liangheming/maskrcnn liangheming/maskrcnn

  • Stars
    star
    9
  • Rank 1,939,727 (Top 39 %)
  • Language
    Python
  • Created almost 4 years ago
  • Updated almost 4 years ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
liangheming/maskrcnn
github

liangheming

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

pytorch mask rcnn 736px，box mAP 39.0, seg mAP 33.7 (COCO val) 23.64fps(RTX 2080Ti)

More Repositories

1

iG-LIO_SAM_LC

iG-LIO with Loop Closure(PGO) and Online Re-Localize
C++
139
star
2

VoxelMapPlus_FASTLIO2

FAST-LIO 2 with VoxelMapPlus and STD
C++
88
star
3

FASTLIO2_ROS2

ROS2 / FAST_LIO / PGO / Online Re-Localization / Consistent Map with BA or HBA
C++
80
star
4

FASTLIO2_SAM_LC

fastlio2 with loop closure and online localization
C++
37
star
5

VoxelMap_LIO_SAM

FASTLIO2 based on Voxel Map
C++
34
star
6

sparse_rcnnv1

Sparse R-CNN 38.9 mAP, 640px(max side), 30.95fps(RTX 2080TI)
Python
31
star
7

atssv1

ATSS (retina) 39.6mAP on COCO,640px(max side),42.95fps(RTX 2080TI)<<Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection>>
Python
20
star
8

fcosv1

FCOS ,640px(max side),mAP 38.2,fps45.45(RTX 2080TI).faster! better! <<Fully Convolutional One-Stage Object Detection>>
Python
19
star
9

retinanetv1

pytorch implement of retinanet,37.4 mAp(coco) at 640px(max side) ,44.24fps(RTX2080TI)
Python
18
star
10

simple_pose

Some Top-Down 2D Pose Estimation
Python
17
star
11

cascade_rcnn

pytorch implement of CascadeRCNN,736px(max side),41.2mAP(COCO),21.94fps(RTX 2080TI)
Python
17
star
12

auto_assignv2

An unofficial pytorch implementation of <<AutoAssign: Differentiable Label Assignment for Dense Object Detection>>
Python
17
star
13

M_FASTLIVO

FAST-LIVO easy to read, esay to understand
C++
15
star
14

free_anchorv1

pytorch implement of FreeAnchor(not strict),640 px(max side),39.5mAP on COCO,43.18fps(RTX 2080TI)
Python
14
star
15

yolo_seriesv1

YOLOv4/v5, clean code, good performance,easy to understand.
Python
14
star
16

gfocal

GFocal 40.6mAP(COCO) 640px(max side) 44.05 fps(rtx 2080ti)
Python
11
star
17

faster_rcnnv1

pytorch implement of fasterRCNN,736px(max side),39.4mAP(COCO),30.21fps(RTX 2080TI)
Python
11
star
18

YOLO_Pedestrian

Python
9
star
19

efficientdet

Python
8
star
20

paav1

PAA ,resnet50+fpn,640px(max side),41.4mAP,43.68fps(RTX 2080TI)<<Probabilistic Anchor Assignment with IoU Prediction for Object Detection>>
Python
7
star
21

detr

Python
6
star
22

M_VINS

VINS_Mono FOR ros2
C++
5
star
23

scaled_yolo

Python
5
star
24

pointpillar3d

lidar based 3d dectection
Python
3
star
25

condinst

Python
2
star
26

monodepth_v2

MonoDepthv2
Python
2
star
27

solov2

Python
2
star
28

light_detection

light-weight detection
Python
1
star
29

SCDepthV1

SCDepthV1 unsupervised mono depth estimator with better performance
Python
1
star