{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"%reload_ext autoreload\n%autoreload 2\n%matplotlib inline\n\n# 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\nfrom fastai.vision import *\nfrom fastai.metrics import *\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 the files in the input directory\n\nimport os\npath = '../input'\nprint(os.listdir(path))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load data"},{"metadata":{"trusted":true},"cell_type":"code","source":"class CustomImageList(ImageList):\n    def open(self, fn):\n        img = fn.reshape(28,28)\n        img = np.stack((img,)*3, axis=-1)\n        return Image(pil2tensor(img, dtype=np.float32))\n    \n    @classmethod\n    def from_csv_custom(cls, path:PathOrStr, csv_name:str, imgIdx:int=1, header:str='infer', **kwargs)->'ItemList': \n        df = pd.read_csv(Path(path)/csv_name, header=header)\n        res = super().from_df(df, path=path, cols=0, **kwargs)\n        \n        res.items = df.iloc[:,imgIdx:].apply(lambda x: x.values / 255.0, axis=1).values\n        \n        return res","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test = CustomImageList.from_csv_custom(path=path, csv_name='test.csv', imgIdx=0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"tfms = get_transforms(do_flip=False)\ndata = (CustomImageList.from_csv_custom(path=path, csv_name='train.csv', imgIdx=1)\n                .split_by_rand_pct(.2)\n                .label_from_df(cols='label')\n                .add_test(test, label=0)\n                .transform(tfms)\n                .databunch(bs=128, num_workers=0)\n                .normalize(imagenet_stats))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.show_batch(rows=3, figsize=(5,5))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Train Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(data, models.resnet50, metrics=accuracy, model_dir='/kaggle/working/models')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()","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":"lr = 1e-2\nlearn.fit_one_cycle(10, lr)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.save('stage1-resnet50')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.load('stage1-resnet50')\nlearn.validate()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.lr_find()\nlearn.recorder.plot()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.unfreeze()\nlearn.fit_one_cycle(5, max_lr=slice(1e-6, 2.5e-4))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.validate()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Submit"},{"metadata":{"trusted":true},"cell_type":"code","source":"# get the predictions\npredictions, *_ = learn.get_preds(DatasetType.Test)\nlabels = np.argmax(predictions, 1)\n# output to a file\nsubmission_df = pd.DataFrame({'ImageId': list(range(1,len(labels)+1)), 'Label': labels})\nsubmission_df.to_csv(f'submission.csv', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.4","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}