win10下使用mmdet训练自己的数据模型

1.环境配置

1.查看自己cuda版本：

2.查看自己python版本

3.安装pytorch
官方地址，按自己的选择复制粘贴到自己的python虚拟环境中。安装完之后在自己的虚拟环境中打开python，输入import torch，如果没有报错，说明自己的pytorch安装成功。
4.安装mmcv和mmdet
在自己虚拟环境中输入pip install mmcv（或者pip install mmcv-full）和pip install mmdet
。如果自己的电脑报错的话可以先安装pycocotools电脑要有visual C++。不过我的电脑没有报错，应该是新版本的会自己下载吧。其实按照git上的步骤应该就是没有问题的。
5.测试是否安装成功下载权重文件，我把他放在了新建的文件夹checkoints中，然后修改并运行以下代码

# coding=utf-8
#改三处
import mmcv
from mmdet.apis import init_detector
from mmdet.apis import inference_detector
from mmdet.apis import show_result_pyplot
# from mmdet.models.detectors.base import BaseDetector

# 模型配置文件
config_file = r'C:\Users\ROBOT-773\Desktop\Downloads\mmdetection-master\mmdetection-master\configs\faster_rcnn\faster_rcnn_r50_fpn_1x_coco.py'#1.改1，这里是你fork的文件夹里面的config文件
# 预训练模型文件
# url: https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth
checkpoint_file = r'C:\Users\ROBOT-773\Desktop\Downloads\mmdetection-master\mmdetection-master\checkpoints\faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth'#改2，这里是刚刚下载的权重文件
# 通过模型配置文件与预训练文件构建模型
model = init_detector(config_file, checkpoint_file, device='cuda:0')
# 测试单张图片并进行展示
# img = '/home/cv/mmdetection/my_pictures/cars1.jpeg'
img=r'C:\Users\ROBOT-773\Desktop\Downloads\mmdetection-master\mmdetection-master\demo\demo.jpg'#改3，这里是图片的地址
result = inference_detector(model, img)
show_result_pyplot(model, img, result)

# 测试一个图像列表并保存结果图像
# imgs = ['test1.jpg', 'test2.jpg', 'test3.jpg']
# for i, result in enumerate(inference_detector(model, imgs)):
#     show_result_pyplot(model, imgs[i], result)


"""
# 
# (3)测试视频和显示测试结果
video = mmcv.VideoReader('demo/Venice-2.mp4')
for frame in video:
    result = inference_detector(model, frame)
    show_result(frame, result, model.CLASSES, wait_time=1)
"""

测试成功，下载完成，进行下一步。

2.制作自己的coco数据集

应该是voc和coco数据集都可以，我自己是用了coco数据集。将自己的图片分成训练集和测试集，然后用labelimg分别生成各自的xml文件，然后用下列代码，将xml文件生成json文件

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 = 20210000000
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 , , ,