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!!!