mmdetection环境安装

mmdetection 的环境安装参考官方文档

https://github.com/open-mmlab/mmdetection/blob/master/docs/get_started.md

遇到的问题如下

第三步Install mmcv-full时，发现自己的cuda是10.1的，然后pytorch是1.7.1的然后就用了这条命令：
pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.7.1/index.html
实际上是错误的，但是没有报错，他就直接给你按了一个最新版本的mmcv-full，这和我想要的是不一样的，我要的是 cuda10.1，pytorch1.7.1的。并没有这样的组合。

安装过程

1. conda create -n mmdetection python=3.7 # 创建虚拟环境mmdetection
2. conda activate mmdetection / source activate mmdetection #（ubuntu服务器上可能是后面的命令）
3. git clone https://github.com/open-mmlab/mmdetection.git #下载mmdetection
4. cd mmdetection #要是已经下载过mmdetection，3和4两步不用执行
5. conda install pytorch=1.6.0 torchvision=0.7.0 cudatoolkit=10.2 -c pytorch
6. pip install mmcv-full==1.3.8 -f https://download.openmmlab.com/mmcv/dist/cu102/torch1.6.0/index.html
7. pip install -r requirements/build.txt
8. pip install -v -e .
   最后两步是在 mmdetection 目录下执行

数据集

mdetection 支持VOC格式数据集，还有COCO数据集格式，还可以自定义数据格式，我们采用VOC的数据格式

-VOC2007
------Annotations
------ImageSets
------Main
------JEPGImages
1.如果数据集没有进行划分， 划分数据集代码如下：（代码用于生成-VOC2007/Main 中的train.txt ,test.txt ,val.txt ，txt已有的话可以不用）参考： link

import os
import random

trainval_percent = 0.8 #划分比例
train_percent = 0.8 #划分比例
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
total_xml = os.listdir(xmlfilepath)

num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)

ftrainval = open('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
fval = open('ImageSets/Main/val.txt', 'w')

for i in list:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        ftrainval.write(name)
        if i in train:
            ftrain.write(name)
        else:
            fval.write(name)
    else:
        ftest.write(name)

ftrainval.close()
ftrain.close()
fval.close()
ftest.close()

修改配置文件

参考大佬的帖子： https://zhuanlan.zhihu.com/p/162730118

1. cd /mmdetection/configs/base/datasets
   打开voc0712.py 修改如下：带 #*# 就是修改的地方
   train_pipeline 中：

   		# dataset settings
   dataset_type = 'VOCDataset'
   #data_root = 'data/VOCdevkit/'
   data_root = '/data1/lirz/DATA/data_board_pascal/zyc-voc/'
   img_norm_cfg = dict(
       mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
   train_pipeline = [
       dict(type='LoadImageFromFile'),
       dict(type='LoadAnnotations', with_bbox=True),
       # dict(type='Resize', img_scale=(1000, 600), keep_ratio=True),
       dict(type='Resize', img_scale=(640, 512), keep_ratio=True),
       dict(type='RandomFlip', flip_ratio=0.5),
       dict(type='Normalize', **img_norm_cfg),
       dict(type='Pad', size_divisor=32),
       dict(type='DefaultFormatBundle'),
       dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels']),
   ]
   test_pipeline = [
       dict(type='LoadImageFromFile'),
       dict(
           type='MultiScaleFlipAug',
           # img_scale=(1000, 600),
           img_scale=(640, 512),
           flip=False,
           transforms=[
               dict(type='Resize', keep_ratio=True),
               dict(type='RandomFlip'),
               dict(type='Normalize', **img_norm_cfg),
               dict(type='Pad', size_divisor=32),
               dict(type='ImageToTensor', keys=['img']),
               dict(type='Collect', keys=['img']),
           ])
   ]
   data = dict(
       samples_per_gpu=1,
       # workers_per_gpu=2,
       workers_per_gpu=1,
       train=dict(
           type='RepeatDataset',
           times=3,
           dataset=dict(
               type=dataset_type,
               ann_file=[
                   data_root + 'VOC2007/ImageSets/Main/trainval.txt',
                   # data_root + 'VOC2012/ImageSets/Main/trainval.txt'
               ],
               # img_prefix=[data_root + 'VOC2007/', data_root + 'VOC2012/'],
               img_prefix=[data_root + 'VOC2007/'],
               pipeline=train_pipeline)),
       val=dict(
           type=dataset_type,
           ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
           img_prefix=data_root + 'VOC2007/',
           pipeline=test_pipeline),
       test=dict(
           type=dataset_type,
           ann_file=data_root + 'VOC2007/ImageSets/Main/test.txt',
           img_prefix=data_root + 'VOC2007/',
           pipeline=test_pipeline))
   evaluation = dict(interval=1, metric='mAP')