This competition wants us to predict bounding boxes around whaet heads from images of wheat plants, to solve this problom we have a sample of image, and csv file containing the image_id (the unique image ID), the width and height of the images, and bounding box, formatted as a Python-style list of [xmin, ymin, width, height]
\n\n***\n\nHello, this is my second notebook in this competition, if you want to see my other notebook, [Global Wheat Detection FASTER R-CNN [EDA - AUGMENTATION - COMPARE MODELS]](https://www.kaggle.com/dhiiyaur/fasterrcnn-eda-augmentation-compare-models). The main idea of this notebook its to compare models in detectron 2 with this dataset ( test with Nvidia T4).\n"},{"metadata":{},"cell_type":"markdown","source":"## Changelog\n\n### V1\n\n> - add new model\n> - add augmentation"},{"metadata":{},"cell_type":"markdown","source":"## Import necessary libraries"},{"metadata":{"_kg_hide-input":true,"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"!pip install '/kaggle/input/torch-15/yacs-0.1.7-py3-none-any.whl'\n!pip install '/kaggle/input/torch-15/fvcore-0.1.1.post200513-py3-none-any.whl'\n!pip install '/kaggle/input/pycocotools/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":"from detectron2.config import get_cfg\nfrom detectron2 import model_zoo","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport torch\nimport os\nimport random\n\nimport matplotlib.pyplot as plt\nfrom matplotlib import patches\nimport seaborn as sns\n%matplotlib inline\n\nimport cv2\nimport itertools\nimport copy\n\n\nimport detectron2\nfrom detectron2.utils.logger import setup_logger\nsetup_logger()\nfrom detectron2 import model_zoo\nfrom detectron2.engine import DefaultPredictor, DefaultTrainer\nfrom detectron2.config import get_cfg\nfrom detectron2.utils.visualizer import Visualizer\nfrom detectron2.data import DatasetCatalog, MetadataCatalog, build_detection_test_loader, build_detection_train_loader\nfrom detectron2.evaluation import COCOEvaluator, inference_on_dataset\nfrom detectron2.structures import BoxMode\nimport detectron2.data.transforms as T\nfrom detectron2.data import detection_utils as utils","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"DATA_DIR = '/kaggle/input/global-wheat-detection/train/'\nTEST_DIR = '/kaggle/input/global-wheat-detection/test/'\nList_Data_dir = os.listdir(DATA_DIR)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Config"},{"metadata":{"trusted":true},"cell_type":"code","source":"# for example model\n\nMODEL_USE = 3\n\nif MODEL_USE == 1:\n MODEL = 'COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml'\n WEIGHT_PATH = '../input/global-wheat-detection-model/Detectron_2/faster_rcnn_R_50_FPN_3x.pth'\nelif MODEL_USE == 2:\n MODEL = 'COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml'\n WEIGHT_PATH = '../input/global-wheat-detection-model/Detectron_2_v2/R-50_5k_augmen.pth'\nelif MODEL_USE == 3:\n MODEL = 'COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml'\n WEIGHT_PATH = '../input/global-wheat-detection-model/Detectron_2_v2/R-50_10k_augmen.pth'\n \nMAX_ITER = 5000 #10000","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Load Data and Simple EDA"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"raw = pd.read_csv('/kaggle/input/global-wheat-detection/train.csv')\nraw","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":false},"cell_type":"code","source":"print(f'Total number of train images: {raw.image_id.nunique()}')\nprint(f'Total number of test images: {len(os.listdir(TEST_DIR))}')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(15,8))\nplt.title('Wheat Distribution', fontsize= 20)\nsns.countplot(x=\"source\", data=raw)\n\n# based on the chart, there are seven types of wheat from images data, with the most types 'ethz_1' and the least is 'inrae_1'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Extract bbox column to xmin, ymin, width, height, then create xmax, ymax, and area columns\n\nraw[['xmin','ymin','w','h']] = pd.DataFrame(raw.bbox.str.strip('[]').str.split(',').tolist()).astype(float)\nraw['xmax'], raw['ymax'], raw['area'] = raw['xmin'] + raw['w'], raw['ymin'] + raw['h'], raw['w'] * raw['h']\nraw","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def show_image(image_id):\n \n fig, ax = plt.subplots(1, 2, figsize = (24, 24))\n ax = ax.flatten()\n \n bbox = raw[raw['image_id'] == image_id ]\n img_path = os.path.join(DATA_DIR, image_id + '.jpg')\n \n image = cv2.imread(img_path, cv2.IMREAD_COLOR)\n image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB).astype(np.float32)\n image /= 255.0\n image2 = image\n \n ax[0].set_title('Original Image')\n ax[0].imshow(image)\n \n for idx, row in bbox.iterrows():\n x1 = row['xmin']\n y1 = row['ymin']\n x2 = row['xmax']\n y2 = row['ymax']\n label = row['source']\n \n cv2.rectangle(image2, (int(x1),int(y1)), (int(x2),int(y2)), (255,255,255), 2)\n font = cv2.FONT_HERSHEY_SIMPLEX\n cv2.putText(image2, label, (int(x1),int(y1-10)), font, 1, (255,255,255), 2)\n \n ax[1].set_title('Image with Bondary Box')\n ax[1].imshow(image2)\n\n plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"show_image(raw.image_id.unique()[1111])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Data Preprocessing"},{"metadata":{"trusted":true},"cell_type":"code","source":"# split train, val\nunique_files = raw.image_id.unique()\n\ntrain_files = set(np.random.choice(unique_files, int(len(unique_files) * 0.90), replace = False))\ntrain_df = raw[raw.image_id.isin(train_files)]\ntest_df = raw[~raw.image_id.isin(train_files)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-input":false},"cell_type":"code","source":"print(len(train_df.image_id.unique()), len(test_df.image_id.unique()))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def custom_dataset(df, dir_image):\n \n dataset_dicts = []\n \n for img_id, img_name in enumerate(df.image_id.unique()):\n \n record = {}\n image_df = df[df['image_id'] == img_name]\n img_path = dir_image + img_name + '.jpg'\n \n record['file_name'] = img_path\n record['image_id'] = img_id\n record['height'] = int(image_df['height'].values[0])\n record['width'] = int(image_df['width'].values[0])\n \n objs = []\n for _, row in image_df.iterrows():\n \n x_min = int(row.xmin)\n y_min = int(row.ymin)\n x_max = int(row.xmax)\n y_max = int(row.ymax)\n \n poly = [(x_min, y_min), (x_max, y_min),\n (x_max, y_max), (x_min, y_max) ]\n \n poly = list(itertools.chain.from_iterable(poly))\n \n obj = {\n \"bbox\": [x_min, y_min, x_max, y_max],\n \"bbox_mode\": BoxMode.XYXY_ABS,\n \"segmentation\": [poly],\n \"category_id\": 0,\n \"iscrowd\" : 0\n \n }\n \n objs.append(obj)\n \n record['annotations'] = objs\n dataset_dicts.append(record)\n \n return dataset_dicts","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def custom_mapper(dataset_dict):\n # Implement a mapper, similar to the default DatasetMapper, but with your own customizations\n dataset_dict = copy.deepcopy(dataset_dict) # it will be modified by code below\n image = utils.read_image(dataset_dict[\"file_name\"], format=\"BGR\")\n transform_list = [T.Resize((800,800)),\n T.RandomFlip(prob=0.5, horizontal=False, vertical=True),\n T.RandomFlip(prob=0.5, horizontal=True, vertical=False), \n ]\n image, transforms = T.apply_transform_gens(transform_list, image)\n dataset_dict[\"image\"] = torch.as_tensor(image.transpose(2, 0, 1).astype(\"float32\"))\n\n annos = [\n utils.transform_instance_annotations(obj, transforms, image.shape[:2])\n for obj in dataset_dict.pop(\"annotations\")\n if obj.get(\"iscrowd\", 0) == 0\n ]\n instances = utils.annotations_to_instances(annos, image.shape[:2])\n dataset_dict[\"instances\"] = utils.filter_empty_instances(instances)\n return dataset_dict\n\n\nclass WheatTrainer(DefaultTrainer):\n \n @classmethod\n def build_train_loader(cls, cfg):\n return build_detection_train_loader(cfg, mapper=custom_mapper)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def register_dataset(df, dataset_label='wheat_train', image_dir = DATA_DIR):\n \n # Register dataset - if dataset is already registered, give it a new name \n try:\n DatasetCatalog.register(dataset_label, lambda d=df: custom_dataset(df, image_dir))\n MetadataCatalog.get(dataset_label).set(thing_classes = ['wheat'])\n except:\n # Add random int to dataset name to not run into 'Already registered' error\n n = random.randint(1, 1000)\n dataset_label = dataset_label + str(n)\n DatasetCatalog.register(dataset_label, lambda d=df: custom_dataset(df, image_dir))\n MetadataCatalog.get(dataset_label).set(thing_classes = ['wheat'])\n\n return MetadataCatalog.get(dataset_label), dataset_label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"metadata, train_dataset = register_dataset(train_df)\nmetadata, val_dataset = register_dataset(test_df, dataset_label='wheat_test')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Create a model and training"},{"metadata":{"trusted":true},"cell_type":"code","source":"MODEL","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"cfg = get_cfg()\ncfg.merge_from_file(model_zoo.get_config_file(MODEL))\ncfg.DATASETS.TRAIN = (train_dataset,)\ncfg.DATASETS.TEST = ()\ncfg.DATALOADER.NUM_WORKERS = 4\ncfg.MODEL.WEIGHTS = model_zoo.get_checkpoint_url(MODEL) \ncfg.SOLVER.IMS_PER_BATCH = 2\ncfg.SOLVER.BASE_LR = 0.00025 \ncfg.SOLVER.MAX_ITER = MAX_ITER\ncfg.MODEL.ROI_HEADS.BATCH_SIZE_PER_IMAGE = 128 \ncfg.MODEL.ROI_HEADS.NUM_CLASSES = 1\nos.makedirs(cfg.OUTPUT_DIR, exist_ok=True)\ntrainer = WheatTrainer(cfg)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Augmentation Visualization"},{"metadata":{"_kg_hide-output":true,"trusted":true},"cell_type":"code","source":"# create data loader\n# code from https://www.kaggle.com/julienbeaulieu/detectron2-wheat-detection-eda-training-eval\n\ntrain_data_loader = trainer.build_train_loader(cfg)\ndata_iter = iter(train_data_loader)\nbatch = next(data_iter)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# visualization\n\nrows, cols = 1, 2\nplt.figure(figsize=(20,20))\n\nfor i, per_image in enumerate(batch[:4]):\n \n plt.subplot(rows, cols, i+1)\n \n # Pytorch tensor is in (C, H, W) format\n img = per_image[\"image\"].permute(1, 2, 0).cpu().detach().numpy()\n img = utils.convert_image_to_rgb(img, cfg.INPUT.FORMAT)\n\n visualizer = Visualizer(img, metadata=metadata, scale=0.5)\n\n target_fields = per_image[\"instances\"].get_fields()\n labels = None\n vis = visualizer.overlay_instances(\n labels=labels,\n boxes=target_fields.get(\"gt_boxes\", None),\n masks=target_fields.get(\"gt_masks\", None),\n keypoints=target_fields.get(\"gt_keypoints\", None),\n )\n plt.imshow(vis.get_image()[:, :, ::-1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"trainer.resume_or_load(resume=False)\ntrainer.train()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Evaluation and Inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"# model + path\n\nprint(MODEL)\nprint(WEIGHT_PATH)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"cfg = get_cfg()\ncfg.merge_from_file(model_zoo.get_config_file(MODEL))\ncfg.MODEL.WEIGHTS = WEIGHT_PATH\ncfg.MODEL.ROI_HEADS.NUM_CLASSES = 1\ncfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.2\ncfg.DATASETS.TEST = ('wheat_test', )\npredictor = DefaultPredictor(cfg)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"evaluator = COCOEvaluator(val_dataset, cfg, False, output_dir=\"./output/\")\nval_loader = build_detection_test_loader(cfg, val_dataset)\ninference_on_dataset(trainer.model, val_loader, evaluator)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Result"},{"metadata":{},"cell_type":"markdown","source":"## Without Augmentation\n\n> ","attachments":{"Untitled.png":{"image/png":"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"}}},{"metadata":{},"cell_type":"markdown","source":"## With Augmentation\n\n> Augmentation\n> * RandomFlip Vertical (0.5)\n> * RandomFlip Horizontal (0.5)\n> * iter 5k & 10k\n\n>","attachments":{"Untitled.png":{"image/png":"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"}}},{"metadata":{"trusted":true},"cell_type":"code","source":"df_sub = pd.read_csv('../input/global-wheat-detection/sample_submission.csv')\ndf_sub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# CONFIG\n\nfont = cv2.FONT_HERSHEY_SIMPLEX \nfontScale = 1 \ncolor = (255, 255, 0)\nthickness = 2\nresults = []\n\ndef format_prediction_string(boxes, scores):\n pred_strings = []\n for j in zip(scores, boxes):\n pred_strings.append(\"{0:.4f} {1} {2} {3} {4}\".format(j[0], j[1][0], j[1][1], j[1][2], j[1][3]))\n\n return \" \".join(pred_strings)\n\n\ndef result_show(df, color):\n \n for image_id in df_sub['image_id']:\n im = cv2.imread('{}/{}.jpg'.format(TEST_DIR, image_id))\n boxes = []\n scores = []\n labels = []\n outputs = predictor(im)\n out = outputs[\"instances\"].to(\"cpu\")\n scores = out.get_fields()['scores'].numpy()\n boxes = out.get_fields()['pred_boxes'].tensor.numpy().astype(int)\n labels= out.get_fields()['scores'].numpy()\n boxes = boxes.astype(int)\n boxes[:, 2] = boxes[:, 2] - boxes[:, 0]\n boxes[:, 3] = boxes[:, 3] - boxes[:, 1]\n result = {'image_id': image_id,'PredictionString': format_prediction_string(boxes, scores)}\n results.append(result)\n im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB).astype(np.float32)\n im /= 255.0\n \n for b,s in zip(boxes,scores):\n cv2.rectangle(im, (b[0],b[1]), (b[0]+b[2],b[1]+b[3]), color, thickness)\n cv2.putText(im, '{:.2}'.format(s), (b[0],b[1]), font, 1, color, thickness)\n \n plt.figure(figsize=(12,12))\n plt.imshow(im)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Model 1\n\n> - faster_rcnn_R_50_FPN_3x\n> - Iter 5000"},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"result_show(df_sub['image_id'], color = (255, 255, 255))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Model 2\n\n> - faster_rcnn_R_50_FPN_3x\n> - Iter 5000\n> - RandomFlip Vertical (0.5)\n> - RandomFlip Horizontal (0.5)"},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"result_show(df_sub['image_id'], color = (255, 255, 0))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Model 3\n\n> - faster_rcnn_R_50_FPN_3x\n> - Iter 10000\n> - RandomFlip Vertical (0.5)\n> - RandomFlip Horizontal (0.5)"},{"metadata":{"trusted":true,"_kg_hide-output":true},"cell_type":"code","source":"result_show(df_sub['image_id'], color = (255, 0, 0))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df = pd.DataFrame(results, columns=['image_id', 'PredictionString'])\ntest_df.to_csv('submission.csv', index=False)\ntest_df","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"