{"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","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from fastai.vision.all import *","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"df = pd.read_csv('../input/plant-pathology-2021-fgvc8/train.csv')\ndf.head()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"path = '../input/plant-pathology-2021-fgvc8'\n\ndef get_x(r):\n    return path + '/train_images/' + r['image']\n\ndef get_y(r):\n    return r['labels'].split(' ')\n\ndblock = DataBlock(blocks=(ImageBlock, MultiCategoryBlock),\n                   get_x = get_x, \n                   get_y = get_y,\n                  item_tfms = RandomResizedCrop(128, min_scale = 0.35),\n                  batch_tfms=aug_transforms())","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"dls = dblock.dataloaders(df)\ntest_files = get_image_files(path + '/test_images')\ntest_files.sort()\ntest_dl = dls.test_dl(test_files)\n\ndls.show_batch(nrows=1, ncols=3)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"f1score_multi = F1ScoreMulti()\nmodel = xresnet50(n_out=dls.c)\nlearn = Learner(dls, model, metrics=f1score_multi)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"learn.lr_find()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"learn.fit_one_cycle(7, 3e-3)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"learn.show_results()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tst_preds, tst_targs = learn.get_preds(dl=test_dl)\nthresh = 0.5\nlabelled_preds = [' '.join([dls.vocab[i] for i,p in enumerate(pred) if p > thresh]) for pred in tst_preds]","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fnames = [(f.name[:-4] + '.jpg') for f in test_files]\nfinal_df = pd.DataFrame({'image':fnames, 'labels':labelled_preds}, columns=['image', 'labels'])\nfinal_df.to_csv('./submission.csv', index=False)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Adapted from: https://github.com/fastai/fastbook/blob/master/06_multicat.ipynb","metadata":{}}]}