{"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%matplotlib inline\nimport matplotlib.pyplot as plt\nimport cv2\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":1,"outputs":[{"output_type":"stream","text":"['test', 'labels.csv', 'sample_submission.csv', 'train']\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"%ls '../input/'\nlabels=pd.read_csv('../input/labels.csv')\ntest=pd.read_csv('../input/sample_submission.csv')","execution_count":2,"outputs":[{"output_type":"stream","text":"labels.csv  sample_submission.csv  \u001b[0m\u001b[01;34mtest\u001b[0m/  \u001b[01;34mtrain\u001b[0m/\r\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"path=labels['id']\ntarget1=labels['breed']\ntestpath=test['id']","execution_count":3,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"target=target1.append(target1)\ntarget=target.append(target)","execution_count":4,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import load_img,img_to_array\nimage_train1=[]\nfor x in path:\n    y=cv2.imread('../input/train/'+x+'.jpg')\n    y=cv2.resize(y,(32,32))\n    y=cv2.GaussianBlur(y,(5,5),0)\n    y=cv2.cvtColor(y, cv2.COLOR_RGB2GRAY)\n    image_train1.append(img_to_array(y))","execution_count":5,"outputs":[{"output_type":"stream","text":"Using TensorFlow backend.\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_test=[]\nfor x in testpath:\n    y=cv2.imread('../input/test/'+x+'.jpg')\n    y=cv2.resize(y,(32,32))\n    y=cv2.GaussianBlur(y,(5,5),0)\n    y=cv2.cvtColor(y, cv2.COLOR_RGB2GRAY)\n    image_test.append(img_to_array(y))","execution_count":6,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_train=np.array(image_train1)\nimage_test=np.array(image_test)","execution_count":7,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_train.shape","execution_count":8,"outputs":[{"output_type":"execute_result","execution_count":8,"data":{"text/plain":"(10222, 32, 32, 1)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_train=np.append(image_train,image_train,0)\nimage_train=np.append(image_train,image_train,0)","execution_count":9,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_train.shape","execution_count":10,"outputs":[{"output_type":"execute_result","execution_count":10,"data":{"text/plain":"(40888, 32, 32, 1)"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"target_all=pd.get_dummies(target,sparse=True)\ntarget=np.asarray(target_all)","execution_count":11,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.layers import Dense,Dropout,Flatten,Conv2D,MaxPool2D,AvgPool2D\nfrom sklearn.model_selection import train_test_split as tts\nxtrain,xtest,ztrain,ztest=tts(image_train,target,train_size=0.8)","execution_count":12,"outputs":[{"output_type":"stream","text":"/opt/conda/lib/python3.6/site-packages/sklearn/model_selection/_split.py:2179: FutureWarning: From version 0.21, test_size will always complement train_size unless both are specified.\n  FutureWarning)\n","name":"stderr"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import MaxPool2D,AvgPool2D\nmodel=Sequential()\nmodel.add(Conv2D(filters=64,kernel_size=(3,3),activation='tanh',input_shape=(32,32,1)))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.05))\nmodel.add(Conv2D(filters=32,kernel_size=(3,3),activation='relu',input_shape=(30,30,1)))\nmodel.add(MaxPool2D(pool_size=(2,2)))\nmodel.add(Dropout(0.05))\nmodel.add(Flatten())\nmodel.add(Dense(500, activation = \"sigmoid\"))\nmodel.add(Dropout(0.05))\nmodel.add(Dense(250, activation = \"relu\"))\nmodel.add(Dropout(0.05))\nmodel.add(Dense(120, activation = \"softmax\"))\nfrom keras.preprocessing.image import ImageDataGenerator\ndata=ImageDataGenerator(height_shift_range=0.1,width_shift_range=0.1,rotation_range=0.1,zoom_range=0.1)","execution_count":15,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='categorical_crossentropy',optimizer='rmsprop',metrics=['accuracy'])","execution_count":16,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history=model.fit_generator(data.flow(xtrain,ztrain,batch_size=1000),steps_per_epoch=1000,epochs=10,\n                            validation_data=[xtest,ztest])","execution_count":17,"outputs":[{"output_type":"stream","text":"WARNING:tensorflow:From /opt/conda/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.\nInstructions for updating:\nUse tf.cast instead.\nEpoch 1/10\n1000/1000 [==============================] - 210s 210ms/step - loss: 3.7750 - acc: 0.1553 - val_loss: 2.5305 - val_acc: 0.4233\nEpoch 2/10\n1000/1000 [==============================] - 197s 197ms/step - loss: 2.2453 - acc: 0.4536 - val_loss: 1.1243 - val_acc: 0.7600\nEpoch 3/10\n1000/1000 [==============================] - 195s 195ms/step - loss: 1.4418 - acc: 0.6290 - val_loss: 0.5186 - val_acc: 0.8981\nEpoch 4/10\n1000/1000 [==============================] - 194s 194ms/step - loss: 1.0619 - acc: 0.7164 - val_loss: 0.3194 - val_acc: 0.9397\nEpoch 5/10\n1000/1000 [==============================] - 192s 192ms/step - loss: 0.8572 - acc: 0.7663 - val_loss: 0.2111 - val_acc: 0.9634\nEpoch 6/10\n1000/1000 [==============================] - 196s 196ms/step - loss: 0.7295 - acc: 0.7977 - val_loss: 0.1623 - val_acc: 0.9713\nEpoch 7/10\n1000/1000 [==============================] - 194s 194ms/step - loss: 0.6436 - acc: 0.8193 - val_loss: 0.1508 - val_acc: 0.9729\nEpoch 8/10\n1000/1000 [==============================] - 193s 193ms/step - loss: 0.5842 - acc: 0.8346 - val_loss: 0.1484 - val_acc: 0.9738\nEpoch 9/10\n1000/1000 [==============================] - 194s 194ms/step - loss: 0.5371 - acc: 0.8464 - val_loss: 0.0928 - val_acc: 0.9883\nEpoch 10/10\n1000/1000 [==============================] - 192s 192ms/step - loss: 0.5019 - acc: 0.8563 - val_loss: 0.1018 - val_acc: 0.9831\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(history.history['acc'])\nplt.plot(history.history['val_acc'])\nplt.show()","execution_count":19,"outputs":[{"output_type":"display_data","data":{"text/plain":"<Figure size 432x288 with 1 Axes>","image/png":"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\n"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"result=model.predict(image_test)\nresult_data=pd.DataFrame(result,columns=target_all.columns.values,index=testpath)","execution_count":21,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_data.to_csv('result_improved_3.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"result_data","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}