import argparse
import os.path as osp
import xml.etree.ElementTree as ET
import mmcv
import numpy as np
from mmdet.core import voc_classes
label_ids = {name: i for i, name in enumerate(voc_classes())}
def parse_xml(args):
xml_path, img_path = args
tree = ET.parse(xml_path)
root = tree.getroot()
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
bboxes = []
labels = []
bboxes_ignore = []
labels_ignore = []
for obj in root.findall('object'):
name = obj.find('name').text
label = label_ids[name]
difficult = int(obj.find('difficult').text)
bnd_box = obj.find('bndbox')
bbox = [
int(bnd_box.find('xmin').text),
int(bnd_box.find('ymin').text),
def cvt_to_coco_json(annotations):
image_id = 0
annotation_id = 0
coco = dict()
coco['images'] = []
coco['type'] = 'instance'
coco['categories'] = []
coco['annotations'] = []
image_set = set()
def addAnnItem(annotation_id, image_id, category_id, bbox, difficult_flag):
annotation_item = dict()
annotation_item['segmentation'] = []
seg = []
# bbox[] is x1,y1,x2,y2
# left_top
seg.append(int(bbox[0]))
seg.append(int(bbox[1]))
# left_bottom
seg.append(int(bbox[0]))
seg.append(int(bbox[3]))
# right_bottom
seg.append(int(bbox[2]))
seg.append(int(bbox[3]))
# right_top
seg.append(int(bbox[2]))
seg.append(int(bbox[1]))
annotation_item['segmentation'].append(seg)
xywh = np.array(
[bbox[0], bbox[1], bbox[2] - bbox[0], bbox[3] - bbox[1]])
annotation_item['area'] = int(xywh[2] * xywh[3])
if difficult_flag == 1:
annotation_item['ignore'] = 0
annotation_item['iscrowd'] = 1
else:
annotation_item['ignore'] = 0
annotation_item['iscrowd'] = 0
annotation_item['image_id'] = int(image_id)
annotation_item['bbox'] = xywh.astype(int).tolist()
annotation_item['category_id'] = int(category_id)
annotation_item['id'] = int(annotation_id)
coco['annotations'].append(annotation_item)
return annotation_id + 1
for category_id, name in enumerate(voc_classes()):
category_item = dict()
category_item['supercategory'] = str('none')
category_item['id'] = int(category_id)
category_item['name'] = str(name)
coco['categories'].append(category_item)
for ann_dict in annotations:
file_name = ann_dict['filename']
ann = ann_dict['ann']
assert file_name not in image_set
image_item = dict()
image_item['id'] = int(image_id)
image_item['file_name'] = str(file_name)
image_item['height'] = int(ann_dict['height'])
image_item['width'] = int(ann_dict['width'])
coco['images'].append(image_item)
image_set.add(file_name)
bboxes = ann['bboxes'][:, :4]
labels = ann['labels']
for bbox_id in range(len(bboxes)):
bbox = bboxes[bbox_id]
label = labels[bbox_id]
annotation_id = addAnnItem(
annotation_id, image_id, label, bbox, difficult_flag=0)
bboxes_ignore = ann['bboxes_ignore'][:, :4]
labels_ignore = ann['labels_ignore']
for bbox_id in range(len(bboxes_ignore)):
bbox = bboxes_ignore[bbox_id]
label = labels_ignore[bbox_id]
annotation_id = addAnnItem(
annotation_id, image_id, label, bbox, difficult_flag=1)
image_id += 1
return coco