{"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\n# for 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","execution":{"iopub.status.busy":"2023-02-01T15:58:12.993064Z","iopub.execute_input":"2023-02-01T15:58:12.993524Z","iopub.status.idle":"2023-02-01T15:58:13.025441Z","shell.execute_reply.started":"2023-02-01T15:58:12.99343Z","shell.execute_reply":"2023-02-01T15:58:13.02453Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import tensorflow.keras\nimport shutil\nimport os\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom tensorflow.keras import layers,models,optimizers\nfrom tensorflow.keras.applications import VGG16\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\n\n","metadata":{"execution":{"iopub.status.busy":"2023-02-01T16:09:38.62092Z","iopub.execute_input":"2023-02-01T16:09:38.621346Z","iopub.status.idle":"2023-02-01T16:09:38.628495Z","shell.execute_reply.started":"2023-02-01T16:09:38.62131Z","shell.execute_reply":"2023-02-01T16:09:38.627293Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import zipfile\npath='/kaggle/input/dogs-vs-cats'\nwork_dir='/kaggle/working'\nz= zipfile.ZipFile(path+'/train.zip')\nz.extractall()\ntrain_dir='/kaggle/working/train'","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"z2= zipfile.ZipFile(path+'/test1.zip')\nz2.extractall()\ntest_dir='/kaggle/working/test1'","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation_dir=os.path.join(work_dir,'validation')\nos.mkdir(validation_dir)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_cat_dir=os.path.join(train_dir,'cat')\nos.mkdir(train_cat_dir)\n\ntrain_dog_dir=os.path.join(train_dir,'dog')\nos.mkdir(train_dog_dir)\n\n","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"validation_cat_dir=os.path.join(validation_dir,'cat')\nos.mkdir(validation_cat_dir)\n\nvalidation_dog_dir=os.path.join(validation_dir,'dog')\nos.mkdir(validation_dog_dir)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_cat_dir=os.path.join(test_dir,'cat')\nos.mkdir(test_cat_dir)\n\ntest_dog_dir=os.path.join(test_dir,'dog')\nos.mkdir(test_dog_dir)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#kopiujemy z test do validation\nfnames=['dog.{}.jpg'.format(i) for i in range(1000)]\nfor fname in fnames:\n    src=os.path.join(train_dir,fname)\n    dst=os.path.join(validation_dog_dir,fname)\n    shutil.copyfile(src,dst)\nfnames=['cat.{}.jpg'.format(i) for i in range(1000)]\nfor fname in fnames:\n    src=os.path.join(train_dir,fname)\n    dst=os.path.join(validation_cat_dir,fname)\n    shutil.copyfile(src,dst)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for file in os.listdir(train_dir):\n    if file[-3]=='j':\n        if file[0]=='c':\n            os.replace(os.path.join(train_dir,file),os.path.join(train_cat_dir,file))\n        else:\n            os.replace(os.path.join(train_dir,file),os.path.join(train_dog_dir,file))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"cat_train_len=len(os.listdir(train_cat_dir))\nprint(cat_train_len)\n\ndog_train_len=len(os.listdir(train_dog_dir))\nprint(dog_train_len)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"conv_base=VGG16(weights='imagenet',\n                include_top=False,\n                input_shape=(150,150,3))\nconv_base.summary()","metadata":{"execution":{"iopub.status.busy":"2023-02-01T16:09:46.51833Z","iopub.execute_input":"2023-02-01T16:09:46.519397Z","iopub.status.idle":"2023-02-01T16:09:49.476269Z","shell.execute_reply.started":"2023-02-01T16:09:46.519357Z","shell.execute_reply":"2023-02-01T16:09:49.474625Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"base_dir=work_dir\ntrain_dir=os.path.join(base_dir,'train')\nvalidation_dir=os.path.join(base_dir,'validation')\ntest_dir=os.path.join(base_dir,'test1')\n","metadata":{"execution":{"iopub.status.busy":"2023-02-01T16:10:19.735712Z","iopub.execute_input":"2023-02-01T16:10:19.736157Z","iopub.status.idle":"2023-02-01T16:10:19.743315Z","shell.execute_reply.started":"2023-02-01T16:10:19.736123Z","shell.execute_reply":"2023-02-01T16:10:19.741849Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"datagen=ImageDataGenerator(rescale=1./255)\nbath_size=20","metadata":{"execution":{"iopub.status.busy":"2023-02-01T16:10:08.035694Z","iopub.execute_input":"2023-02-01T16:10:08.036094Z","iopub.status.idle":"2023-02-01T16:10:08.042449Z","shell.execute_reply.started":"2023-02-01T16:10:08.036056Z","shell.execute_reply":"2023-02-01T16:10:08.040718Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def extract_features(directory,sample_count):\n    features=np.zeros(shape=(sample_count,4,4,512))\n    labels=np.zeros(shape=(sample_count))\n    generator=datagen.flow_from_directory(\n                directory,\n                target_size=(150,150),\n                batch_size=bath_size,\n                class_mode='binary'\n    )\n    i=0\n    for input_batch,labels_batch in generator:\n        features_batch=conv_base.predict(input_batch)\n        features[i*bath_size:(i+1)*bath_size]=features_batch\n        labels[i*bath_size:(i+1)*bath_size]=labels_batch\n        i+=1\n        if i*bath_size>=sample_count: break\n    return features,labels","metadata":{"execution":{"iopub.status.busy":"2023-02-01T16:24:55.036351Z","iopub.execute_input":"2023-02-01T16:24:55.03682Z","iopub.status.idle":"2023-02-01T16:24:55.073254Z","shell.execute_reply.started":"2023-02-01T16:24:55.036729Z","shell.execute_reply":"2023-02-01T16:24:55.071802Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_features,train_labels=extract_features(train_dir,2000)\nvalidation_features,validation_labels=extract_features(validation_dir,1000)\ntest_features,test_labels=extract_features(test_dir,1000)","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_features=np.reshape(train_features,(2000,4*4*512))\nvalidation_features=np.reshape(validation_features,(1000,4*4*512))\ntest_features=np.reshape(test_features,(1000,4*4*512))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model=models.Sequential()\nmodel.add(layers.Dense(256, activation='relu',input_dim=4*4*512))\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(1,activation='sigmoid'))","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.compile(optimizer=optimizers.RMSprop(lr=2e-5),\n                loss='binary_crossentropy',\n                metrics=['acc'])","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history=model.fit(\n    train_features,\n    train_labels,\n    epochs=30,\n    batch_size=20,\n    validation_data=(validation_features,validation_labels)\n)\nmodel.save('cat_and_dog_p2_1.h5')","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"acc=history.history['acc']\nval_acc=history.history['val_acc']\nloss=history.history['loss']\nval_loss=history.history['val_loss']\n\nepochs=range(len(acc))\n\nplt.plot(epochs,loss,'bo',label='Strata trenowania')\nplt.plot(epochs,val_loss,'b',label='Strata walidacji')\nplt.title('Strata trenowania i walidacji')\nplt.legend()\nplt.figure()\n\nplt.plot(epochs,acc,'bo',label='Dokladnosc trenowania')\nplt.plot(epochs,val_acc,'b',label='Dokladnosc walidacji')\nplt.title('Dokladnosc trenowania i walidacji')\n\nplt.show()","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}