{"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 all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        #print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import os, shutil, random, glob\nimport cv2\nimport numpy as np\nimport pandas as pd\n\n# os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"2\"\n# CUDA_VISIBLE_DEVICES = 2\n\nimport keras\nfrom keras.datasets import cifar10\nfrom keras.optimizers import SGD\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.models import Sequential\nfrom keras.layers import Dense, Dropout, Activation, Flatten\nfrom keras.layers import Conv2D, MaxPooling2D, ZeroPadding2D, BatchNormalization\nimport matplotlib.pyplot as plt","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"resize = 224\ndef load_data():\n    imgs = os.listdir(\"/kaggle/input/dogs-vs-cats-redux-kernels-edition/train/\")\n    num = len(imgs)\n    print(num)\n    train_data = np.empty((5000, resize, resize, 3), dtype=\"int32\")\n    train_label = np.empty((5000, ), dtype=\"int32\")\n    test_data = np.empty((5000, resize, resize, 3), dtype=\"int32\")\n    test_label = np.empty((5000, ), dtype=\"int32\")\n    for i in range(5000):\n        if i % 2:\n            train_data[i] = cv2.resize(cv2.imread('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train/' + 'dog.' + str(i) + '.jpg'), (resize, resize))\n            train_label[i] = 1\n        else:\n            train_data[i] = cv2.resize(cv2.imread('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train/' + 'cat.' + str(i) + '.jpg'), (resize, resize))\n            train_label[i] = 0\n    for i in range(5000, 10000):\n        if i % 2:\n            test_data[i-5000] = cv2.resize(cv2.imread('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train/' + 'dog.' + str(i) + '.jpg'), (resize, resize))\n            test_label[i-5000] = 1\n        else:\n            test_data[i-5000] = cv2.resize(cv2.imread('/kaggle/input/dogs-vs-cats-redux-kernels-edition/train/' + 'cat.' + str(i) + '.jpg'), (resize, resize))\n            test_label[i-5000] = 0\n    return train_data, train_label, test_data, test_label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data, train_label, test_data, test_label = load_data()\ntrain_data, test_data = train_data.astype('float32'), test_data.astype('float32')\ntrain_data, test_data = train_data/255, test_data/255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img = train_data[0]\nimg = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)\nplt.imshow(img)\nplt.axis(\"off\")\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_label = keras.utils.to_categorical(train_label, 2)\ntest_label = keras.utils.to_categorical(test_label, 2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#LeNet-5\n# model = Sequential()\n# model.add(Conv2D(filters=6, kernel_size=(5,5), \n#                  padding='valid', \n#                  input_shape=(224, 224, 3), \n#                  activation='tanh'))\n# model.add(MaxPooling2D(pool_size=(2,2)))\n# model.add(Conv2D(filters=16, kernel_size=(5,5), \n#                  padding='valid', \n#                  activation='tanh')) #双曲正切函数作激活函数 tanhx = (e^x-e^-x)/(e^x+e^-x)\n# model.add(MaxPooling2D(pool_size=(2,2)))\n# model.add(Flatten())\n# model.add(Dense(120, activation='tanh'))\n# model.add(Dense(84, activation='tanh'))\n# model.add(Dense(2, activation='softmax')) #softmax函数做激活函数 e^x/(sum(e^x))\n\n# sgd = SGD(lr=0.01, decay=0, momentum=0, nesterov=True) #采用随机梯度下降法作为优化算法\n# model.compile(loss='binary_crossentropy',\n#               optimizer=sgd, \n#               metrics=['accuracy'])\n\n# AlexNet\nmodel = Sequential()\n#第一段\nmodel.add(Conv2D(filters=96, kernel_size=(11,11),\n                 strides=(4,4), padding='valid',\n                 input_shape=(resize,resize,3),\n                 activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(3,3), \n                       strides=(2,2), \n                       padding='valid'))\n#第二段\nmodel.add(Conv2D(filters=256, kernel_size=(5,5), \n                 strides=(1,1), padding='same', \n                 activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(3,3), \n                       strides=(2,2), \n                       padding='valid'))\n#第三段\nmodel.add(Conv2D(filters=384, kernel_size=(3,3), \n                 strides=(1,1), padding='same', \n                 activation='relu'))\nmodel.add(Conv2D(filters=384, kernel_size=(3,3), \n                 strides=(1,1), padding='same', \n                 activation='relu'))\nmodel.add(Conv2D(filters=256, kernel_size=(3,3), \n                 strides=(1,1), padding='same', \n                 activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(3,3), \n                       strides=(2,2), padding='valid'))\n#第四段\nmodel.add(Flatten())\nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(4096, activation='relu'))\nmodel.add(Dropout(0.5))\n\nmodel.add(Dense(1000, activation='relu'))\nmodel.add(Dropout(0.5))\n\n# Output Layer\nmodel.add(Dense(2))\nmodel.add(Activation('softmax'))\n\nmodel.compile(loss='categorical_crossentropy',\n              optimizer='sgd',\n              metrics=['accuracy'])\n# model.summary()  ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(train_data, train_label,\n          batch_size = 64,\n          epochs = 50,\n          validation_split = 0.2,\n          shuffle = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"scores = model.evaluate(train_data, train_label, verbose=1)\nprint(scores)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"scores = model.evaluate(test_data, test_label, verbose=1)\nprint(scores)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#test_path=os.listdir('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test/')\n\n#test_path.remove(12500)\n\nfor root, dirs, files in os.walk('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test/'):\n    test_path=files\n\nprint(len(test_path))\nprint(test_path[0])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nresize = 224\ntest1_data = np.empty((12500, resize, resize, 3), dtype=\"int32\")\nfor i in range(12500):\n    test1_data [i] = cv2.resize(cv2.imread('/kaggle/input/dogs-vs-cats-redux-kernels-edition/test/' + str(test_path[i])),(resize, resize))\n            \n     ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\npredict_test = model.predict_classes(test1_data[0:10]).astype('int')\n\nprint(predict_test)\n\n","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":1}