{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport glob\nfrom PIL import Image\nimport matplotlib.pyplot as plt\n\nimport os\nprint(os.listdir(\"../working/\"))\nfiles = os.listdir(\"../input/train/\")","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"89ebe4b8539235ec1b85af6d9acf738a5a94f88c"},"cell_type":"markdown","source":"# **1 - Importation des données**"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"features = []\ntargets = []\n\nfor file in files[:1000]:\n    features.append(np.array(Image.open(\"../input/train/\" + file).resize((60, 60))))\n    target = 1 if \"cat\" in file else 0\n    targets.append(target)\n    \nfeatures = np.array(features)\ntargets = np.array(targets)\nprint(\"features :\", features.shape)\nprint(\"targets : \", targets.shape)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"f9d8d19f04a75013707b3041462d1ed3121889b2"},"cell_type":"markdown","source":"# **2 - Echantillonnage**"},{"metadata":{"trusted":true,"_uuid":"849ca51e3e835a2e2250a2c129ecea268267a5f2"},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\n\nx_train, x_valid, y_train, y_valid = train_test_split(features, targets, test_size=0.1, random_state=123)\n\nprint(\"x_train =\",x_train.shape,\"  |  y_train =\",y_train.shape)\nprint(\"x_valid =\",x_valid.shape,\"  |  y_valid =\",y_valid.shape)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d15bbe69df06b82bfe1a1e0a1482ded77c05ecff"},"cell_type":"markdown","source":"# **3 - Visualisation**"},{"metadata":{"trusted":true,"_uuid":"c684008ab387a4844e49334e26c71d143af4bc18"},"cell_type":"code","source":"index = np.arange(len(x_train))\nnp.random.shuffle(index)\nx_train = x_train[index]\ny_train = y_train[index]\n\nfig = plt.figure(figsize=(17,17))\nplt.gcf().subplots_adjust( wspace = 0, hspace = 0.2)\nfor i in range(1,26):\n    plt.subplot(5, 5, i)\n    img = plt.imshow(features[i])\n    img.axes.get_xaxis().set_visible(False)\n    img.axes.get_yaxis().set_visible(False)\n    if targets[i] == 0:\n        label = \"Chien\"\n    else:\n        label = \"Chat\"\n    plt.title((label))\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"428b2e69baf483812f4f53ef906cd1fad81c80b7"},"cell_type":"code","source":"import keras\nfrom keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization\n\nmodel = Sequential()\n\nmodel.add(Conv2D(64, (3, 3), activation='relu', input_shape=(60, 60, 3)))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(256, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(512, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(256, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))\n\n#model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\nmodel.compile(loss='binary_crossentropy',\n              optimizer=keras.optimizers.SGD(lr=0.001, momentum=0.9, nesterov=True)\n             , metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"33cf2cbb3db4ba18ebe95b3d742e9ac837e7c756","scrolled":false},"cell_type":"code","source":"from keras.callbacks import ModelCheckpoint\ncheckpointer = ModelCheckpoint(filepath='../working/weights.hdf5', verbose=1, save_best_only=True)\n\nmodel.fit(x=x_train, \n          y=y_train, \n          batch_size=200, \n          epochs=1, \n          verbose=1, \n          callbacks=[checkpointer], \n          validation_data=(x_valid,y_valid), \n          shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"17523bf75efe0a8efdee2fbe8a59d5dd58c5b5f6"},"cell_type":"code","source":"print(os.listdir(\"../working/\"))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"911ba97f53218a8a1b450cd9321a0bd0a0860e41"},"cell_type":"code","source":"# Verification des Performace\nloss_and_metrics = model.evaluate(x_test, y_test, batch_size=200)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7e5c9108791fcff5bec8544ee0139aa0c059eb65"},"cell_type":"code","source":"# Prédiction\nclasses = model.predict(x_test, batch_size=128)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"3b030ad790363d0acebb5445935a00aa266b331e"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"63b31e91a8c3a3950f599f73324b989a3f305dd6"},"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}