{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"dataset=pd.read_csv(\"../input/labels.csv\")\ndataset_test=pd.read_csv(\"../input/sample_submission.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f4616cf76cd88c036d3652f52696e04000533739"},"cell_type":"code","source":"target=pd.Series(dataset['breed'])\none_hot=pd.get_dummies(target,sparse=True)\ntarget=np.asarray(one_hot)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"bfac79f6bc6ffa45706b9200b07ac6916626bbe3"},"cell_type":"code","source":"im_size= 64#----> image size\nids = dataset['id']\nx_train =[]\ny_train = target","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ec1fa2a24ee1c74f261b3791d7ac52e6f8aa672b"},"cell_type":"code","source":"import cv2\nfor id in ids:\n    img = cv2.imread('../input/train/{}'.format(id)+'.jpg')\n    if img is not None:\n        \n        \n        img = cv2.resize(img, (64,64))\n        x_train.append(img)\n        \n    else:\n        print(\"image not loaded {}\".format(id))\nx_train=np.array(x_train,np.float32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"81389486acd180b92d2af438921f0725852ceea0"},"cell_type":"code","source":"x_test = list()\nids_test = dataset_test['id']\nfor id in ids_test:\n    img = cv2.imread('../input/test/{}'.format(id)+'.jpg')\n    x_test.append(cv2.resize(img,(64,64)))\nx_test = np.array(x_test,np.float32)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2812950cf55940eabaedc194f368c50dde7faa2d"},"cell_type":"code","source":"def standardize(array):\n    array/=255\n    return array\nx_train = standardize(x_train)\nx_test = standardize(x_test)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"2bb4b5ebdc78936046e0e44bdc9eeaedc1c944f8"},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D\nfrom keras.layers import MaxPooling2D\nfrom keras.layers import Flatten\nfrom keras.layers import Dense\n\n# Initialising the CNN\nclassifier = Sequential()\n\n# Step 1 - Convolution\nclassifier.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))\n\n# Step 2 - Pooling\nclassifier.add(MaxPooling2D(pool_size = (2, 2)))\n\n# Adding a second convolutional layer\nclassifier.add(Conv2D(32, (3, 3), activation = 'relu'))\nclassifier.add(MaxPooling2D(pool_size = (2, 2)))\n\n# Adding a third convolutional layer\nclassifier.add(Conv2D(32, (3, 3), activation = 'relu'))\nclassifier.add(MaxPooling2D(pool_size = (2, 2)))\n\n# Step 3 - Flattening\nclassifier.add(Flatten())\n\n# Step 4 - Full connection\nclassifier.add(Dense(units = 128, activation = 'relu'))\nclassifier.add(Dense(units = 120, activation = 'softmax'))\n\n# Compiling the CNN\nclassifier.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"scrolled":true,"_uuid":"87fc9237ebda3c6741f148baa58f7f9ee93dd0e3"},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\ndatagen = ImageDataGenerator(\n    featurewise_center=True,\n    featurewise_std_normalization=True,\n    rotation_range=20,\n    width_shift_range=0.2,\n    height_shift_range=0.2,\n    horizontal_flip=True)\n\n# compute quantities required for featurewise normalization\n# (std, mean, and principal components if ZCA whitening is applied)\ndatagen.fit(x_train)\n\n# fits the model on batches with real-time data augmentation:\nclassifier.fit_generator(datagen.flow(x_train, y_train, batch_size=32),\n                    steps_per_epoch=len(x_train) / 32, epochs=20)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"d2a4e14c2dfcc1ddfb1b09089be83855a9f4344a"},"cell_type":"code","source":"test_predictions=classifier.predict(x_test,batch_size=32,verbose=1)\ndog_species=dataset_test.columns[1:]\nsubmission_rishi=pd.DataFrame(data=test_predictions,index=ids_test,columns=dog_species)\nsubmission_rishi.index.name='id'\nsubmission_rishi.to_csv('submission_rishi.csv',encoding='utf-8',index=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"60106f4ae0512cfa17d4ae3564731678736340de"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}