ubuntu18.04+pytorch1.3+mmdetection v1.2.0 运行自己制作的coco数据集
coco格式数据集制作
- labelme的安装及使用 :该部分主要参考labelme安装及使用,需要注意的是上述链接是在Windows环境下安装的,因此若在Ubuntu环境下安装,视频后半部分关于批量操作.json文件的部分不应采取;
- 使用labelme标注图片 :在使用labelme标注图片时,需特别注意图片的位置,以下是我标注的步骤,首先在mmdetection1.2.0文件下创建data文件夹,data文件夹下创建coco文件夹,coco文件夹下创建annotations,train2017,val2017三个文件夹如下图所示
将train图片和val图片分别放入对应文件夹下,在标注时分别打开两个文件夹分别标注.json文件放置在当前标注图片的文件夹中;
- labelme转coco :标注完成后需要将标注的.json文件转文coco格式,以便在mmdetection中使用。首先新建文件labelme2coco.py
# -*- coding:utf-8 -*-
# !/usr/bin/env python
import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image
class MyEncoder(json.JSONEncoder):
def default(self, obj):
if isinstance(obj, np.integer):
return int(obj)
elif isinstance(obj, np.floating):
return float(obj)
elif isinstance(obj, np.ndarray):
return obj.tolist()
else:
return super(MyEncoder, self).default(obj)
class labelme2coco(object):
def __init__(self, labelme_json=[], save_json_path='/home/biao/PycharmProjects/mmdetection-1.2.0/data/coco/annotations/instances_val2017.json'):
''‘
:param labelme_json: 所有labelme的json文件路径组成的列表
:param save_json_path: json保存位置,利用train文件夹中.json文件生成instances_train2017.json,利用val文件夹中.json文件生成instances_val2017.json,
'''
self.labelme_json = labelme_json
self.save_json_path = save_json_path
self.images = []
self.categories = []
self.annotations = []
# self.data_coco = {}
self.label = []
self.annID = 1
self.height = 0
self.width = 0
self.save_json()
def data_transfer(self):
for num, json_file in enumerate(self.labelme_json):
with open(json_file, 'r') as fp:
data = json.load(fp) # 加载json文件
self.images.append(self.image(data, num))
for shapes in data['shapes']:
label = shapes['label']
if label not in self.label:
self.categories.append(self.categorie(label))
self.label.append(label)
points = shapes['points']#这里的point是用rectangle标注得到的,只有两个点,需要转成四个点
#points.append([points[0][0],points[1][1]])
#points.append([points[1][0],points[0][1]])
self.annotations.append(self.annotation(points, label, num))
self.annID += 1
def image(self, data, num):
image = {}
img = utils.img_b64_to_arr(data['imageData']) # 解析原图片数据
# img=io.imread(data['imagePath']) # 通过图片路径打开图片
# img = cv2.imread(data['imagePath'], 0)
height, width = img.shape[:2]
img = None
image['height'] = height
image['width'] = width
image['id'] = num + 1
image['file_name'] = data['imagePath'].split('/')[-1]
# image['file_name'] = data['imagePath'][3:14]
self.height = height
self.width = width
return image
def categorie(self, label):
categorie = {}
categorie['supercategory'] = 'Cancer'
categorie['id'] = len(self.label) + 1 # 0 默认为背景
categorie['name'] = label
return categorie
def annotation(self, points, label, num):
annotation = {}
annotation['segmentation'] = [list(np.asarray(points).flatten())]
annotation['iscrowd'] = 0
annotation['image_id'] = num + 1
# annotation['bbox'] = str(self.getbbox(points)) # 使用list保存json文件时报错(不知道为什么)
# list(map(int,a[1:-1].split(','))) a=annotation['bbox'] 使用该方式转成list
annotation['bbox'] = list(map(float, self.getbbox(points)))
annotation['area'] = annotation['bbox'][2] * annotation['bbox'][3]
# annotation['category_id'] = self.getcatid(label)
annotation['category_id'] = self.getcatid(label)#注意,源代码默认为1
annotation['id'] = self.annID
return annotation
def getcatid(self, label):
for categorie in self.categories:
if label == categorie['name']:
return categorie['id']
return 1
def getbbox(self, points):
# img = np.zeros([self.height,self.width],np.uint8)
# cv2.polylines(img, [np.asarray(points)], True, 1, lineType=cv2.LINE_AA) # 画边界线
# cv2.fillPoly(img, [np.asarray(points)], 1) # 画多边形 内部像素值为1
polygons = points
mask = self.polygons_to_mask([self.height, self.width], polygons)
return self.mask2box(mask)
def mask2box(self, mask):
'''从mask反算出其边框
mask:[h,w] 0、1组成的图片
1对应对象,只需计算1对应的行列号(左上角行列号,右下角行列号,就可以算出其边框)
'''
# np.where(mask==1)
index = np.argwhere(mask == 1)
rows = index[:, 0]
clos = index[:, 1]
# 解析左上角行列号
left_top_r = np.min(rows) # y
left_top_c = np.min(clos) # x
# 解析右下角行列号
right_bottom_r = np.max(rows)
right_bottom_c = np.max(clos)
# return [(left_top_r,left_top_c),(right_bottom_r,right_bottom_c)]
# return [(left_top_c, left_top_r), (right_bottom_c, right_bottom_r)]
# return [left_top_c, left_top_r, right_bottom_c, right_bottom_r] # [x1,y1,x2,y2]
return [left_top_c, left_top_r, right_bottom_c - left_top_c,
right_bottom_r - left_top_r] # [x1,y1,w,h] 对应COCO的bbox格式
def polygons_to_mask(self, img_shape, polygons):
mask = np.zeros(img_shape, dtype=np.uint8)
mask = PIL.Image.fromarray(mask)
xy = list(map(tuple, polygons))
PIL.ImageDraw.Draw(mask).polygon(xy=xy, outline=1, fill=1)
mask = np.array(mask, dtype=bool)
return mask
def data2coco(self):
data_coco = {}
data_coco['images'] = self.images
data_coco['categories'] = self.categories
data_coco['annotations'] = self.annotations
return data_coco
def save_json(self):
self.data_transfer()
self.data_coco = self.data2coco()
# 保存json文件
json.dump(self.data_coco, open(self.save_json_path, 'w'), indent=4, cls=MyEncoder) # indent=4 更加美观显示
labelme_json = glob.glob('/home/biao/PycharmProjects/mmdetection-1.2.0/data/coco/val2017/*.json')#访问train2017或val2017文件夹下.json文件
# labelme_json=['./Annotations/*.json']
labelme2coco(labelme_json, '/home/biao/PycharmProjects/mmdetection-1.2.0/data/coco/annotations/instances_val2017.json')#保存生成的instances_train2017.json或instances_val2017.json
在生成instances_train2017.json和instances_val2017.json应分别改变上述代码到对应的文件夹下,若成功运行可得到下图文件中部分内容如下图
至此可完成coco数据集的制作
训练,测试
先贴上参考的博客【mmdetection】使用自定义的coco格式数据集进行训练及测试
不同点是我标注的只有一类,另外在运行代码
python tools/train.py configs/faster_rcnn_r50_fpn_1x.py --gpus 1 --validate --work_dir work_dirs
时出现很多错误,其中大部分是因为数据集的制作有问题,还有一个错误的原因时pycocotools文件报错,解决办法pycocptools报错
在运行测试代码
python tools/test.py configs/faster_rcnn_r50_fpn_1x.py work_dirs/epoch_100.pth --out ./result/result_100.pkl --eval bbox --show
需根据自己训练时work_dir文件中生成的情况修改,并建立result文件夹,以便存放生成的result_**.pkl文件。