本流程主要是在mmdet上使用，前五个步骤为数据集制作步骤，后面为在mmdet版本使用步骤
1.在网上下载coco数据集
2.安装COCOAPI（Linux版本）
git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
cd $COCOAPI/PythonAPI
make
python3.7 setup.py install --user #Python版本改为自己对应的3.提取特定类别（此处借鉴其他博主内容，可以使用此代码提取多个类别，提取类别时，测试集和训练集是根据图片中的类别标定类别id的，因此后续需要进行更改，此处是一个小坑！https://blog.csdn.net/weixin_40922744/article/details/111180137：）
from pycocotools.coco import COCO
import os
import shutil
from tqdm import tqdm
import skimage.io as io
import matplotlib.pyplot as plt
import cv2
from PIL import Image, ImageDraw
# 需要设置的路径
savepath = "/data1/bhuang/4/"
img_dir = savepath + 'images/'
anno_dir = savepath + 'annotations/'
datasets_list = ['val2017']
# coco有80类，这里写要提取类的名字，以person为例
classes_names = ['person']
# 提取多个类别示例：classes_names = ['person','car','train']
# 包含所有类别的原coco数据集路径
# 包含所有类别的原coco数据集路径
'''
目录格式如下：
$COCO_PATH
----|annotations
----|train2017
----|val2017
----|test2017
'''
dataDir = '/data1/bhuang/coco/annotations_trainval2017/'
headstr = """\
<annotation>
<folder>VOC</folder>
<filename>%s</filename>
<source>
<database>My Database</database>
<annotation>COCO</annotation>
<image>flickr</image>
<flickrid>NULL</flickrid>
</source>
<owner>
<flickrid>NULL</flickrid>
<name>company</name>
</owner>
<size>
<width>%d</width>
<height>%d</height>
<depth>%d</depth>
</size>
<segmented>0</segmented>
"""
objstr = """\
<object>
<name>%s</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>%d</xmin>
<ymin>%d</ymin>
<xmax>%d</xmax>
<ymax>%d</ymax>
</bndbox>
</object>
"""
tailstr = '''\
</annotation>
'''
# 检查目录是否存在，如果存在，先删除再创建，否则，直接创建
def mkr(path):
if not os.path.exists(path):
os.makedirs(path) # 可以创建多级目录
def id2name(coco):
classes = dict()
for cls in coco.dataset['categories']:
classes[cls['id']] = cls['name']
return classes
def write_xml(anno_path, head, objs, tail):
f = open(anno_path, "w")
f.write(head)
for obj in objs:
f.write(objstr % (obj[0], obj[1], obj[2], obj[3], obj[4]))
f.write(tail)
def save_annotations_and_imgs(coco, dataset, filename, objs):
# 将图片转为xml，例:COCO_train2017_000000196610.jpg-->COCO_train2017_000000196610.xml
dst_anno_dir = os.path.join(anno_dir, dataset)
mkr(dst_anno_dir)
anno_path = dst_anno_dir + '/' + filename[:-3] + 'xml'
img_path = dataDir + dataset + '/' + filename
print("img_path: ", img_path)
dst_img_dir = os.path.join(img_dir, dataset)
mkr(dst_img_dir)
dst_imgpath = dst_img_dir + '/' + filename
print("dst_imgpath: ", dst_imgpath)
img = cv2.imread(img_path)
# if (img.shape[2] == 1):
# print(filename + " not a RGB image")
# return
shutil.copy(img_path, dst_imgpath)
head = headstr % (filename, img.shape[1], img.shape[0], img.shape[2])
tail = tailstr
write_xml(anno_path, head, objs, tail)
def showimg(coco, dataset, img, classes, cls_id, show=True):
global dataDir
I = Image.open('%s/%s/%s' % (dataDir, dataset, img['file_name']))
# 通过id，得到注释的信息
annIds = coco.getAnnIds(imgIds=img['id'], catIds=cls_id, iscrowd=None)
# print(annIds)
anns = coco.loadAnns(annIds)
# print(anns)
# coco.showAnns(anns)
objs = []
for ann in anns:
class_name = classes[ann['category_id']]
if class_name in classes_names:
print(class_name)
if 'bbox' in ann:
bbox = ann['bbox']
xmin = int(bbox[0])
ymin = int(bbox[1])
xmax = int(bbox[2] + bbox[0])
ymax = int(bbox[3] + bbox[1])
obj = [class_name, xmin, ymin, xmax, ymax]
objs.append(obj)
draw = ImageDraw.Draw(I)
draw.rectangle([xmin, ymin, xmax, ymax])
if show:
plt.figure()
plt.axis('off')
plt.imshow(I)
plt.show()
return objs
for dataset in datasets_list:
# ./COCO/annotations/instances_train2017.json
annFile = '{}/annotations/instances_{}.json'.format(dataDir, dataset)
# 使用COCO API用来初始化注释数据
coco = COCO(annFile)
# 获取COCO数据集中的所有类别
classes = id2name(coco)
print(classes)
# [1, 2, 3, 4, 6, 8]
classes_ids = coco.getCatIds(catNms=classes_names)
print(classes_ids)
for cls in classes_names:
# 获取该类的id
cls_id = coco.getCatIds(catNms=[cls])
img_ids = coco.getImgIds(catIds=cls_id)
print(cls, len(img_ids))
# imgIds=img_ids[0:10]
for imgId in tqdm(img_ids):
img = coco.loadImgs(imgId)[0]
filename = img['file_name']
# print(filename)
objs = showimg(coco, dataset, img, classes, classes_ids, show=False)
print(objs)
save_annotations_and_imgs(coco, dataset, filename, objs)
4.提取完成后得到的是xml格式文件，划分数据集后再进行转换。按照6:2:2或者8:2划分数据集（有两个数据集划分代码，第二个无法同时划分图片和标注文件）
# 将图片和标注数据按比例切分为 训练集和测试集
import os
import random
from shutil import copy2
# 原始路径
image_original_path = "/data1/bhuang/3/images/train2017/"
label_original_path = "/data1/bhuang/3/annotations/train2017/"
# 上级目录
# parent_path = os.path.dirname(os.getcwd())
# parent_path = "D:\\AI_Find"
# 训练集路径
# train_image_path = os.path.join(parent_path, "image_data/seed/train/images/")
# train_label_path = os.path.join(parent_path, "image_data/seed/train/labels/")
train_image_path = os.path.join("/data1/bhuang/5/train/images/")
train_label_path = os.path.join("/data1/bhuang/5/train/annotations/")
# 测试集路径
test_image_path = os.path.join("/data1/bhuang/5/test/images/")
test_label_path = os.path.join("/data1/bhuang/5/test/annotations/")
# test_image_path = os.path.join(parent_path, 'image_data/seed/val/images/')
# test_label_path = os.path.join(parent_path, 'image_data/seed/val/labels/')
# 检查文件夹是否存在
def mkdir():
if not os.path.exists(train_image_path):
os.makedirs(train_image_path)
if not os.path.exists(train_label_path):
os.makedirs(train_label_path)
if not os.path.exists(test_image_path):
os.makedirs(test_image_path)
if not os.path.exists(test_label_path):
os.makedirs(test_label_path)
def main():
mkdir()
# 复制移动图片数据
all_image = os.listdir(image_original_path)
for i in range(len(all_image)):
num = random.randint(1,5)#随机给图片赋值，每五个随机赋值一次，抽取不为2的图片
if num != 2:
copy2(os.path.join(image_original_path, all_image[i]), train_image_path)
train_index.append(i)
else:
copy2(os.path.join(image_original_path, all_image[i]), test_image_path)
val_index.append(i)
# 复制移动标注数据
all_label = os.listdir(label_original_path)
for i in train_index:
copy2(os.path.join(label_original_path, all_label[i]), train_label_path)
for i in val_index:
copy2(os.path.join(label_original_path, all_label[i]), test_label_path)
if __name__ == '__main__':
train_index = []
val_index = []
main()
# *_*coding: utf-8 *_*
# Author --LiMing--
import os
import random
import shutil
import time
def copyFile(fileDir, class_name):
image_list = os.listdir(fileDir) # 获取图片的原始路径
image_number = len(image_list)
train_number = int(image_number * train_rate)
train_sample = random.sample(image_list, train_number) # 从image_list中随机获取0.8比例的图像.
test_sample = list(set(image_list) - set(train_sample))
sample = [train_sample, test_sample]
# 复制图像到目标文件夹
for k in range(len(save_dir)):
if os.path.isdir(save_dir[k] + class_name):
for name in sample[k]:
shutil.copy(os.path.join(fileDir, name), os.path.join(save_dir[k] + class_name+'/', name))
else:
os.makedirs(save_dir[k] + class_name)
for name in sample[k]:
shutil.copy(os.path.join(fileDir, name), os.path.join(save_dir[k] + class_name+'/', name))
if __name__ == '__main__':
time_start = time.time()
# 原始数据集路径
origion_path = '/data1/bhuang/3/'
#origion_path = '/data1/bhuang/3/images/'
# 保存路径
# save_train_dir = '/data1/bhuang/5/images/train/images/'
# save_test_dir = '/data1/bhuang/5/images/val/images/'
save_train_dir = '/data1/bhuang/5/'
save_test_dir = '/data1/bhuang/5/'
save_dir = [save_train_dir, save_test_dir]
# 训练集比例
train_rate = 0.8
# 数据集类别及数量
file_list = os.listdir(origion_path)
num_classes = len(file_list)
for i in range(num_classes):
class_name = file_list[i]
image_Dir = os.path.join(origion_path, class_name)
copyFile(image_Dir, class_name)
print('%s划分完毕！' % class_name)
time_end = time.time()
print('---------------')
print('训练集和测试集划分共耗时%s!' % (time_end - time_start))5.划分完数据集对标注文件转换成json格式（转换完成后特制小型coco数据集制作完成）
import xml.etree.ElementTree as ET
import os
import json
coco = dict()
coco['images'] = []
coco['type'] = 'instances'
coco['annotations'] = []
coco['categories'] = []
category_set = dict()
image_set = set()
category_item_id = 0
image_id = 20180000000
annotation_id = 0
def addCatItem(name):
global category_item_id
category_item = dict()
category_item['supercategory'] = 'none'
category_item_id += 1
category_item['id'] = category_item_id
category_item['name'] = name
coco['categories'].append(category_item)
category_set[name] = category_item_id
return category_item_id
def addImgItem(file_name, size):
global image_id
if file_name is None:
raise Exception('Could not find filename tag in xml file.')
if size['width'] is None:
raise Exception('Could not find width tag in xml file.')
if size['height'] is None:
raise Exception('Could not find height tag in xml file.')
image_id += 1
image_item = dict()
image_item['id'] = image_id
image_item['file_name'] = file_name
image_item['width'] = size['width']
image_item['height'] = size['height']
coco['images'].append(image_item)
image_set.add(file_name)
return image_id
def addAnnoItem(object_name, image_id, category_id, bbox):
global annotation_id
annotation_item = dict()
annotation_item['segmentation'] = []
seg = []
# bbox[] is x,y,w,h
# left_top
seg.append(bbox[0])
seg.append(bbox[1])
# left_bottom
seg.append(bbox[0])
seg.append(bbox[1] + bbox[3])
# right_bottom
seg.append(bbox[0] + bbox[2])
seg.append(bbox[1] + bbox[3])
# right_top
seg.append(bbox[0] + bbox[2])
seg.append(bbox[1])
annotation_item['segmentation'].append(seg)
annotation_item['area'] = bbox[2] * bbox[3]
annotation_item['iscrowd'] = 0
annotation_item['ignore'] = 0
annotation_item['image_id'] = image_id
annotation_item['bbox'] = bbox
annotation_item['category_id'] = category_id
annotation_id += 1
annotation_item['id'] = annotation_id
coco['annotations'].append(annotation_item)
def parseXmlFiles(xml_path):
for f in os.listdir(xml_path):
if not f.endswith('.xml'):
continue
bndbox = dict()
size = dict()
current_image_id = None
current_category_id = None
file_name = None
size['width'] = None
size['height'] = None
size['depth'] = None
xml_file = os.path.join(xml_path, f)
print(xml_file)
tree = ET.parse(xml_file)
root = tree.getroot()
if root.tag != 'annotation':
raise Exception('pascal voc xml root element should be annotation, rather than {}'.format(root.tag))
# elem is <folder>, <filename>, <size>, <object>
for elem in root:
current_parent = elem.tag
current_sub = None
object_name = None
if elem.tag == 'folder':
continue
if elem.tag == 'filename':
file_name = elem.text
if file_name in category_set:
raise Exception('file_name duplicated')
# add img item only after parse <size> tag
elif current_image_id is None and file_name is not None and size['width'] is not None:
if file_name not in image_set:
current_image_id = addImgItem(file_name, size)
print('add image with {} and {}'.format(file_name, size))
else:
raise Exception('duplicated image: {}'.format(file_name))
# subelem is <width>, <height>, <depth>, <name>, <bndbox>
for subelem in elem:
bndbox['xmin'] = None
bndbox['xmax'] = None
bndbox['ymin'] = None
bndbox['ymax'] = None
current_sub = subelem.tag
if current_parent == 'object' and subelem.tag == 'name':
object_name = subelem.text
if object_name not in category_set:
current_category_id = addCatItem(object_name)
else:
current_category_id = category_set[object_name]
elif current_parent == 'size':
if size[subelem.tag] is not None:
raise Exception('xml structure broken at size tag.')
size[subelem.tag] = int(subelem.text)
# option is <xmin>, <ymin>, <xmax>, <ymax>, when subelem is <bndbox>
for option in subelem:
if current_sub == 'bndbox':
if bndbox[option.tag] is not None:
raise Exception('xml structure corrupted at bndbox tag.')
bndbox[option.tag] = int(option.text)
# only after parse the <object> tag
if bndbox['xmin'] is not None:
if object_name is None:
raise Exception('xml structure broken at bndbox tag')
if current_image_id is None:
raise Exception('xml structure broken at bndbox tag')
if current_category_id is None:
raise Exception('xml structure broken at bndbox tag')
bbox = []
# x
bbox.append(bndbox['xmin'])
# y
bbox.append(bndbox['ymin'])
# w
bbox.append(bndbox['xmax'] - bndbox['xmin'])
# h
bbox.append(bndbox['ymax'] - bndbox['ymin'])
print('add annotation with {},{},{},{}'.format(object_name, current_image_id, current_category_id,
bbox))
addAnnoItem(object_name, current_image_id, current_category_id, bbox)
if __name__ == '__main__':
# 需要自己设定的地址，一个是已生成的是xml文件的父目录；一个是要生成的json文件的目录
xml_dir = r'/data1/bhuang/5/test/'
json_dir = r'/data1/bhuang/4/annotations/test/'
# dataset_lists = ['train2017', 'val2017']
dataset_lists = ['annotations']
for dataset in dataset_lists:
xml_path = os.path.join(xml_dir, dataset)
json_file = json_dir + '/instances_{}.json'.format(dataset)
parseXmlFiles(xml_path)
json.dump(coco, open(json_file, 'w'))
6.开始在mmdetection上使用，以Faster-rcnn为例
首先在configs/_base_/datasets/coco_detection.py中更改数据集路径
data = dict(
samples_per_gpu=1,
workers_per_gpu=1,
train=dict(
type=dataset_type,
ann_file=data_root + '5/annotations/train/instances_annotations.json',
img_prefix=data_root + '5/images/train/images/',
#CLASSES = CLASSES,
pipeline=train_pipeline),
val=dict(
type=dataset_type,
ann_file=data_root + '5/annotations/test/instances_annotations.json',
img_prefix=data_root + '5/images/test/images/',
#CLASSES = CLASSES,
pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + '5/annotations/test/instances_annotations.json',
img_prefix=data_root + '5/images/test/images/',
#CLASSES = CLASSES,
pipeline=test_pipeline))其次在mmdet/datasets/coco.py中更改coco类别（改成自己的类别）
class CocoDataset(CustomDataset):
CLASSES = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog')
# CLASSES = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
# 'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
# 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
# 'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
# 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
# 'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat',
# 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
# 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
# 'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
# 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
# 'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop',
# 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
# 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
# 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush')接下来在mmdet/core/evaluation/class_names.py中更改coco类别，必须和上面类别一一对应，第二个小坑
def coco_classes():
return [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
'truck', 'boat', 'traffic_light', 'fire_hydrant', 'stop_sign',
'parking_meter', 'bench', 'bird', 'cat', 'dog'
]
# return [
# 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
# 'truck', 'boat', 'traffic_light', 'fire_hydrant', 'stop_sign',
# 'parking_meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
# 'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella',
# 'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard',
# 'sports_ball', 'kite', 'baseball_bat', 'baseball_glove', 'skateboard',
# 'surfboard', 'tennis_racket', 'bottle', 'wine_glass', 'cup', 'fork',
# 'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange',
# 'broccoli', 'carrot', 'hot_dog', 'pizza', 'donut', 'cake', 'chair',
# 'couch', 'potted_plant', 'bed', 'dining_table', 'toilet', 'tv',
# 'laptop', 'mouse', 'remote', 'keyboard', 'cell_phone', 'microwave',
# 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase',
# 'scissors', 'teddy_bear', 'hair_drier', 'toothbrush'
# ]最后在faster_rcnn_r50_fpn.py中更改
num_classes=12 #自己coco数据集的类别
最后一个小坑，由于之前提取的数据集的测试集和训练集json文件中类别id不同，需要将test中的类别id改为train中的类别id，上面涉及到的类别顺序必须相同一一对应。