MMRotate从零开始训练自己的数据集_mmrotate训练自己数据集

conda create --name mmrotate python=3.8
 
conda activate mmrotate

​

pip install mmdet

pip install mmrotate

pip install -r requirements.txt

# Copyright (c) OpenMMLab. All rights reserved.
"""Inference on single image.
Example:
```
wget -P checkpoint https://download.openmmlab.com/mmrotate/v0.1.0/oriented_rcnn/oriented_rcnn_r50_fpn_1x_dota_le90/oriented_rcnn_r50_fpn_1x_dota_le90-6d2b2ce0.pth  # noqa: E501, E261.
python demo/image_demo.py \
    demo/demo.jpg \
    configs/oriented_rcnn/oriented_rcnn_r50_fpn_1x_dota_le90.py \
    work_dirs/oriented_rcnn_r50_fpn_1x_dota_v3/epoch_12.pth
```
"""  # nowq
 
from argparse import ArgumentParser
 
from mmdet.apis import inference_detector, init_detector, show_result_pyplot
 
import mmrotate  # noqa: F401
import os
 
ROOT = os.getcwd()
 
 
def parse_args():
    parser = ArgumentParser()
    parser.add_argument('--img', default=os.path.join(ROOT, 'demo.jpg'), help='Image file')
    parser.add_argument('--config', default=os.path.join(ROOT, '../configs/oriented_rcnn/oriented_rcnn_r50_fpn_1x_dota_le90.py'), help='Config file')
    parser.add_argument('--checkpoint', default=os.path.join(ROOT, '../pre-models/oriented_rcnn_r50_fpn_1x_dota_le90-6d2b2ce0.pth'), help='Checkpoint file')
    parser.add_argument(
        '--device', default='cuda:0', help='Device used for inference')
    parser.add_argument(
        '--palette',
        default='dota',
        choices=['dota', 'sar', 'hrsc', 'hrsc_classwise', 'random'],
        help='Color palette used for visualization')
    parser.add_argument(
        '--score-thr', type=float, default=0.3, help='bbox score threshold')
    args = parser.parse_args()
    return args
 
 
def main(args):
    # build the model from a config file and a checkpoint file
    model = init_detector(args.config, args.checkpoint, device=args.device)
    # test a single image
    result = inference_detector(model, args.img)
    # show the results
    show_result_pyplot(
        model,
        args.img,
        result,
        palette=args.palette,
        score_thr=args.score_thr)
 
 
if __name__ == '__main__':
    args = parse_args()
    main(args)
 
 

'''
rolabelimg xml data to dota 8 points data 
'''
import os
import xml.etree.ElementTree as ET
import math
import cv2
import numpy as np
 
 
def edit_xml(xml_file):
 
    if ".xml" not in xml_file:
        return 
        
    tree = ET.parse(xml_file)
    objs = tree.findall('object')
 
    txt=xml_file.replace(".xml",".txt")
 
    png=xml_file.replace(".xml",".png")
    src=cv2.imread(png,1)
 
    with open(txt,'w') as wf:
        wf.write("imagesource:Google\n")
        # wf.write("gsd:0.115726939386\n")
 
        for ix, obj in enumerate(objs):
 
            x0text = ""
            y0text =""
            x1text = ""
            y1text =""
            x2text = ""
            y2text = ""
            x3text = ""
            y3text = ""
            difficulttext=""
            className=""
 
            obj_type = obj.find('type')
            type = obj_type.text
 
            obj_name = obj.find('name')
            className = obj_name.text
 
            obj_difficult= obj.find('difficult')
            difficulttext = obj_difficult.text
 
            if type == 'bndbox':
                obj_bnd = obj.find('bndbox')
                obj_xmin = obj_bnd.find('xmin')
                obj_ymin = obj_bnd.find('ymin')
                obj_xmax = obj_bnd.find('xmax')
                obj_ymax = obj_bnd.find('ymax')
                xmin = float(obj_xmin.text)
                ymin = float(obj_ymin.text)
                xmax = float(obj_xmax.text)
                ymax = float(obj_ymax.text)
 
                x0text = str(xmin)
                y0text = str(ymin)
                x1text = str(xmax)
                y1text = str(ymin)
                x2text = str(xmin)
                y2text = str(ymax)
                x3text = str(xmax)
                y3text = str(ymax)
 
                points=np.array([[int(x0text),int(y0text)],[int(x1text),int(y1text)],[int(x2text),int(y2text)],[int(x3text),int(y3text)]],np.int32)
                cv2.polylines(src,[points],True,(255,0,0)) #画任意多边
 
            elif type == 'robndbox':
                obj_bnd = obj.find('robndbox')
                obj_bnd.tag = 'bndbox'   # 修改节点名
                obj_cx = obj_bnd.find('cx')
                obj_cy = obj_bnd.find('cy')
                obj_w = obj_bnd.find('w')
                obj_h = obj_bnd.find('h')
                obj_angle = obj_bnd.find('angle')
                cx = float(obj_cx.text)
                cy = float(obj_cy.text)
                w = float(obj_w.text)
                h = float(obj_h.text)
                angle = float(obj_angle.text)
 
                x0text, y0text = rotatePoint(cx, cy, cx - w / 2, cy - h / 2, -angle)
                x1text, y1text = rotatePoint(cx, cy, cx + w / 2, cy - h / 2, -angle)
                x2text, y2text = rotatePoint(cx, cy, cx + w / 2, cy + h / 2, -angle)
                x3text, y3text = rotatePoint(cx, cy, cx - w / 2, cy + h / 2, -angle)
 
                points=np.array([[int(x0text),int(y0text)],[int(x1text),int(y1text)],[int(x2text),int(y2text)],[int(x3text),int(y3text)]],np.int32)
                cv2.polylines(src,[points],True,(255,0,0)) #画任意多边形
 
          
 
            # print(x0text,y0text,x1text,y1text,x2text,y2text,x3text,y3text,className,difficulttext)
            wf.write("{} {} {} {} {} {} {} {} {} {}\n".format(x0text,y0text,x1text,y1text,x2text,y2text,x3text,y3text,className,difficulttext))
 
        # cv2.imshow("ddd",src)
        # cv2.waitKey()
 
 
# 转换成四点坐标
def rotatePoint(xc, yc, xp, yp, theta):
    xoff = xp - xc;
    yoff = yp - yc;
    cosTheta = math.cos(theta)
    sinTheta = math.sin(theta)
    pResx = cosTheta * xoff + sinTheta * yoff
    pResy = - sinTheta * xoff + cosTheta * yoff
    return str(int(xc + pResx)), str(int(yc + pResy))
 
 
if __name__ == '__main__':
    dir = r"H:\duocicaiji\biaozhu_all"
    filelist = os.listdir(dir)
    for file in filelist:
        edit_xml(os.path.join(dir, file))