{"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":{"trusted":true},"cell_type":"code","source":"import os\nprint(os.getcwd())","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import pandas as pd\ndf = pd.read_csv('train.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import ast","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df.bbox = df.bbox.apply(ast.literal_eval)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df = df.groupby('image_id')['bbox'].apply(list).reset_index()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"DATA_PATH = '/kaggle/input/global-wheat-detection/'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn import model_selection\n\ndf_train , df_valid = model_selection.train_test_split(\ndf,test_size = 0.1 ,random_state = 42 ,shuffle = True)\n\ndf_train  = df_train.reset_index(drop = True)\ndf_valid  = df_valid.reset_index(drop = True)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true},"cell_type":"code","source":"os.mkdir('/kaagle/wheat_data')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.mkdir('/kaagle/wheat_data/images')\nos.mkdir('/kaagle/wheat_data/labels')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"collapsed":true},"cell_type":"code","source":"os.mkdir('/kaagle/wheat_data/images/train')\nos.mkdir('/kaagle/wheat_data/images/validation')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.mkdir('/kaagle/wheat_data/labels/train')\nos.mkdir('/kaagle/wheat_data/labels/validation')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"OUTPUT_PATH = '/kaagle/wheat_data'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm\nimport shutil\nimport numpy as np\ndef process_data(data,data_type = 'train'):\n    for _, row in tqdm(data.iterrows() , total = len(data)):\n        image_name = row['image_id']\n        bounding_boxes = row['bbox']\n        yolo_data = []\n        for bobox in bounding_boxes:\n            x = bobox[0]\n            y = bobox[1]\n            w = bobox[2]\n            h = bobox[3]\n            x_center = x + w / 2\n            y_center = y + h / 2\n            x_center /= 1024\n            y_center /= 1024\n            w /= 1024\n            h /= 1024\n            yolo_data.append([0 , x_center , y_center , w, h  ])\n        yolo_data = np.array(yolo_data)\n        np.savetxt(os.path.join(OUTPUT_PATH , f\"labels/{data_type}/{image_name}.txt\"),\n                   yolo_data,\n                  fmt=[\"%d\" , \"%f\", \"%f\" ,\"%f\" , \"%f\"])\n        shutil.copyfile(os.path.join(DATA_PATH, f\"train/{image_name}.jpg\")\n                       ,os.path.join(OUTPUT_PATH, f\"images/{data_type}/{image_name}.jpg\"))\n        \n            \n            \n            \n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"process_data(df_valid ,data_type = 'validation')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"process_data(df_train ,data_type = 'train')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nos.chdir('/kaggle/input/yolov5/yolov5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!python train.py --img 1024 --batch 10 --epochs 100 --data /kaggle/input/wheat123/wheat.yaml --cfg /kaggle/input/yolov5/yolov5/models/yolov5s.yaml --name wm","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}