{"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 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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"# For the CSVs\nimport pandas as pd\n# For the Model\nfrom fastai.vision.all import *\n# For acessing the Files\nimport os\n\n# Defining the Path:\npath = Path('../input/cassava-leaf-disease-classification')\n# Lets take a look at the CSV.\ndata = pd.read_csv(path/'train.csv')\ntrain = data[~data['image_id'].isin(['1562043567.jpg', '3551135685.jpg', '2252529694.jpg'])]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"path = Path('../input/cassava-leaf-disease-classification')\n\ndef get_x(r):\n    return path/'train_images'/r['image_id']\n\ndef get_y(r):\n    return r['label']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_data(size=256, bs=64, data_df=train):\n    block = DataBlock(blocks=(ImageBlock, CategoryBlock), \n                      splitter=RandomSplitter(seed=42), \n                      get_x=get_x,\n                      get_y=get_y, \n                      item_tfms = RandomResizedCrop(512),\n                      batch_tfms = [*aug_transforms(size=size),\n                                    Normalize.from_stats(*imagenet_stats)])\n\n    \n    return block.dataloaders(data_df, bs=bs)\n\ndataloader = get_data()\ndataloader.show_batch()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = cnn_learner(dataloader, resnet50, metrics=accuracy)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.fine_tune(1,0.010964781977236271)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn.export(\"/export.pth\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learn = load_learner(\"./export.pth\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = pd.read_csv(path/'sample_submission.csv')\n\ntest_data_path = submission_df['image_id'].apply(lambda x: path/'test_images'/x)\ntst_dl = learn.dls.test_dl(test_data_path)\npredictions = learn.tta(dl = tst_dl, n=10)\n\nsubmission_df['label'] = np.argmax(predictions[0],axis=1)\nsubmission_df\n\nsubmission_df.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}