{"cells":[{"metadata":{"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)\nimport cv2\nimport matplotlib.pyplot as plt\nimport tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Flatten, Dropout, Activation, Conv2D, MaxPooling2D\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","execution_count":21,"outputs":[{"output_type":"stream","text":"['train', 'sampleSubmission.csv', 'test1']\n","name":"stdout"}]},{"metadata":{"trusted":true},"cell_type":"code","source":"main_dir = \"../input/\"\ntrain_dir = \"train/train\"\npath = os.path.join(main_dir,train_dir)\n\nfor p in os.listdir(path):\n    category = 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    plt.imshow(new_img_array,cmap=\"gray\")\n    break","execution_count":22,"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":"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":23,"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)","execution_count":24,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X = X/255.0","execution_count":25,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n# Adds a densely-connected layer with 64 units to the model:\nmodel.add(Conv2D(64,(3,3), activation = 'relu', input_shape = X.shape[1:]))\nmodel.add(MaxPooling2D(pool_size = (2,2)))\n# Add another:\nmodel.add(Conv2D(64,(3,3), activation = 'relu'))\nmodel.add(MaxPooling2D(pool_size = (2,2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(64, activation='relu'))\n# Add a softmax layer with 10 output units:\nmodel.add(Dense(1, activation='sigmoid'))\n\nmodel.compile(optimizer=\"adam\",\n              loss='binary_crossentropy',\n              metrics=['accuracy'])","execution_count":26,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(X, y, epochs=10, batch_size=32, validation_split=0.2)\n","execution_count":27,"outputs":[{"output_type":"stream","text":"Train on 20000 samples, validate on 5000 samples\nWARNING: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\n20000/20000 [==============================] - 232s 12ms/sample - loss: 0.6410 - acc: 0.6261 - val_loss: 0.6201 - val_acc: 0.6686\nEpoch 2/10\n20000/20000 [==============================] - 231s 12ms/sample - loss: 0.5325 - acc: 0.7345 - val_loss: 0.5327 - val_acc: 0.7422\nEpoch 3/10\n20000/20000 [==============================] - 231s 12ms/sample - loss: 0.4505 - acc: 0.7918 - val_loss: 0.4653 - val_acc: 0.7770\nEpoch 4/10\n20000/20000 [==============================] - 231s 12ms/sample - loss: 0.3942 - acc: 0.8219 - val_loss: 0.4682 - val_acc: 0.7854\nEpoch 5/10\n20000/20000 [==============================] - 229s 11ms/sample - loss: 0.3331 - acc: 0.8525 - val_loss: 0.4690 - val_acc: 0.7906\nEpoch 6/10\n20000/20000 [==============================] - 232s 12ms/sample - loss: 0.2712 - acc: 0.8850 - val_loss: 0.4771 - val_acc: 0.7968\nEpoch 7/10\n20000/20000 [==============================] - 236s 12ms/sample - loss: 0.2085 - acc: 0.9150 - val_loss: 0.5289 - val_acc: 0.7920\nEpoch 8/10\n20000/20000 [==============================] - 235s 12ms/sample - loss: 0.1422 - acc: 0.9457 - val_loss: 0.6173 - val_acc: 0.7886\nEpoch 9/10\n20000/20000 [==============================] - 232s 12ms/sample - loss: 0.0925 - acc: 0.9669 - val_loss: 0.7330 - val_acc: 0.7836\nEpoch 10/10\n20000/20000 [==============================] - 231s 12ms/sample - loss: 0.0574 - acc: 0.9825 - val_loss: 0.8518 - val_acc: 0.7744\n","name":"stdout"},{"output_type":"execute_result","execution_count":27,"data":{"text/plain":"<tensorflow.python.keras.callbacks.History at 0x7fa97f3eb1d0>"},"metadata":{}}]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dir = \"test1/test1\"\npath = os.path.join(main_dir,train_dir)\n#os.listdir(path)\n\nX_test = []\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","execution_count":28,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = model.predict(X_test)\n","execution_count":29,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predicted_val = [int(round(p[0])) for p in predictions]\n","execution_count":30,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = pd.DataFrame({'id':id_line, 'label':predicted_val})\n","execution_count":31,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df.to_csv(\"submission.csv\", index=False)\n","execution_count":32,"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}