def convert(imgdir, annpath, result_dir):
'''
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
'''
coco_output = {}
coco_output['info'] = {
"description": "Example Dataset",
"url": "",
"version": "1.0",
"year": 2019,
"contributor": "Black Jack",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
coco_output['licenses'] = [{
"id":
1,
"name":
"Attribution-NonCommercial-ShareAlike License",
"url":
"http://creativecommons.org/licenses/by-nc-sa/2.0/"
}]
coco_output['categories'] = [{
"supercategory": "fish",
"id": 1,
"name": "fish",
"keypoints": [
"Head",
"Caudal",
],
"skeleton": [
[1, 2],
]
}]
coco_output['images'] = []
coco_output['annotations'] = []
ann = json.load(open(annpath))
# annotations id start from zero
ann_id = 0
num_invalid_images = 0
cat_id = 1 # 我直接默认所有类别为"fish"，所以只有一个cat_id，其值为1
iscrowd = 0
#in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
ann_num = 0
regions = ann[key]["regions"]
shapes = [r['shape_attributes']['name'] for r in regions]
if 'polygon' not in shapes:
continue
i1 = shapes.index('polygon')
region_polygon = regions[i1]
points_x = region_polygon['shape_attributes']['all_points_x']
points_y = region_polygon['shape_attributes']['all_points_y']
# if filename == 'data2_385.0.png':
# print(len(points_x), len(points_y), 'polygonlen')
assert len(points_x) == len(points_y), \
"in via json file polygon, length of all_points_x must equal to length of all_points_y. "
area = getArea.GetAreaOfPolyGon(points_x, points_y)
if not area:
continue
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x - min_x, max_y - min_y]
# 仔细分析json分拣，VIA直接导出的COCO格式的json文件其实是不对的，使用mmdetection库进行训练时，根本不能识别出标注数据。
# 其中非常明显的就是 segmentation不对。
segmentation = get_segmenation(points_x, points_y)
# keypoints
kp_names = ['head', 'tail']
keypoints = [0] * (len(kp_names) * 3)
ik = [i for i, r in enumerate(shapes) if r == 'point']
num_keypoints = len(ik)
if len(ik) > 0:
for i, kp_name in enumerate(kp_names):
for ik_ in ik:
region_kp = regions[ik_]
if kp_name in region_kp["region_attributes"].values():
keypoints[i * 3 +
0] = region_kp["shape_attributes"]["cx"]
keypoints[i * 3 +
1] = region_kp["shape_attributes"]["cy"]
keypoints[i * 3 + 2] = 2
break
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cat_id, iscrowd,
area, box, segmentation, keypoints,
num_keypoints)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
ann_num += 1
if ann_num > 0:
filename = ann[key]['filename']
print(filename)
img = cv2.imread(osp.join(imgdir, filename))
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id, os.path.basename(filename),
img.shape[:2])
coco_output['images'].append(image_info)
shutil.copy(osp.join(imgdir, filename),
osp.join(result_dir, 'imgs', filename))
else:
num_invalid_images += 1
print('total invalid image number is {}'.format(num_invalid_images))
return coco_output
def convert(imgdir, annpath, result_dir):
'''
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
'''
coco_output = {}
coco_output['info'] = {
"description": "Example Dataset",
"url": "",
"version": "1.0",
"year": 2019,
"contributor": "Black Jack",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
coco_output['licenses'] = [{
"id":
1,
"name":
"Attribution-NonCommercial-ShareAlike License",
"url":
"http://creativecommons.org/licenses/by-nc-sa/2.0/"
}]
coco_output['categories'] = [{
"supercategory": "fish",
"id": 1,
"name": "fish",
"keypoints": [
"Head",
"Caudal",
],
"skeleton": [
[1, 2],
]
}]
coco_output['images'] = []
coco_output['annotations'] = []
ann = json.load(open(annpath))
# annotations id start from zero
ann_id = 0
num_invalid_images = 0
cat_id = 1 # 我直接默认所有类别为"fish"，所以只有一个cat_id，其值为1
iscrowd = 0
kp_names = ['Head', 'Caudal']
#in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
ann_num = 0
lab = ann[key]
filename = lab["filename"]
img_path = osp.join(imgdir, filename)
scatter_kps = [
(reg["region_attributes"]["keypoint"],
reg["shape_attributes"]["cx"], reg["shape_attributes"]["cy"])
# (kp_name, x, y)
for reg in lab["regions"]
if reg["shape_attributes"]["name"] == "point"
and "keypoint" in reg["region_attributes"].keys()
]
mask_polygons = [
list(
zip(reg["shape_attributes"]["all_points_x"],
reg["shape_attributes"]["all_points_y"]))
for reg in lab["regions"]
if reg["shape_attributes"]["name"] == "polygon"
]
if len(mask_polygons) < 0 or not osp.exists(img_path):
continue
img = cv2.imread(img_path)
for polygon in mask_polygons:
points_x = []
points_y = []
for x, y in polygon:
points_x.append(x)
points_y.append(y)
mask = np.zeros_like(img[:, :, 0])
mask = cv2.fillPoly(
img=mask,
pts=[np.expand_dims(np.array(polygon), axis=1)],
color=(1, ))
keypoints = []
num_keypoints = 0
for kp_name in kp_names:
chosen = None
candidates = [kp for kp in scatter_kps if kp[0] == kp_name]
for kp in candidates:
if mask[kp[2], kp[1]] == 1:
chosen = [kp[1], kp[2], 2] # (x, y, visibility)
num_keypoints += 1
break
if chosen is None:
chosen = [0, 0, 0]
keypoints.extend(chosen)
assert len(points_x) == len(points_y), \
"in via json file polygon, length of all_points_x must equal to length of all_points_y. "
area = getArea.GetAreaOfPolyGon(points_x, points_y)
if not area:
continue
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x - min_x, max_y - min_y]
# 仔细分析json分拣，VIA直接导出的COCO格式的json文件其实是不对的，使用mmdetection库进行训练时，根本不能识别出标注数据。
# 其中非常明显的就是 segmentation不对。
segmentation = get_segmenation(points_x, points_y)
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cat_id, iscrowd,
area, box, segmentation,
keypoints, num_keypoints)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
ann_num += 1
if ann_num > 0:
print(filename)
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id, os.path.basename(filename),
img.shape[:2])
coco_output['images'].append(image_info)
shutil.copy(img_path, osp.join(result_dir, 'imgs', filename))
else:
num_invalid_images += 1
print('total invalid image number is {}'.format(num_invalid_images))
return coco_output
def convert(imgdir, annpath, result_path):
'''
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
'''
via_output = {}
ann = json.load(open(annpath))
# annotations id start from zero
num_invalid_images = 0
#in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
imgs_valid_list = os.listdir(imgdir)
regions = ann[key]["regions"]
filename = ann[key]['filename']
size = ann[key]["size"]
if filename not in imgs_valid_list:
continue
# img = cv2.imread(os.path.join(imgdir, filename))
num_mask = 0
regions_new = []
# for one image ,there are many regions,they share the same img id
for region in regions:
# # 这里也需要修改。原作者是region['region_attributes']['label'],
# # #但是其实应该是region['region_attributes']['supercategory_name']
# cat = region['region_attributes']['type'] #我的返回的子类的编号，所以其实不需要这一段，
# print(cat)
# assert cat in ['fish',]# 如果你的返回的是子类名字。那么这一段就需要。assert cat in ['name1', 'name2', 'name3',...]
# if cat == 'fish': # if cat == 'name1':
# cat_id = 1
cat_id = 1 # 我直接默认所有类别为"fish"，所以只有一个cat_id，其值为1
iscrowd = 0
if 'cx' in region['shape_attributes']:
regions_new.append(region)
continue
points_x = region['shape_attributes']['all_points_x']
points_y = region['shape_attributes']['all_points_y']
# if filename == 'data2_385.0.png':
# print(len(points_x), len(points_y), 'polygonlen')
assert len(points_x) == len(points_y), \
"in via json file polygon, length of all_points_x must equal to length of all_points_y. "
area = getArea.GetAreaOfPolyGon(points_x, points_y)
if area <= 0:
continue
# min_x = min(points_x)
# max_x = max(points_x)
# min_y = min(points_y)
# max_y = max(points_y)
# box = [min_x, min_y, max_x-min_x, max_y-min_y]
# # patch = img[min_y: max_y, min_x: max_x]
# # patch_name = filename[:-4]+'_'+str(num_mask)+'.jpg'
# # cv2.imwrite(os.path.join(result_path, patch_name), patch)
# points_x = [i - min_x for i in points_x]
# points_y = [i - min_y for i in points_y]
region_new = {
"shape_attributes": {
"name": "polygon",
"all_points_x": points_x,
"all_points_y": points_y
},
"region_attributes": {
"type": "fish"
}
}
regions_new.append(region_new)
num_mask += 1
if num_mask > 0:
shutil.copy(os.path.join(imgdir, filename),
os.path.join(result_path, filename))
print(filename)
else:
num_invalid_images += 1
via_output[filename + str(size)] = {
'filename': filename,
'size': size,
'regions': regions_new,
"file_attributes": {}
}
print('total invalid image number is {}'.format(num_invalid_images))
return via_output
def vgg_to_labelme(img_dir, out_dir):
'''
:param img_dir: 图片和json文件位于同一个目录下
:param out_dir: 输出路径
:return:
'''
# 获取所有json文件全路径
vgg_json = glob.glob(os.path.join(img_dir, "*.json"))
# 遍历文件夹中所有的json文件
for num, json_file in enumerate(vgg_json):
coco_output = {}
coco_output['version'] = "4.2.9"
coco_output['flags'] = {}
coco_output['shapes'] = []
shapes_info = [] # shapes的结果
json_file_name = os.path.basename(json_file)
img_file_name = json_file_name.replace(".json", ".jpg")
img_path = os.path.join(img_dir, img_file_name)
img = cv2.imread(img_path)
# 用 base64 将图片保存为字符串
# 读取二进制图片，获得原始字节码，注意 'rb'
with open(img_path, 'rb') as jpg_file:
byte_content = jpg_file.read()
# 把原始字节码编码成 base64 字节码
base64_bytes = b64encode(byte_content)
# 将 base64 字节码解码成 utf-8 格式的字符串
base64_string = base64_bytes.decode('utf-8')
data = json.load(open(json_file))
for img_id, key in enumerate(data.keys()):
filename = data[key]['filename']
regions = data[key]["regions"]
for region in regions:
shapes_sample = {}
shape_att = region["shape_attributes"]
if shape_att['name'] == 'polygon':
shapes_sample['label'] = 'building'
all_points_x = shape_att["all_points_x"]
all_points_y = shape_att["all_points_y"]
area = getArea.GetAreaOfPolyGon(all_points_x, all_points_y)
points = _get_point(all_points_x, all_points_y)
shapes_sample['points'] = points
shapes_sample['group_id'] = None
shapes_sample['shape_type'] = "polygon"
shapes_sample['flags'] = {}
#shapes_sample['area'] = area
if area < 2:
continue
shapes_info.append(shapes_sample)
coco_output["shapes"] = shapes_info
coco_output['imagePath'] = os.path.basename(img_file_name)
coco_output['imageData'] = base64_string
coco_output['imageHeight'] = img.shape[0]
coco_output['imageWidth'] = img.shape[1]
# 把结果导出json文件
out_path = os.path.join(out_dir, json_file_name)
with open(out_path, 'w', encoding='utf8') as file_obj:
json.dump(coco_output, file_obj, indent=2)
def convert(VIA_ORIGINAL_ANNOTATIONS_NAME, imgdir, annpath):
"""
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
"""
annotations = json.load(
open(VIA_ORIGINAL_ANNOTATIONS_NAME, encoding="utf-8"))
annotations = list(annotations.values()) # don't need the dict keys
annotations = [a for a in annotations if a['regions']]
name_supercategory_dict = {}
for a in annotations:
names = [r['region_attributes']['name'] for r in a['regions']]
supercategories = ["part" for r in a['regions']]
for index, name in enumerate(names):
if name not in name_supercategory_dict.keys():
name_supercategory_dict[name] = supercategories[index]
coco_output = {}
coco_output['info'] = {
"description": "CAR Dataset",
"url": "https://github.com/Lplenka/",
"version": "0.1.0",
"year": 2020,
"contributor": "Lplenka",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
coco_output['licenses'] = [{
"id":
1,
"name":
"Attribution-NonCommercial-ShareAlike License",
"url":
"http://creativecommons.org/licenses/by-nc-sa/2.0/"
}]
# coco_output['categories'] = [{
# 'id': 1,
# 'name': "中性杆状核粒细胞",
# 'supercategory': "粒細胞系",
# },
# {
# 'id': 2,
# 'name': '中性中幼粒细胞',
# 'supercategory': '粒細胞系',
# },
# .
# .
# .
# ]
# get the coco category from dict
coco_output['categories'] = []
for i in range(len(name_supercategory_dict)):
category = {
'id':
i + 1,
'name':
list(name_supercategory_dict)[i],
'supercategory':
name_supercategory_dict[list(name_supercategory_dict)[i]]
}
coco_output['categories'].append(category)
coco_output['images'] = []
coco_output['annotations'] = []
##########################################################################################################
ann = json.load(open(annpath, encoding="utf-8"))
# annotations id start from zero
ann_id = 0
# in VIA annotations, [key]['filename'] are image name
for img_id, key in enumerate(ann.keys()):
filename = ann[key]['filename']
img = cv2.imread(imgdir + filename)
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id, os.path.basename(filename),
img.shape[:2])
coco_output['images'].append(image_info)
regions = ann[key]["regions"]
# for one image ,there are many regions,they share the same img id
for region in regions:
cate = region['region_attributes']['name']
# cate must in categories
assert cate in [i['name'] for i in coco_output['categories']]
# get the cate_id
cate_id = 0
for category in coco_output['categories']:
if cate == category['name']:
cate_id = category['id']
####################################################################################################
iscrowd = 0
points_x = region['shape_attributes']['all_points_x']
points_y = region['shape_attributes']['all_points_y']
area = getArea.GetAreaOfPolyGon(points_x, points_y)
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x - min_x, max_y - min_y]
segmentation = get_segmenation(points_x, points_y)
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cate_id, iscrowd,
area, box, segmentation)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
return coco_output
def convert(imgdir, annpath):
'''
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
'''
coco_output = {}
coco_output['info'] = {
"description": "Example Dataset",
"url": "https://triasoft.wordpress.com/",
"version": "0.1.0",
"year": 2019,
"contributor": "schwabse",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
coco_output['licenses'] = [{
"id":
1,
"name":
"Attribution-NonCommercial-ShareAlike License",
"url":
"http://creativecommons.org/licenses/by-nc-sa/2.0/"
}]
coco_output['categories'] = [{
'id': 1,
'name': 'vertebrae',
'supercategory': 'spine',
}, {
'id': 2,
'name': 'vertebrae',
'supercategory': 'spine',
}]
coco_output['images'] = []
coco_output['annotations'] = []
ann = json.load(open(annpath))
# annotations id start from zero
ann_id = 0
# in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
filename = ann[key]['filename']
img = cv2.imread(imgdir + filename)
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id, os.path.basename(filename),
img.shape[:2])
coco_output['images'].append(image_info)
regions = ann[key]["regions"]
# for one image ,there are many regions,they share the same img id
for region in regions:
cur = regions[region]
try:
cat = cur['region_attributes']['label']
print(cat)
assert cat in ['vertebrae', 'S']
except:
cat = ''
if cat == 'rib':
cat_id = 1
else:
cat_id = 2
iscrowd = 0
points_x = cur['shape_attributes']['all_points_x']
points_y = cur['shape_attributes']['all_points_y']
area = getArea.GetAreaOfPolyGon(points_x, points_y)
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x - min_x, max_y - min_y]
segmentation = get_segmenation(points_x, points_y)
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cat_id, iscrowd,
area, box, segmentation)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
return coco_output
def convert(imgdir, annpath, result_dir):
'''
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
'''
coco_output = {}
coco_output['info'] = {
"description": "Example Dataset",
"url": "",
"version": "1.0",
"year": 2019,
"contributor": "Black Jack",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
coco_output['licenses'] = [{
"id":
1,
"name":
"Attribution-NonCommercial-ShareAlike License",
"url":
"http://creativecommons.org/licenses/by-nc-sa/2.0/"
}]
coco_output['categories'] = [
{
'id': 1,
'name': 'shrimp',
'supercategory': 'allShrimp',
},
]
coco_output['images'] = []
coco_output['annotations'] = []
ann = json.load(open(annpath))
# annotations id start from zero
ann_id = 0
num_invalid_images = 0
cat_id = 1 # 我直接默认所有类别为"fish"，所以只有一个cat_id，其值为1
iscrowd = 0
#in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
ann_num = 0
regions = ann[key]["regions"]
filename = ann[key]['filename']
img_path = osp.join(imgdir, filename)
if not osp.exists(img_path):
continue
# for one image ,there are many regions,they share the same img id
for region in regions:
if region['shape_attributes']['name'] == "point":
x = region['shape_attributes']['x']
y = region['shape_attributes']['y']
width = region['shape_attributes']['width']
height = region['shape_attributes']['height']
box = [x, y, width, height]
area = 0
segmentation = [[]]
ann_info = create_annotation_info(ann_id, img_id, cat_id,
iscrowd, area, box,
segmentation)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
# # 这里也需要修改。原作者是region['region_attributes']['label'],
# # #但是其实应该是region['region_attributes']['supercategory_name']
# cat = region['region_attributes']['type'] #我的返回的子类的编号，所以其实不需要这一段，
# print(cat)
# assert cat in ['fish',]# 如果你的返回的是子类名字。那么这一段就需要。assert cat in ['name1', 'name2', 'name3',...]
# if cat == 'fish': # if cat == 'name1':
# cat_id = 1
elif region['shape_attributes']['name'] == "polygon":
points_x = region['shape_attributes']['all_points_x']
points_y = region['shape_attributes']['all_points_y']
# if filename == 'data2_385.0.png':
# print(len(points_x), len(points_y), 'polygonlen')
assert len(points_x) == len(points_y), \
"in via json file polygon, length of all_points_x must equal to length of all_points_y. "
area = getArea.GetAreaOfPolyGon(points_x, points_y)
if not area:
continue
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x - min_x, max_y - min_y]
# 仔细分析json分拣，VIA直接导出的COCO格式的json文件其实是不对的，使用mmdetection库进行训练时，根本不能识别出标注数据。
#其中非常明显的就是 segmentation不对。
segmentation = get_segmenation(points_x, points_y)
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cat_id,
iscrowd, area, box,
segmentation)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
ann_num += 1
if ann_num > 0:
print(filename)
img = cv2.imread(img_path)
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id, os.path.basename(filename),
img.shape[:2])
coco_output['images'].append(image_info)
shutil.copy(img_path, osp.join(result_dir, 'imgs', filename))
else:
num_invalid_images += 1
print('total invalid image number is {}'.format(num_invalid_images))
return coco_output
def convert(
imgdir,
annpath,
categories=None,
super_categories=None,
output_file_name=None,
first_class_index=1, # typically, 0 or 1
):
"""
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
"""
if categories is None:
categories = ["rib", "clavicle"]
default_category = categories[0]
category_dict = dict()
for (cat_id, cat_name) in enumerate(categories, start=first_class_index):
category_dict[cat_name] = cat_id
if super_categories is None:
default_super_category = "bone"
super_categories = [default_super_category for _ in categories]
coco_output = {}
coco_output["info"] = {
"description": "Example Dataset",
"url": "https://github.com/waspinator/pycococreator",
"version": "0.1.0",
"year": 2018,
"contributor": "waspinator",
"date_created": datetime.datetime.utcnow().isoformat(" "),
}
coco_output["licenses"] = [{
"id":
1,
"name":
"Attribution-NonCommercial-ShareAlike License",
"url":
"http://creativecommons.org/licenses/by-nc-sa/2.0/",
}]
coco_output["categories"] = [{
"id": category_dict[cat_name],
"name": cat_name,
"supercategory": super_cat_name,
} for (cat_name, super_cat_name) in zip(categories, super_categories)]
coco_output["images"] = []
coco_output["annotations"] = []
ann = json.load(open(annpath))
# annotations id start from zero
ann_id = 0
# in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
filename = ann[key]["filename"]
img = Image.open(imgdir + filename)
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id,
os.path.basename(filename),
image_size=img.size)
# Caveat: image shapes are conventionally (height, width) whereas image sizes are conventionally (width, height)
# References:
# - https://note.nkmk.me/en/python-opencv-pillow-image-size/
# - https://github.com/facebookresearch/detectron2/blob/master/detectron2/data/detection_utils.py#L189
coco_output["images"].append(image_info)
regions = ann[key]["regions"]
# for one image ,there are many regions,they share the same img id
for region in regions:
region_attributes = regions[region]["region_attributes"]
try:
cat_name = region_attributes["label"]
except KeyError:
cat_name = default_category
try:
cat_id = category_dict[cat_name]
except KeyError:
print("Skipping unknown category {} in {}".format(
cat_name, filename))
continue
iscrowd = 0
shape_attributes = regions[region]["shape_attributes"]
points_x = shape_attributes["all_points_x"]
points_y = shape_attributes["all_points_y"]
area = getArea.GetAreaOfPolyGon(points_x, points_y)
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x - min_x, max_y - min_y]
segmentation = get_segmenation(points_x, points_y)
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cat_id, iscrowd,
area, box, segmentation)
coco_output["annotations"].append(ann_info)
ann_id = ann_id + 1
if output_file_name is not None:
print("Saving to {}".format(output_file_name))
with open(output_file_name, "w") as f:
json.dump(coco_output, f)
return coco_output
def convert(xmls):
json_dict = {
"images": [],
"type": "instances",
"annotations": [],
"categories": []
}
bnd_id = START_BOUNDING_BOX_ID
image_id = START_IMAGE_ID
# categories = ['人物', '背景', '天空', '轿车', '其他', '巴士', '狗', '马']
for i, xml in enumerate(xmls):
print(i, xml)
name = xml.split('/')[-1].replace('.xml', '.jpg')
tree = ET.parse(xml)
root = tree.getroot()
size = get_and_check(root, 'size', 1)
width = int(get_and_check(size, 'width', 1).text)
height = int(get_and_check(size, 'height', 1).text)
image = {
'file_name': name,
'height': height,
'width': width,
'id': image_id
}
json_dict['images'].append(image)
for obj in get(root, 'object'):
category = get_and_check(obj, 'name', 1).text
# if category not in categories:
# categories.append(category)
try:
category_id = CATEGORIES[category]
bndbox = get_and_check(obj, 'bndbox', 1)
assert len(bndbox) % 2 == 0
points = []
for i in range(len(bndbox) // 2):
points.append(
float(
get_and_check(bndbox, 'x{}'.format(i + 1),
1).text))
points.append(
float(
get_and_check(bndbox, 'y{}'.format(i + 1),
1).text))
all_x, all_y = points[0::2], points[1::2]
xmin, xmax = min(all_x), max(all_x)
ymin, ymax = min(all_y), max(all_y)
o_width = xmax - xmin
o_height = ymax - ymin
area = getArea.GetAreaOfPolyGon(all_x, all_y)
ann = {
'image_id': image_id,
'bbox': [xmin, ymin, o_width, o_height],
'area': area,
'iscrowd': 0,
'ignore': 0,
'category_id': category_id,
'id': bnd_id,
'segmentation': [points]
}
json_dict['annotations'].append(ann)
bnd_id += 1
except:
continue
image_id += 1
categories = [
{
'supercategory': 'background',
'id': 0,
'name': 'background'
},
{
'supercategory': 'person',
'id': 1,
'name': 'person'
},
{
'supercategory': 'dog',
'id': 3,
'name': 'dog'
},
]
json_dict['catgories'] = categories
return json_dict
def convert(imgdir, annpath):
'''
:param imgdir: directory for your images
:param annpath: path for your annotations
:return: coco_output is a dictionary of coco style which you could dump it into a json file
as for keywords 'info','licenses','categories',you should modify them manually
'''
coco_output = {}
coco_output['info'] = {
"description": "Example Dataset",
"url": "",
"version": "1.0",
"year": 2019,
"contributor": "Black Jack",
"date_created": datetime.datetime.utcnow().isoformat(' ')
}
coco_output['licenses'] = [
{
"id": 1,
"name": "Attribution-NonCommercial-ShareAlike License",
"url": "http://creativecommons.org/licenses/by-nc-sa/2.0/"
}
]
coco_output['categories'] = [
{
'id': 1,
'name': 'papercup',
'supercategory': 'rubbish',
},
{
'id': 2,
'name': 'can',
'supercategory': 'rubbish',
},
{
'id': 3,
'name': 'plasticbottle',
'supercategory': 'rubbish',
},
{
'id': 4,
'name': 'hand',
'supercategory': 'rubbish',
}
]
coco_output['images'] = []
coco_output['annotations'] = []
ann = json.load(open(annpath))
# annotations id start from zero
ann_id = 0
#in VIA annotations, keys are image name
for img_id, key in enumerate(ann.keys()):
filename = ann[key]['filename']
print(filename)
img = cv2.imread(imgdir+filename)
# make image info and storage it in coco_output['images']
image_info = create_image_info(img_id, os.path.basename(filename), img.shape[:2])
coco_output['images'].append(image_info)
regions = ann[key]["regions"]
# for one image ,there are many regions,they share the same img id
for region in regions:
# 这里也需要修改。原作者是region['region_attributes']['label'],
# #但是其实应该是region['region_attributes']['supercategory_name']
cat = region['region_attributes']['rubbish'] #我的返回的子类的编号，所以其实不需要这一段，
print(cat)
assert cat in ['1', '2', '3', '4']# 如果你的返回的是子类名字。那么这一段就需要。assert cat in ['name1', 'name2', 'name3',...]
if cat == '1': # if cat == 'name1':
cat_id = 1
elif cat == '2':
cat_id = 2
elif cat == '3':
cat_id = 3
else:
cat_id = 4
iscrowd = 0
points_x = region['shape_attributes']['all_points_x']
points_y = region['shape_attributes']['all_points_y']
area = getArea.GetAreaOfPolyGon(points_x, points_y)
min_x = min(points_x)
max_x = max(points_x)
min_y = min(points_y)
max_y = max(points_y)
box = [min_x, min_y, max_x-min_x, max_y-min_y]
# 仔细分析json分拣，VIA直接导出的COCO格式的json文件其实是不对的，使用mmdetection库进行训练时，根本不能识别出标注数据。
#其中非常明显的就是 segmentation不对。
segmentation = get_segmenation(points_x, points_y)
# make annotations info and storage it in coco_output['annotations']
ann_info = create_annotation_info(ann_id, img_id, cat_id, iscrowd, area, box, segmentation)
coco_output['annotations'].append(ann_info)
ann_id = ann_id + 1
return coco_output