{"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":"# 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 matplotlib.pyplot as plt\n%matplotlib inline\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":{"execution":{"iopub.status.busy":"2021-09-10T08:55:50.572171Z","iopub.execute_input":"2021-09-10T08:55:50.572512Z","iopub.status.idle":"2021-09-10T08:56:39.832225Z","shell.execute_reply.started":"2021-09-10T08:55:50.572413Z","shell.execute_reply":"2021-09-10T08:56:39.823576Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df=pd.read_csv('../input/dog-breed-identification/labels.csv')\ndf.head(10)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:56:39.837577Z","iopub.execute_input":"2021-09-10T08:56:39.837898Z","iopub.status.idle":"2021-09-10T08:56:39.887517Z","shell.execute_reply.started":"2021-09-10T08:56:39.837864Z","shell.execute_reply":"2021-09-10T08:56:39.886580Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df.info()","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:56:39.889191Z","iopub.execute_input":"2021-09-10T08:56:39.889554Z","iopub.status.idle":"2021-09-10T08:56:39.908198Z","shell.execute_reply.started":"2021-09-10T08:56:39.889517Z","shell.execute_reply":"2021-09-10T08:56:39.907267Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data=df\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:56:39.909631Z","iopub.execute_input":"2021-09-10T08:56:39.909968Z","iopub.status.idle":"2021-09-10T08:56:39.920044Z","shell.execute_reply.started":"2021-09-10T08:56:39.909932Z","shell.execute_reply":"2021-09-10T08:56:39.918971Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"Y = pd.get_dummies(train_data['breed'])\nY.shape","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:56:39.921759Z","iopub.execute_input":"2021-09-10T08:56:39.922249Z","iopub.status.idle":"2021-09-10T08:56:39.936844Z","shell.execute_reply.started":"2021-09-10T08:56:39.922210Z","shell.execute_reply":"2021-09-10T08:56:39.935889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_file_location = '../input/dog-breed-identification/train/' \ntrain_data = df.assign(img_path = lambda x : train_file_location + x['id'] + '.jpg')\ntrain_data.head()\n\nfrom keras.preprocessing.image import load_img,img_to_array, ImageDataGenerator\nx = np.array([img_to_array(load_img(img,target_size = (128,128))) for img in train_data['img_path'].values.tolist()])\nprint(x.shape)\ny = pd.get_dummies(train_data['breed'])\nprint(y.shape)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:56:39.938411Z","iopub.execute_input":"2021-09-10T08:56:39.938801Z","iopub.status.idle":"2021-09-10T08:58:21.124134Z","shell.execute_reply.started":"2021-09-10T08:56:39.938765Z","shell.execute_reply":"2021-09-10T08:58:21.122302Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.model_selection import train_test_split\nx_train,x_val,y_train,y_val  = train_test_split(x,y,test_size = 0.25)\nprint(x_train.shape,y_train.shape)\nprint(x_val.shape,y_val.shape)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:21.127214Z","iopub.execute_input":"2021-09-10T08:58:21.127583Z","iopub.status.idle":"2021-09-10T08:58:22.397832Z","shell.execute_reply.started":"2021-09-10T08:58:21.127550Z","shell.execute_reply":"2021-09-10T08:58:22.396841Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense,Conv2D,MaxPool2D,Dropout,Flatten,Activation\nfrom keras.layers import BatchNormalization","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:22.399571Z","iopub.execute_input":"2021-09-10T08:58:22.400103Z","iopub.status.idle":"2021-09-10T08:58:22.404915Z","shell.execute_reply.started":"2021-09-10T08:58:22.400061Z","shell.execute_reply":"2021-09-10T08:58:22.404032Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.utils import normalize\nx_train = normalize(x_train)\nx_val = normalize(x_val)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:22.406110Z","iopub.execute_input":"2021-09-10T08:58:22.406609Z","iopub.status.idle":"2021-09-10T08:58:27.696637Z","shell.execute_reply.started":"2021-09-10T08:58:22.406572Z","shell.execute_reply":"2021-09-10T08:58:27.695513Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_datagen = ImageDataGenerator(shear_range = 0.2,\n                                   zoom_range = 0.2,\n                                   horizontal_flip = True)\ntrain_datagen.fit(x_train)\n\ntrain_generator = train_datagen.flow(x_train,y_train,batch_size = 32)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:27.698117Z","iopub.execute_input":"2021-09-10T08:58:27.698669Z","iopub.status.idle":"2021-09-10T08:58:28.284274Z","shell.execute_reply.started":"2021-09-10T08:58:27.698628Z","shell.execute_reply":"2021-09-10T08:58:28.283332Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\n\nmodel.add(Conv2D(64,(3,3),input_shape = (128,128,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(64,(3,3)))\nmodel.add(Activation('relu'))\n\nmodel.add(MaxPool2D(pool_size = (2,2)))\n\nmodel.add(Conv2D(64,(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(32,(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(32,(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(MaxPool2D(pool_size = (2,2)))\n\nmodel.add(Conv2D(32,(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(16,(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Conv2D(8,(3,3)))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Flatten())\n\nmodel.add(Dense(128))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Dense(100))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Dense(100))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Dense(100))\nmodel.add(Activation('relu'))\n\nmodel.add(Dropout(0.25))\n\nmodel.add(Dense(100))\nmodel.add(Activation('relu'))\n\nmodel.add(Dense(100))\nmodel.add(BatchNormalization())\nmodel.add(Activation('relu'))\n\nmodel.add(Dense(Y.shape[1]))\nmodel.add(Activation('softmax'))\n\nmodel.summary()","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:28.285589Z","iopub.execute_input":"2021-09-10T08:58:28.286045Z","iopub.status.idle":"2021-09-10T08:58:30.360162Z","shell.execute_reply.started":"2021-09-10T08:58:28.286007Z","shell.execute_reply":"2021-09-10T08:58:30.359156Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer='adam',\n             loss='categorical_crossentropy',\n             metrics=['accuracy'])","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:30.363189Z","iopub.execute_input":"2021-09-10T08:58:30.363460Z","iopub.status.idle":"2021-09-10T08:58:30.378545Z","shell.execute_reply.started":"2021-09-10T08:58:30.363434Z","shell.execute_reply":"2021-09-10T08:58:30.377711Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model_=model.fit_generator(train_generator,\n         validation_data=(x_val,y_val),\n         epochs=5,\n         verbose=2)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T08:58:30.379783Z","iopub.execute_input":"2021-09-10T08:58:30.380211Z","iopub.status.idle":"2021-09-10T09:00:57.794888Z","shell.execute_reply.started":"2021-09-10T08:58:30.380183Z","shell.execute_reply":"2021-09-10T09:00:57.793976Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_datagen = ImageDataGenerator ( \n    rescale=1./255\n)\n\ntest_set = test_datagen.flow_from_directory(\n    '/kaggle/input/dog-breed-identification',\n    target_size = (128,128),\n    batch_size = 128,\n    classes=['test']\n)\ny_pred = model.predict(test_set)","metadata":{"execution":{"iopub.status.busy":"2021-09-10T09:00:57.797925Z","iopub.execute_input":"2021-09-10T09:00:57.798205Z","iopub.status.idle":"2021-09-10T09:02:54.963871Z","shell.execute_reply.started":"2021-09-10T09:00:57.798177Z","shell.execute_reply":"2021-09-10T09:02:54.962902Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.read_csv('../input/dog-breed-identification/sample_submission.csv')\nsubmission.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-10T09:02:54.967360Z","iopub.execute_input":"2021-09-10T09:02:54.967676Z","iopub.status.idle":"2021-09-10T09:02:55.684948Z","shell.execute_reply.started":"2021-09-10T09:02:54.967647Z","shell.execute_reply":"2021-09-10T09:02:55.684076Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import re\nfile_list = test_set.filenames\nid_list = []\nfor name in file_list:\n    m = re.sub('test/', '', name)\n    m = re.sub('.jpg', '', m)\n    id_list.append(m)\n    \nsubmission['id'] = id_list\nsubmission.iloc[:,1:] =y_pred\nsubmission.head()","metadata":{"execution":{"iopub.status.busy":"2021-09-10T09:02:55.688699Z","iopub.execute_input":"2021-09-10T09:02:55.690684Z","iopub.status.idle":"2021-09-10T09:02:56.373653Z","shell.execute_reply.started":"2021-09-10T09:02:55.690646Z","shell.execute_reply":"2021-09-10T09:02:56.372541Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"final_df = submission.set_index('id')\nfinal_df.to_csv('submission.csv')","metadata":{"execution":{"iopub.status.busy":"2021-09-10T09:02:56.375999Z","iopub.execute_input":"2021-09-10T09:02:56.376321Z","iopub.status.idle":"2021-09-10T09:02:58.773924Z","shell.execute_reply.started":"2021-09-10T09:02:56.376290Z","shell.execute_reply":"2021-09-10T09:02:58.773061Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}