded_model_json)\n# load weights into new model\nloaded_model.load_weights(\"model.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport cv2\nimport pandas as pd\ntest_set = []\ntest_set_ids = []\nfor curImage in os.listdir('input/dog-breed-identification/test'):\n    test_set_ids.append(os.path.splitext(curImage)[0])\n    #print(os.path.splitext(curImage)[0])\n    curImage = cv2.imread('input/dog-breed-identification/test/'+curImage)\n    test_set.append(cv2.resize(curImage,(224, 224)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_set = np.array(test_set, np.float32)/255.0","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions=model.predict(test_set)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\ntraining_set.class_indices","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"classes= {index:breed for breed,index in training_set.class_indices.items()}\ncolumn_names = [classes[i] for i in range(120)]\ncolumn_names","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions_df = pd.DataFrame(predictions)\npredictions_df.columns = column_names\npredictions_df.insert(0,'id', test_set_ids)\n#predictions_df.index = test_set_ids\npredictions_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions_df.to_csv('submission.csv',sep=\",\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nimport os\nos.chdir(r'working')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions_df.to_csv(r'submission.csv',sep=\",\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from IPython.display import FileLink\nFileLink(r'submission.csv')","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}