{"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_minor":4,"nbformat":4,"cells":[{"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\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 read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"распакуем архивы с тренировочными и тестовыми данными","metadata":{}},{"cell_type":"code","source":"import zipfile\nzip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r')\nzip_ref.extractall('/kaggle/temp/dogs-vs-cats/')\nzip_ref = zipfile.ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r')\nzip_ref.extractall('/kaggle/temp/dogs-vs-cats/')\nzip_ref.close()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/dogs-vs-cats/","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"создадим дериктории для тренировочных данных и перенесем их в новые дериктории","metadata":{}},{"cell_type":"code","source":"!mkdir /kaggle/temp/dogs-vs-cats/train/dog/\n!mkdir /kaggle/temp/dogs-vs-cats/train/cat/","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import shutil\nfor file in os.listdir('/kaggle/temp/dogs-vs-cats/train/'):\n    if 'dog' in str(file) and 'jpg' in str(file):\n        shutil.move('/kaggle/temp/dogs-vs-cats/train/'+str(file),'/kaggle/temp/dogs-vs-cats/train/dog/'+str(file))\n    if 'cat' in str(file) and 'jpg' in str(file):\n        shutil.move('/kaggle/temp/dogs-vs-cats/train/'+str(file),'/kaggle/temp/dogs-vs-cats/train/cat/'+str(file))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/dogs-vs-cats/train","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"создадим новые дериктории для валидационных данных и также перенесем их","metadata":{}},{"cell_type":"code","source":"!mkdir /kaggle/temp/dogs-vs-cats/validate/\n!mkdir /kaggle/temp/dogs-vs-cats/validate/dog/\n!mkdir /kaggle/temp/dogs-vs-cats/validate/cat/","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!ls /kaggle/temp/dogs-vs-cats/","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for file in os.listdir('/kaggle/temp/dogs-vs-cats/train/dog/')[:1250]:\n    shutil.move('/kaggle/temp/dogs-vs-cats/train/dog/'+str(file),'/kaggle/temp/dogs-vs-cats/validate/dog/'+str(file))\nfor file in os.listdir('/kaggle/temp/dogs-vs-cats/train/cat/')[:1250]:\n    shutil.move('/kaggle/temp/dogs-vs-cats/train/cat/'+str(file),'/kaggle/temp/dogs-vs-cats/validate/cat/'+str(file))\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"создадим новые дериктории для тестовых данных и перенесем их в новые дериктории ","metadata":{}},{"cell_type":"code","source":"!mkdir /kaggle/temp/dogs-vs-cats/test/\n!mkdir /kaggle/temp/dogs-vs-cats/test/dog\n!mkdir /kaggle/temp/dogs-vs-cats/test/cat","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for file in os.listdir('/kaggle/temp/dogs-vs-cats/train/dog/')[:1250]:\n    shutil.move('/kaggle/temp/dogs-vs-cats/train/dog/'+str(file),'/kaggle/temp/dogs-vs-cats/test/dog/'+str(file))\nfor file in os.listdir('/kaggle/temp/dogs-vs-cats/train/cat/')[:1250]:\n    shutil.move('/kaggle/temp/dogs-vs-cats/train/cat/'+str(file),'/kaggle/temp/dogs-vs-cats/test/cat/'+str(file))\n","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(len(os.listdir('/kaggle/temp/dogs-vs-cats/train/dog/')))\nprint(len(os.listdir('/kaggle/temp/dogs-vs-cats/train/cat/')))\nprint(len(os.listdir('/kaggle/temp/dogs-vs-cats/validate/dog/')))\nprint(len(os.listdir('/kaggle/temp/dogs-vs-cats/validate/cat/')))\nprint(len(os.listdir('/kaggle/temp/dogs-vs-cats/test/dog/')))\nprint(len(os.listdir('/kaggle/temp/dogs-vs-cats/test/cat/')))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"преобразуем данные в удобный вид для тренировки нейронной сети","metadata":{}},{"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\nTRAIN_DIR = '/kaggle/temp/dogs-vs-cats/train/'\nVALIDATION_DIR ='/kaggle/temp/dogs-vs-cats/validate/'\nTEST_DIR ='/kaggle/temp/dogs-vs-cats/test/'\n\ntrain_datagen = ImageDataGenerator(rescale=1/255)\ntrain_generator = train_datagen.flow_from_directory(\n    TRAIN_DIR,\n    batch_size = 32,\n    shuffle=True,\n    target_size=(32,32),\n    class_mode='binary'\n)\n\n\nvalidation_datagen = ImageDataGenerator(rescale=1/255)\nvalidation_generator = validation_datagen.flow_from_directory(\n    VALIDATION_DIR,\n    batch_size = 32,\n    target_size=(32,32),\n    class_mode='binary'\n)\n\ntest_datagen = ImageDataGenerator(rescale=1/255)\ntest_generator = test_datagen.flow_from_directory(\n    TEST_DIR,\n    batch_size = 32,\n    target_size=(32,32),\n    class_mode='binary'\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Dense, Flatten\nfrom keras.layers import Dropout\nfrom keras.layers.convolutional import Conv2D, MaxPooling2D\nfrom keras.layers.normalization import BatchNormalization","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, (3, 3), input_shape=(32,32,3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(32, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\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'))\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(loss='binary_crossentropy',\n              optimizer='adam',\n              metrics=['accuracy'])","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit(\n    train_generator,\n    epochs=15,\n    validation_data=validation_generator,\n    shuffle=True,\n    verbose=1)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nhistory_dict = history.history\nacc_values = history_dict['accuracy']\nval_acc_values = history_dict['val_accuracy']\nepochs = range(1, len(acc_values) + 1)\nloss_values = history_dict['loss']\nval_loss_values = history_dict['val_loss']\nepochs = range(1, len(loss_values) + 1)\nf,ax=plt.subplots(1,2,figsize=(18,8))\nax[0].plot(epochs, acc_values, 'b', label='Training acc')\nax[0].plot(epochs, val_acc_values, 'r', label='Validation acc')\nax[0].set_title(\"метрика accuracy для тренировочной и валидационной выборки\")\nax[0].set_xlabel('Epochs')\nax[0].set_ylabel('Accuracy')\nax[0].legend()\nax[0].grid()\nax[1].plot(epochs, loss_values, 'b', label='Training loss')\nax[1].plot(epochs, val_loss_values, 'r', label='Validation loss')\nax[1].set_title(\"функции ошибок тренировочной и валидационной выборки\")\nax[1].set_xlabel('Epochs')\nax[1].set_ylabel('Loss')\nax[1].legend()\nax[1].grid()\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"scores = model.evaluate(test_generator, verbose=0)\nprint(\"Точность работы на тестовых данных: %.2f%%\" % (scores[1]*100))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!mkdir /kaggle/temp/dogs-vs-cats/test1/pred","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for file in os.listdir('/kaggle/temp/dogs-vs-cats/test1'):\n    if 'jpg' in str(file):\n        shutil.move('/kaggle/temp/dogs-vs-cats/test1/'+str(file),'/kaggle/temp/dogs-vs-cats/test1/pred/'+str(file))\n   ","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"создадим датасет с помощью данных полученных от обученной нейронной сети","metadata":{}},{"cell_type":"code","source":"PRED_DIR ='/kaggle/temp/dogs-vs-cats/test1/'\n\npred_datagen = ImageDataGenerator(rescale=1/255)\npred_generator = pred_datagen.flow_from_directory(\n    PRED_DIR,\n    batch_size = 32,\n    shuffle=False,\n    target_size=(32,32),\n    class_mode=None\n)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction = model.predict(pred_generator)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"prediction_result = [np.around(k) for k in prediction]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"results=pd.DataFrame({\"id\":range(1, len(prediction_result)+1),\"label\":prediction_result})\nresults","metadata":{"_kg_hide-output":true,"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"results['label'] = results.label.astype(\"int32\")","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"вычислим процентное содержание кошек и собак в датасете","metadata":{}},{"cell_type":"code","source":"results.label.value_counts()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"max_persetage = results.label.value_counts()[0] + results.label.value_counts()[1]\ndog_persantage = results.label.value_counts()[1] / max_persetage\ncat_persantage = results.label.value_counts()[0] / max_persetage","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"процент кошек в датасете составляет {}%, а процент собак {}%\".format(cat_persantage*100, dog_persantage*100))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"objects = ('Cats', 'Dogs')\ny_pos = np.arange(len(objects))\nperformance = [cat_persantage*100,dog_persantage*100]\n\nplt.bar(y_pos, performance, align='center', alpha=0.5)\nplt.xticks(y_pos, objects)\nplt.ylabel('%')\nplt.title('процентное содержание кошек и собак')\n\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}