Dark Mode

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly
Sign up
Appearance settings

DataXujing/Cascade_RCNN_mmdetection

Repository files navigation

mmdetectionXun Lian Cascade RCNN

Cascade RCNN Xun Lian Zi Ji De Shu Ju

Xu Jing

Shang Tang Ke Ji (2018 COCO Mu Biao Jian Ce Tiao Zhan Sai Guan Jun )He Xiang Gang Zhong Wen Da Xue Zui Jin Kai Yuan Liao Yi Ge Ji Yu PytorchShi Xian De Shen Du Xue Xi Mu Biao Jian Ce Gong Ju Xiang mmdetection,Zhi Chi Faster-RCNN,Mask-RCNN,Fast-RCNN,Cascade-RCNNDeng Zhu Liu Mu Biao Jian Ce Kuang Jia . Ke Yi Kuai Su Bu Shu Zi Ji De Mo Xing .

Xiang Mu Di Zhi :https://github.com/open-mmlab/mmdetection

Guan Fang Jiao Cheng :https://mmdetection.readthedocs.io](https://mmdetection.readthedocs.io/

paper: https://arxiv.org/abs/1906.07155

2.Huan Jing Yao Qiu

  1. Linux (Guan Fang Bu Zhi Chi windows,Dan Shi Wo Men Ke Yi Kan Dao Wang Shang Guan Yu Zai windowsAn Zhuang mmdetectionDe Jiao Cheng )

  2. Python 3.5+

  3. >=PyTorch 1.1.0, torchvision 0.3.0

  4. >=CUDA 9.0

  5. NCCL 2

  6. >=GCC 4.9

  7. mmcv

1.Huan Jing An Zhuang

An Zhao Guan Fang Wen Dang Jian Yi Xian An Zhuang Anaconda,Chuang Jian pythonXu Ni Huan Jing ,Shi Yong condaJin Xing An Zhuang ,Zhe Li Wo Men Shi Yong virtualenvAn Zhuang

1.virtualenvChuang Jian Yi Ge Xu Ni Huan Jing

virtualenv -p python3 mmlab
cd mmlab/bin
source activate

2.An Zhuang pytorchHe torchvision

https://pytorch.org/ Xia Zai An Zhuang
https://download.pytorch.org/whl/torch_stable.html
pip install torch==1.1.0 torchvision==0.3.0 -f https://download.pytorch.org/whl/torch_stable.html
# conda install pytorch==1.1.0 torchvision==0.3.0

3.Xia Zai mmdetection

git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection

4.An Zhuang mmdetection

pip3 install mmcv cython -i https://pypi.tuna.tsinghua.edu.cn/simple
#An Zhuang mmcvHe cython
pip3 install albumentations>=0.3.2 imagecorruptions pycocotools six terminaltables
#An Zhuang Yi Lai Bao
python3 setup.py develop
# Zai rootYong Hu Xia Zuo ,Fa Xian Zi Ji ubuntu16.04Bu Zai rootYong Hu Xia Zuo Bao Cuo
# Bi Xu Xian An Zhuang mmcv,Zai Yun Xing setup.pyBian Yi ,Bu Ran Hui Bao Cuo .

2.Yan Zheng Shi Fou An Zhuang Cheng Gong

Xia Zai Yi Ge faster_rcnn_r50_fpn_1xDe Yu Xun Lian Mo Xing ,Bao Cun Dao mmdetection/checkpointsMu Lu Xia ,Yun Xing Xia Mian De Dai Ma ,Ru Guo Neng Xian Shi Tu Pian ,Shuo Ming An Zhuang Cheng Gong Liao .

from mmdet.apis import init_detector, inference_detector, show_result
import mmcv

config_file = 'configs/faster_rcnn_r50_fpn_1x.py'
checkpoint_file = 'checkpoints/faster_rcnn_r50_fpn_1x_20181010-3d1b3351.pth'

# build the model from a config file and a checkpoint file
model = init_detector(config_file, checkpoint_file, device='cuda:0')

# test a single image and show the results
img = 'test.jpg' # or img = mmcv.imread(img), which will only load it once
result = inference_detector(model, img)
# visualize the results in a new window
# show_result(img, result, model.CLASSES)
# or save the visualization results to image files
show_result(img, result, model.CLASSES,score_thr=0.90,show=False,out_file='result.jpg')

Zhe Yang Wo Men Jiu Wan Cheng mmdetectionDe An Zhuang !

3.Gou Jian Xun Lian Ji

1.Chuang Jian Xiang Ying Wen Jian Jia

  • ./config/bingzao: Mo Xing Xun Lian De Pei Zhi Wen Jian Cun Fang Di Zhi

    • Jiang cascade_rcnn_r101_fpn_1x.pyWen Jian Cun Fang Zai Ci ,Bing Dui Qi Jin Xing Xiu Gai

  • data: Xun Lian Shu Ju De De Cun Fang Di Zhi

    ./data
    +-coco
    | +-annotations # Cun Fang train.json,val.json,test.json
    | +-test # Ce Shi Huo Ji
    | | +-annotations # Ce Shi Huo Yan Zheng xmlBiao Zhu
    | | +-JPEGImages # Ce Shi Huo Yan Zheng Tu Pian
    | +-train # Xun Lian Ji
    | +-annotations # Xun Lian Ji De xmlBiao Zhu
    | +-JPEGImages # Xun Lian Ji De Tu Pian
    +-pretrained # Yu Xun Lian Mo Xing De Cun Fang Di Zhi
    +-results # Ce Shi Jie Guo De Cun Fang Di Zhi ,Yong Yu Ce Shi
    +-source # Dai Chu Li De Shu Ju Cun Fang Di Zhi ,Jiang Zui Zhong De Shu Ju Jian Cha Hou Cun Fang Zai cocoWen Jian Jia
    +-test
    | +-annotations
    | +-JPEGImages
    +-train
    +-annotations
    +-JPEGImages

  • work_dirs: Yong Yu Bao Cun Xun Lian Mo Xing De Mo Xing Wen Jian He Xun Lian log

  • checkpoint: Yong Yu Bao Cun Yu Xun Lian De Mo Xing (Zhe Li Wo Men Bing Mei You Shi Yong )

2.Xun Lian Ji Zhun Bei

Wang Wang Wo Men Na Dao De Shu Ju Ji Du Shi Ji Yu VOCShu Ju Ge Shi De Shu Ju ,You xmlBiao Zhu Wen Jian He Tu Xiang Yuan Wen Jian ,Wo Men Jiang Huo De De Yuan Shu Ju Cun Fang Zai ./data/source/Wen Jian Xia .

3.Xiu Gai Dai Ma Jiang VOCShu Ju Zhuan Wei COCOShu Ju

Ke Yi Can Kao Zhe Ge Dai Ma ,Jiang Zi Ji De Shu Ju Zhuan Huan Wei cocoGe Shi ,Ta Zhi Chi :

  • csv to coco
  • csv to voc
  • labelme to coco
  • labelme to voc
  • csv to json

A.Xin Jian Xiu Gai mmdetection/mmdet/datasets/bingzao.py

# Qi Jie Gou Yu mmdetection/mmdet/datasets/coco.pyXiang Si ,Dan Lei Ming He CLASSESBu Tong
@DATASETS.register_module
class bingzao(CustomDataset): # Lei Ming Xiu Gai Cheng bingzao
# Xiu Gai CLASSES,Xiu Gai Cheng Zi Ji De
CLASSES = ("Barrett","CX","FLXSGY","HJQ","JCJZQA","JCXR",
"JCZA","JZQWA","JS","KYXJCY","MXWSXWY","QP","QG","QTMH",
"QTQPGY","SGJMQZ","SGZA","TW","WKY","WZA","YD","ZZ")

Tong Shi Xiu Gai Tong Ji Mu Lu Xia De __init__.py

from .builder import build_dataset
from .cityscapes import CityscapesDataset
from .coco import CocoDataset
from .custom import CustomDataset
from .dataset_wrappers import ConcatDataset, RepeatDataset
from .loader import DistributedGroupSampler, GroupSampler, build_dataloader
from .registry import DATASETS
from .voc import VOCDataset
from .wider_face import WIDERFaceDataset
from .xml_style import XMLDataset
from .bingzao import bingzao

__all__ = [
'CustomDataset', 'XMLDataset', 'CocoDataset', 'VOCDataset',
'CityscapesDataset', 'GroupSampler', 'DistributedGroupSampler',
'build_dataloader', 'ConcatDataset', 'RepeatDataset', 'WIDERFaceDataset',
'DATASETS', 'build_dataset',"bingzao" #Zai Ci Tian Jia
]

B.Xin Jian Xiu Gai mmdetection/mmdet/tools/data_process

./tools
+-data_process
00_img_rename.py # Tong Guo uuidZhong Ming Ming Xun Lian Ji ,Ce Shi Ji copyDao cocoWen Jian Jia
01_check_img.py # Jian Cha Shu Ju De He Gui Xing
02_check_box.py # Jian Cha Biao Zhu De He Gui Xing
03_xml2coco.py # VOCShu Ju Zhuan COCOShu Ju
generate_test_json.py # testWu xml,Sui Ji Sheng Cheng COCO,Fang Bian Hou Qi Ce Shi Ce Shi Ji

C.Xiu Gai mmdetection/mmdet/core/evaluationXia De __init__.py,class_names.py

# class_names.py
# Xin Zeng Lei
def bingzao_classes():
return [
"Barrett","CX","FLXSGY","HJQ","JCJZQA","JCXR","JCZA","JZQWA",
"JS","KYXJCY","MXWSXWY","QP","QG","QTMH","QTQPGY","SGJMQZ",
"SGZA","TW","WKY","WZA","YD","ZZ"
]
# __init__.py Xiu Gai
from .class_names import (cityscapes_classes, coco_classes, dataset_aliases,
get_classes, imagenet_det_classes,
imagenet_vid_classes, voc_classes,bingzao_classes)
from .eval_hooks import DistEvalHook
from .mean_ap import average_precision, eval_map, print_map_summary
from .recall import (eval_recalls, plot_iou_recall, plot_num_recall,
print_recall_summary)

__all__ = [
'voc_classes', 'imagenet_det_classes', 'imagenet_vid_classes',
'coco_classes', 'cityscapes_classes', 'dataset_aliases', 'get_classes',
'DistEvalHook', 'average_precision', 'eval_map', 'print_map_summary',
'eval_recalls', 'print_recall_summary', 'plot_num_recall',
'plot_iou_recall',"bingzao_classes" # Tian Jia Zhe Ge Lei
]

4.Xia Zai Yu Xun Lian De Mo Xing

Zai model ZooXia Zai Wo Men Xu Yao De Mo Xing ,Xia Zai Hao De Yu Xun Lian Mo Xing Jiang Qi Cun Fang Zai Xin Jian De ./checkpoint(Guan Fang Tui Jian )Wen Jian Jia Huo ./data/pretrainedWen Jian Jia ,Zhe Ge Qu Jue Wo Men Zai Section4Zhong Pei Zhi Wen Jian De Pei Zhi ,Wo Men Jiang Xia Zai De cascade_rcnn_r101_fpn_1x_20181129-d64ebac7.pth COCOYu Xun Lian De Mo Xing Cun Fang Zai ./data/pretrainedWen Jian Jia .

  1. Sheng Cheng COCOShu Ju

    Zhun Bei Hao Shang Shu Shu Ju Hou ,Yun Xing

    python ./tools/data_process/00_img_rename.py
    python ./tools/data_process/01_check_img.py
    python ./tools/data_process/02_check_box.py
    python ./tools/data_process/03_xml2coco.py

    Zui Zhong Zai ./data/coco/annotations/Xia Sheng Cheng Liao train.jsonHe test.json,Yong Yi Xun Lian Mo Xing Zuo Zui Hou De Shu Ju Zhun Bei !

4.Xiu Gai mmdetectionDe Mo Xing configWen Jian

Xiu Gai ./configs/bingzao/cascade_rcnn_r101_fpn_1x.py

Zhan Kai Wo Cha Kan :cascade_rcnn_r101_fpn_1x.py
# model settings
model = dict(
type='CascadeRCNN',
num_stages=3,
pretrained='torchvision://resnet101',
backbone=dict(
type='ResNet',
depth=101,
num_stages=4,
out_indices=(0, 1, 2, 3),
frozen_stages=1,
style='pytorch'),
neck=dict(
type='FPN',
in_channels=[256, 512, 1024, 2048],
out_channels=256,
num_outs=5),
rpn_head=dict(
type='RPNHead',
in_channels=256,
feat_channels=256,
anchor_scales=[8],
anchor_ratios=[0.5, 1.0, 2.0],
anchor_strides=[4, 8, 16, 32, 64],
target_means=[.0, .0, .0, .0],
target_stds=[1.0, 1.0, 1.0, 1.0],
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)),
bbox_roi_extractor=dict(
type='SingleRoIExtractor',
roi_layer=dict(type='RoIAlign', out_size=7, sample_num=2),
out_channels=256,
featmap_strides=[4, 8, 16, 32]),
bbox_head=[
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=23, #----------- Xiu Gai Lei Bie Ge Shu 81 Lei Bie Shu Liang +1----------
target_means=[0., 0., 0., 0.],
target_stds=[0.1, 0.1, 0.2, 0.2],
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)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.05, 0.05, 0.1, 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)),
dict(
type='SharedFCBBoxHead',
num_fcs=2,
in_channels=256,
fc_out_channels=1024,
roi_feat_size=7,
num_classes=81,
target_means=[0., 0., 0., 0.],
target_stds=[0.033, 0.033, 0.067, 0.067],
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,
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=0.7,
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,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.6,
neg_iou_thr=0.6,
min_pos_iou=0.6,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False),
dict(
assigner=dict(
type='MaxIoUAssigner',
pos_iou_thr=0.7,
neg_iou_thr=0.7,
min_pos_iou=0.7,
ignore_iof_thr=-1),
sampler=dict(
type='RandomSampler',
num=512,
pos_fraction=0.25,
neg_pos_ub=-1,
add_gt_as_proposals=True),
pos_weight=-1,
debug=False)
],
stage_loss_weights=[1, 0.5, 0.25])
test_cfg = dict(
rpn=dict(
nms_across_levels=False,
nms_pre=1000,
nms_post=1000,
max_num=1000,
nms_thr=0.7,
min_bbox_size=0),
rcnn=dict( #-------------Xiu Gai Yi Xie Hou Chu Li De Can Shu NMS,WBF,Soft NMS-------------
score_thr=0.0001, nms=dict(type='soft_nms', iou_thr=0.5,min_score=0.0001), max_per_img=200))
# dataset settings
dataset_type = 'bingzao' #---------Xiu Gai Shu Ju Ji Ming Cheng -----------
data_root = 'data/coco/' #---------Xiu Gai Shu Ju De Gen Mu Lu ---------
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),
#-------------Xun Lian Shu Ju Zeng Qiang Zai Ci Tian Jia Cao Zuo ---------------------
# https://blog.csdn.net/Mr_health/article/details/103552617?depth_1-utm_source=distribute.pc_relevant.none-task&utm_source=distribute.pc_relevant.none-task
dict(type='Resize', img_scale=[(1920,1080),(1280, 1024),(1024,768),(1528,1036),(720,576)], keep_ratio=True,multiscale_mode='value'),
#-----Xiu Gai Duo Chi Du Xun Lian dict(type='Resize', img_scale=[(4096, 600), (4096, 1000)],multiscale_mode='range', 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',
#---------Duo Chi Du Tui Duan Zai Ci Xiu Gai ------------
img_scale=[(1920,1080),(1280, 1024),(1024,768),(1528,1036),(720,576)],
#--------img_scale=[(4096, 600), (4096, 800), (4096, 1000)],--------
flip=True, # Mo Ren Shi 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(
imgs_per_gpu=4, # -----Mei Ge GPUJi Suan De Tu Xiang Shu Liang -----
workers_per_gpu=2, # -----Mei Ge GPUFen Pei De Xian Cheng Shu -----
train=dict(
type=dataset_type,
ann_file=data_root + 'annotations/train.json', # ---Biao Zhu De annotationLu Jing ---
img_prefix=data_root + 'train/JPEGImages', #---Shu Ju Jiu De Tu Pian Lu Jing ---
pipeline=train_pipeline),
#-----Zhe Li Wo Men Mei You Fen Pei Yan Zheng Ji ,Ru Guo Fen Pei Ke Jia Ru ----------------
# val=dict(
# type=dataset_type,
# ann_file=data_root + 'annotations/instances_val2017.json',
# img_prefix=data_root + 'val2017/',
# pipeline=test_pipeline),
test=dict(
type=dataset_type,
ann_file=data_root + 'annotations/test.json', # ----Mei You De Hua Ke Yi Sui Ji Sheng Cheng De ---
img_prefix=data_root + 'test/JPEGImages',
pipeline=test_pipeline))
evaluation = dict(interval=1, metric='bbox')
# ------optimizer------
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
policy='step',
warmup='linear', # -----warmupDe Ce Lue ,Zhe Li She Zhi Wei Xian Xing Zeng Jia ------
warmup_iters=500, # ----Zai Chu Shi De 500Ci Die Dai Zhong Xue Xi Lu Zhu Jian Zeng Jia -----
warmup_ratio=1.0 / 30, # -----Qi Shi De Xue Xi Lu 1.0/3-------
step=[70, 90]) #-----Zai Di 8He 11Ge epochShi Jiang Di Xue Xi Lu ------
checkpoint_config = dict(interval=20) #-----Mei nGe epochCun Chu Yi Ci Mo Xing ------
# yapf:disable
log_config = dict(
interval=20, #-----Mei 20iterBao Gao Yi Ci Xun Lian De log-------
hooks=[
dict(type='TextLoggerHook'),
# dict(type='TensorboardLoggerHook') #-----Da Kai Ke Yi Shi Yong tensorboard------
])
# yapf:enable
# runtime settings
total_epochs = 100 # ------Xun Lian De epoch-----
dist_params = dict(backend='nccl') # -----Fen Bu Shi Can Shu -----
log_level = 'INFO'
work_dir = './work_dirs/cascade_rcnn_r101_fpn_1x' #----Xun Lian Guo Cheng Zhong Mo Xing He Xun Lian logDe Bao Cun Di Zhi --
# load_from = None # ----Jia Zai Mo Xing De Lu Jing ,NoneBiao Shi Cong Yu Xun Lian Mo Xing Jia Zai ---
#-----Yu Xun Lian Mo Xing De Di Zhi ,Wo Men Zai section3Yi Jing Xia Zai Cun Fang Hao
#load_form = "./checkpoint/cascade_rcnn_r101_fpn_1x.py"
load_from = "data/pretrained/cascade_rcnn_r101_fpn_1x_20181129-d64ebac7.pth"
resume_from = None # -----Hui Fu Xun Lian Mo Xing De Lu Jing ,Yong Yu Duan Dian Xun Lian -----
workflow = [('train', 1)] # ------Dang Qian Gong Zuo Qu De Ming Cheng -------

5.Xun Lian Cascade RCNN

1.Dan GPUXun Lian

#python tools/train.py ${Mo Xing Pei Zhi Wen Jian }
source ./mmlab/bin/activate
python tools/train.py configs/bingzao/cascade_rcnn_r101_fpn_1x.py

2.Duo GPUXun Lian

#./tools/dist_train.sh ${Mo Xing Pei Zhi Wen Jian } ${GPUShu Liang } [Ke Xuan ]
./tools/dist_trian.sh configs/bingzao/cascade_rcnn_r101_fpn_1x.py 4

Xun Lian Wan Zhi Hou work_dirsWen Jian Jia Zhong Hui Bao Cun Xun Lian Guo Cheng Zhong De logRi Zhi Wen Jian , Bao Cun De Jian Ge Zhou Qi De pthWen Jian (Zhe Ge Wen Jian Jiang Hui Yong Yu Hou Mian De testCe Shi )

6.Ce Shi Cascade RCNN

TODO

  • Dan Chi Du Tui Duan
  • Duo Chi Du Tui Duan
  • Dan GPUCe Shi
  • Duo GPUCe Shi

7.Citation

@article{mmdetection,
title = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
author = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
journal= {arXiv preprint arXiv:1906.07155},
year={2019}
}
https://github.com/python-bookworm/mmdetection-new
https://github.com/zhengye1995/underwater-objection-detection

About

Cascade RCNN De Xun Lian Ji Yu mmdetection

Topics

Resources

Readme

License

Apache-2.0 license

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published