{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"19721f9e-86be-994a-ceb5-f5801ae9f3f6"},"source":"### Try to play with Keras now"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"5236deed-d18a-bae9-91b3-bd2f2120f25e"},"outputs":[],"source":"%matplotlib inline\nfrom __future__ import division,print_function\nimport os, json\nfrom glob import glob\nimport numpy as np\nimport pandas as pd\nimport scipy\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.metrics import confusion_matrix\nnp.set_printoptions(precision=4, linewidth=100)\nfrom matplotlib import pyplot as plt\n\nfrom numpy.random import random, permutation\nfrom scipy import misc, ndimage\nfrom scipy.ndimage.interpolation import zoom\n\nimport keras\nfrom keras import backend as K\nfrom keras.utils.data_utils import get_file\nfrom keras.models import Sequential\nfrom keras.layers import Input\nfrom keras.layers.core import Flatten, Dense, Dropout, Lambda\nfrom keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D\nfrom keras.optimizers import SGD, RMSprop\nfrom keras.preprocessing import image"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"8e3027cb-e635-c0a8-ce6d-98f6de861461"},"outputs":[],"source":"TRAIN_DIR = '../input/train/'\nTEST_DIR = '../input/test/'\n\nx = random((30, 2))\n\n# y = a1x1 + a2x2 + b\ny = np.dot(x, [2., 3.]) + 1\ny"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"d2c9d30a-853e-ea78-7e98-768e25a7c728"},"outputs":[],"source":"lm = Sequential([Dense(1, input_shape=(2,))])\nlm.compile(optimizer=SGD(lr=0.1), loss='mse')"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"4cb39510-d14c-6fb5-1de0-9d29f919a4c0"},"outputs":[],"source":"lm.evaluate(x, y, verbose=1)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"2c834430-06da-6211-7c27-c1ec49d8df83"},"outputs":[],"source":"lm.fit(x, y, epochs=5, batch_size=1)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"a51262dd-e2b4-be8c-a109-b3a20e8e1189"},"outputs":[],"source":"lm.get_weights()"},{"cell_type":"markdown","metadata":{"_cell_guid":"6e0228ed-2cc7-b663-d5de-dcff748ce9a1"},"source":"###Now move onto real example"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"bb6d572c-1835-2d95-d090-c735a7956a9b"},"outputs":[],"source":"vgg = keras.applications.vgg16.VGG16(include_top=True, weights='imagenet', input_tensor=None, input_shape=None)\nvgg"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"58aea71a-c3d4-2461-934d-e8e33b2fc5a8"},"outputs":[],"source":""}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0}