{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install '/kaggle/input/detectron2/torch-1.5.0cu101-cp37-cp37m-linux_x86_64.whl'\n!pip install '/kaggle/input/detectron2/torchvision-0.6.0cu101-cp37-cp37m-linux_x86_64.whl'\n!pip install '/kaggle/input/detectron2/yacs-0.1.7-py3-none-any.whl'\n!pip install '/kaggle/input/detectron2/fvcore-0.1.1.post20200607-py3-none-any.whl'\n!pip install '/kaggle/input/detectron2/pycocotools-2.0-cp37-cp37m-linux_x86_64.whl'\n!pip install '/kaggle/input/detectron2/detectron2-0.1.3cu101-cp37-cp37m-linux_x86_64.whl'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import detectron2\nfrom detectron2.utils.logger import setup_logger\nsetup_logger()\n\nimport os\nimport json\nimport numpy as np\nimport pandas as pd\nimport cv2\nimport random\nimport itertools\nimport torch, torchvision\n\nfrom detectron2 import model_zoo\nfrom detectron2.engine import DefaultPredictor\nfrom detectron2.config import get_cfg\nfrom detectron2.utils.visualizer import Visualizer\nfrom detectron2.data import DatasetCatalog, MetadataCatalog\nfrom detectron2.structures import BoxMode\n\nfrom detectron2.engine import DefaultTrainer\nfrom detectron2.config import get_cfg\nfrom detectron2.utils.visualizer import ColorMode","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cfg = get_cfg()\ncfg.merge_from_file(model_zoo.get_config_file(\"COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml\"))\ncfg.MODEL.WEIGHTS = \"/kaggle/input/detectron2/model_0019999.pth\"\ncfg.MODEL.ROI_HEADS.NUM_CLASSES = 1\n# cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.7\npredictor = DefaultPredictor(cfg)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_image_dir = \"/kaggle/input/global-wheat-detection/test\"\ntest_images = os.listdir(test_image_dir)\nresults = []\nfor image in test_images:\n    image_id = image[:image.find(\".\")]\n\n    img = cv2.imread(os.path.join(test_image_dir, image))\n    outputs = predictor(img)\n    out = outputs[\"instances\"].to(\"cpu\")\n\n    scores = out.get_fields()[\"scores\"].numpy()\n    scores = scores.tolist()\n    scores = [round(scores, 5) for scores in scores]\n\n    boxes = out.get_fields()['pred_boxes'].tensor.numpy().astype(int)\n    boxes[:,2] = boxes[:, 2] - boxes[:, 0]\n    boxes[:, 3] = boxes[:, 3] - boxes[:, 1]\n    boxes = boxes.tolist()\n\n    for i in range(len(scores)):\n        boxes[i].insert(0, scores[i])\n  \n    prediction = []\n    for boxes in boxes:\n        prediction.extend(boxes)\n    prediction = [str(prediction) for prediction in prediction]\n\n    PredictionString = \"\"\n    for i in prediction:\n        PredictionString += f\"{i} \"\n    PredictionString = PredictionString.rstrip()\n\n    result = {\"image_id\":image_id, \"PredictionString\":PredictionString}\n    results.append(result)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"results[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.DataFrame(results, columns=['image_id', 'PredictionString'])\ntest_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}