From 2b867e8e2250f087c845160c958d2927f38b1796 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Wed, 28 Apr 2021 20:11:02 +0200 Subject: [PATCH] Global Wheat Detection 2020 Dataset Auto-Download (#2968) * Create GlobalWheat2020.yaml * Update and rename visdrone.yaml to VisDrone.yaml * Update GlobalWheat2020.yaml (cherry picked from commit 33712d6dd0cc54e28b97d56cb999aa050a1c94ef) --- data/GlobalWheat2020.yaml | 55 +++++++++++++++++++++++++++++++++++ data/VisDrone.yaml | 61 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+) create mode 100644 data/GlobalWheat2020.yaml create mode 100644 data/VisDrone.yaml diff --git a/data/GlobalWheat2020.yaml b/data/GlobalWheat2020.yaml new file mode 100644 index 000000000000..b6f812d70383 --- /dev/null +++ b/data/GlobalWheat2020.yaml @@ -0,0 +1,55 @@ +# Global Wheat 2020 dataset http://www.global-wheat.com/ +# Train command: python train.py --data GlobalWheat2020.yaml +# Default dataset location is next to YOLOv5: +# /parent_folder +# /datasets/GlobalWheat2020 +# /yolov5 + + +# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] +train: # 3422 images + - ../datasets/GlobalWheat2020/images/arvalis_1 + - ../datasets/GlobalWheat2020/images/arvalis_2 + - ../datasets/GlobalWheat2020/images/arvalis_3 + - ../datasets/GlobalWheat2020/images/ethz_1 + - ../datasets/GlobalWheat2020/images/rres_1 + - ../datasets/GlobalWheat2020/images/inrae_1 + - ../datasets/GlobalWheat2020/images/usask_1 + +val: # 748 images (WARNING: train set contains ethz_1) + - ../datasets/GlobalWheat2020/images/ethz_1 + +test: # 1276 + - ../datasets/GlobalWheat2020/images/utokyo_1 + - ../datasets/GlobalWheat2020/images/utokyo_2 + - ../datasets/GlobalWheat2020/images/nau_1 + - ../datasets/GlobalWheat2020/images/uq_1 + +# number of classes +nc: 1 + +# class names +names: [ 'wheat_head' ] + + +# download command/URL (optional) -------------------------------------------------------------------------------------- +download: | + from utils.general import download, Path + + # Download + dir = Path('../datasets/GlobalWheat2020') # dataset directory + urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip'] + download(urls, dir=dir) + + # Make Directories + for p in 'annotations', 'images', 'labels': + (dir / p).mkdir(parents=True, exist_ok=True) + + # Move + for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \ + 'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1': + (dir / p).rename(dir / 'images' / p) # move to /images + f = (dir / p).with_suffix('.json') # json file + if f.exists(): + f.rename((dir / 'annotations' / p).with_suffix('.json')) # move to /annotations diff --git a/data/VisDrone.yaml b/data/VisDrone.yaml new file mode 100644 index 000000000000..c4603b200132 --- /dev/null +++ b/data/VisDrone.yaml @@ -0,0 +1,61 @@ +# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset +# Train command: python train.py --data VisDrone.yaml +# Default dataset location is next to YOLOv5: +# /parent_folder +# /VisDrone +# /yolov5 + + +# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/] +train: ../VisDrone/VisDrone2019-DET-train/images # 6471 images +val: ../VisDrone/VisDrone2019-DET-val/images # 548 images +test: ../VisDrone/VisDrone2019-DET-test-dev/images # 1610 images + +# number of classes +nc: 10 + +# class names +names: [ 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor' ] + + +# download command/URL (optional) -------------------------------------------------------------------------------------- +download: | + from utils.general import download, os, Path + + def visdrone2yolo(dir): + from PIL import Image + from tqdm import tqdm + + def convert_box(size, box): + # Convert VisDrone box to YOLO xywh box + dw = 1. / size[0] + dh = 1. / size[1] + return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh + + (dir / 'labels').mkdir(parents=True, exist_ok=True) # make labels directory + pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}') + for f in pbar: + img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size + lines = [] + with open(f, 'r') as file: # read annotation.txt + for row in [x.split(',') for x in file.read().strip().splitlines()]: + if row[4] == '0': # VisDrone 'ignored regions' class 0 + continue + cls = int(row[5]) - 1 + box = convert_box(img_size, tuple(map(int, row[:4]))) + lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n") + with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl: + fl.writelines(lines) # write label.txt + + + # Download + dir = Path('../VisDrone') # dataset directory + urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip', + 'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip'] + download(urls, dir=dir) + + # Convert + for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev': + visdrone2yolo(dir / d) # convert VisDrone annotations to YOLO labels