{"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\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 5GB 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"!ls /kaggle/input/dogs-vs-cats-redux-kernels-edition","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip\n!unzip /kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!ls","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%reload_ext autoreload\n%autoreload 2\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from fastai.vision import *\nfrom fastai.metrics import error_rate\nfrom pathlib import Path\nimport pandas as pd\nimport numpy as np\nimport os\nimport warnings\nwarnings.filterwarnings('ignore')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.getcwd()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path = Path()\nprint(path.ls())\ntrain_path = path/'train'\ntest_path = path/'test'\nprint(train_path, test_path)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fnames = get_image_files(train_path)\nfnames[:5]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.random.seed(2)\n#pat = r'/([^/]+).\\d+.jpg$'\npat = r\"([a-z]+).\\d+.jpg$\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bs = 64 #Batch size\ndata = ImageDataBunch.from_name_re(path, fnames, pat, ds_tfms=get_transforms(),test='test', size=224, bs=bs\n                                  ).normalize(imagenet_stats)\ndata","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.show_batch(rows=3, figsize=(7,6))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(data.classes)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(data, models.resnet34, metrics=error_rate)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fit_one_cycle(4)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-1')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!find . -name *.pth -print","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"interp = ClassificationInterpretation.from_learner(learn)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"interp.plot_top_losses(9, figsize=(15,11))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"interp.plot_confusion_matrix(figsize=(12,12), dpi=60)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"interp.most_confused(min_val=2)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage-1');\nlearn.lr_find(stop_div=False, num_it=200)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()\nlearn.fit_one_cycle(2, max_lr=slice(1e-6, 1e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot_losses()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.recorder.plot_lr()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage-2')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds, _ = learn.get_preds(DatasetType.Test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(preds.size())\nprint(preds)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"labels = np.argmax(preds, axis=1)\nlabels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"input_path = Path('/kaggle/input/dogs-vs-cats-redux-kernels-edition')\ntest_df = pd.read_csv(input_path/'sample_submission.csv')\ntest_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ids = [int(file.stem) for file in data.test_ds.x.items]\nids","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({'id':ids,'label':labels})\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = submission.sort_values(by=['id'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv('submission.csv', index=False)","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":4}