赞
踩
这个代码我硬生生的撸了3天,具体原因很简单适用于Linux系统,我尝试过自己笔记本的RTX3060显卡,前期OBBDetection安装老是出错。我还在一些服务器尝试,但都是windows的系统,都GG了,所以花钱跑在了平台,才运行了起来。
这个工程是适用于OBB标注的格式,一些博客的讲解也都是关于跑OBB标注的数据集,如果不知道OBB和HBB的标注区别请自行搜索。【代码工程本就有HBB的程序,稍微改一下即可】
- #新建obbdetection 环境
-
- conda create -n obbdetection python=3.6 -y
- source activate obbdetection
-
- #安装pytorch(请根据自己的cuda进行安装)
- conda install pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=10.1 -c pytorch
(1)将官方的https://github.com/jbwang1997OBBDetection和BboxToolkit打包下来,将OBBDetection里面的BboxToolkit替换掉即可,先安装BboxToolkit再安装OBBDetection。
- #安装BboxToolkit(默认主目录在OBBDetection下)
-
- cd BboxToolkit
- pip install -v -e . # or "python setup.py develop"
- cd ..
(2)安装mmcv和mmpycocotools,将{mmcv_version}替换为1.4.0我测的没有问题记得换掉后面的配置,mmpycocotools安装的时候有爆红,但是不影响我这边。
- pip install mmcv-full=={mmcv_version} -f https://download.openmmlab.com/mmcv/dist/cu101/torch1.6.0/index.html --no-cache-dir
-
- pip install mmpycocotools
(3)安装OBBDetection,如果这一步没有问题,就配置ok!
- pip install -r requirements/build.txt
- pip install -v -e . # or "python setup.py develop"
(1)下载预训练权重,可以下载faster_rcnn_orpn_r50_fpn_3x_hrsc_epoch36.pth,我按照这个继续,进行测试。linux如果有界面的话,是有show image的,代码在mmdet/apis/inference.py下
plt.imshow(mmcv.bgr2rgb(img))
plt.show()
(2)如果没有界面的话,在这个程序后加上下面的代码,运行完以后会保存在主目录下
plt.savefig('./demo.jpg')
(3)下面是结果,挺不错的
(1)将HRSC2016数据集放在OBBDetection/data/HRSC2016,修改训练的数据集路径文件在configs/obb/base/datasets/hrsc.py,可在configs/obb/_base_/schedules/schedule_3x.py对跑的轮数进行修改。
total_epochs = 200
(2)重头训练和继续训练
- #重新训练
-
- python tools/train.py configs/obb/oriented_rcnn/faster_rcnn_orpn_r50_fpn_3x_hrsc.py --work-dir work_dirs
-
- #继续训练
-
- python tools/train.py configs/obb/oriented_rcnn/faster_rcnn_orpn_r50_fpn_3x_hrsc.py --work-dir work_dirs >xxxcbtrain202204051625.log 2>&1 &
-
对第5轮进行测试
python tools/test.py configs/obb/oriented_rcnn/faster_rcnn_orpn_r50_fpn_3x_hrsc.py /root/OBBDetection/work_dirs/epoch_5.pth --eval mAP
- data = dict(
- samples_per_gpu=2,
- workers_per_gpu=4,
- train=dict(
- type=dataset_type,
- xmltype='hbb',
- imgset=data_root + 'ImageSets/Main/trainval.txt',
- ann_file=data_root + 'Annotations',
- img_prefix=data_root + 'JPEGImages/',
- pipeline=train_pipeline),
- test=dict(
- type=dataset_type,
- xmltype='hbb',
- imgset=data_root + 'ImageSets/Main/test.txt',
- ann_file=data_root + 'Annotations',
- img_prefix=data_root + 'JPEGImages/',
- pipeline=test_pipeline))
- evaluation = None
- _base_ = [
- '../_base_/datasets/dior.py',
- '../_base_/schedules/schedule_3x.py',
- '../../_base_/default_runtime.py'
- ]
-
-
- model = dict(
- type='OrientedRCNN',
- pretrained='torchvision://resnet50',
- backbone=dict(
- type='ResNet',
- depth=50,
- num_stages=4,
- out_indices=(0, 1, 2, 3),
- frozen_stages=1,
- norm_cfg=dict(type='BN', requires_grad=True),
- norm_eval=True,
- style='pytorch'),
- neck=dict(
- type='FPN',
- in_channels=[256, 512, 1024, 2048],
- out_channels=256,
- num_outs=5),
- rpn_head=dict(
- type='OrientedRPNHead',
- in_channels=256,
- feat_channels=256,
- anchor_generator=dict(
- type='AnchorGenerator',
- scales=[8],
- ratios=[0.5, 1.0, 2.0],
- strides=[4, 8, 16, 32, 64]),
- bbox_coder=dict(
- type='MidpointOffsetCoder',
- target_means=[.0, .0, .0, .0, .0, .0],
- target_stds=[1.0, 1.0, 1.0, 1.0, 0.5, 0.5]),
- loss_cls=dict(
- type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
- roi_head=dict(
- type='OBBStandardRoIHead',
- bbox_roi_extractor=dict(
- type='OBBSingleRoIExtractor',
- roi_layer=dict(type='RoIAlignRotated', out_size=7, sample_num=2),
- out_channels=256,
- extend_factor=(1.4, 1.2),
- featmap_strides=[4, 8, 16, 32]),
- bbox_head=dict(
- type='OBBShared2FCBBoxHead',
- start_bbox_type='obb',
- end_bbox_type='obb',
- in_channels=256,
- fc_out_channels=1024,
- roi_feat_size=7,
- num_classes=1,
- bbox_coder=dict(
- type='OBB2OBBDeltaXYWHTCoder',
- target_means=[0., 0., 0., 0., 0.],
- target_stds=[0.1, 0.1, 0.2, 0.2, 0.1]),
- reg_class_agnostic=True,
- loss_cls=dict(
- type='CrossEntropyLoss',
- use_sigmoid=False,
- loss_weight=1.0),
- loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
- loss_weight=1.0))))
- # model training and testing settings
- train_cfg = dict(
- rpn=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.7,
- neg_iou_thr=0.3,
- min_pos_iou=0.3,
- match_low_quality=True,
- gpu_assign_thr=200,
- ignore_iof_thr=-1),
- sampler=dict(
- type='RandomSampler',
- num=256,
- pos_fraction=0.5,
- neg_pos_ub=-1,
- add_gt_as_proposals=False),
- allowed_border=0,
- pos_weight=-1,
- debug=False),
- rpn_proposal=dict(
- nms_across_levels=False,
- nms_pre=2000,
- nms_post=2000,
- max_num=2000,
- nms_thr=0.8,
- min_bbox_size=0),
- rcnn=dict(
- assigner=dict(
- type='MaxIoUAssigner',
- pos_iou_thr=0.5,
- neg_iou_thr=0.5,
- min_pos_iou=0.5,
- match_low_quality=False,
- ignore_iof_thr=-1,
- iou_calculator=dict(type='OBBOverlaps')),
- sampler=dict(
- type='OBBRandomSampler',
- num=512,
- pos_fraction=0.25,
- neg_pos_ub=-1,
- add_gt_as_proposals=True),
- pos_weight=-1,
- debug=False))
- test_cfg = dict(
- rpn=dict(
- nms_across_levels=False,
- nms_pre=2000,
- nms_post=2000,
- max_num=2000,
- nms_thr=0.8,
- min_bbox_size=0),
- rcnn=dict(
- score_thr=0.05, nms=dict(type='obb_nms', iou_thr=0.1), max_per_img=2000))
结语:感谢您的观看,如果有什么疑问或者文章有什么不妥欢迎提出问题,以上内容仅用于学习!!!
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。