Pinned Repositories
ACoL
(CVPR2018) Adversarial Complementary Learning for Weakly Supervised Object Localization
adv-patch
PyTorch implementation of Adversarial Patch
AdvancedEAST
AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.https://github.com/huoyijie/raspberrypi-car
AdvancedEAST-PyTorch
将原本Keras版本的AdvancedEAST改写成PyTorch版，将数据集由.npy文件改成一个LMDB文件，加入Precision，Recall, F1 score方便训练以及调试，底层网络仍然用VGG16。
AlignSeg
AlignSeg: Feature-Aligned Segmentation Networks (TPAMI 2021)
group_sparsity
Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression. CVPR2020.
lightweight-human-pose-estimation.pytorch
Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
Skip-Conv
torch_ImageNet
基于pytorch深度学习框架的图像分类(集成了pytorch原生api, apex, DALI等...)
VINS-Mono-opencv4
Lovegood-1's Repositories
Lovegood-1/VINS-Mono-opencv4
Lovegood-1/AlignSeg
AlignSeg: Feature-Aligned Segmentation Networks (TPAMI 2021)
Lovegood-1/CDS-SLAM-Semantic-mapping-in-dynamic-environment
This project is the result of my undergraduate dissertation. The localization in dynamic environment is to deploy TensorRT optimized YOLOX in the front end of ORB-SLAM3 for object detection, and then eliminate all points belonging to the human bounding box. At the same time, the semantic information is sent to the mapping module to dye the 3D point
Lovegood-1/Citation-Style-for-IOPEN
A CSL file for zotero users in IOPEN
Lovegood-1/ContourNet
A PyTorch implementation of "ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection" (CVPR2020)
Lovegood-1/DanMuCanShu
Lovegood-1/DB
A PyTorch implementation of "Real-time Scene Text Detection with Differentiable Binarization".
Lovegood-1/detectron2
Detectron2 is FAIR's next-generation platform for object detection and segmentation.
Lovegood-1/FaPN
[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
Lovegood-1/GCNDepth
Self-Supervised CNN-GCN Autoencoder
Lovegood-1/icdar2png
Lovegood-1/K-Net
[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation
Lovegood-1/landmark_annotation
:punch: Keypoint/Landmark Annotation Software 关键点标注软件
Lovegood-1/Livox_loam_noted
学习Livox loam并进行了注释
Lovegood-1/MapEdit
Lovegood-1/mmdetection
OpenMMLab Detection Toolbox and Benchmark
Lovegood-1/mmdetection-mini
mmdetection最小学习版
Lovegood-1/moco
PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
Lovegood-1/MultiMap3D
Use ORB-SLAM2 to build a metricmap and localization, fcaf3d to detect 3D objects, and build a tracker database to manage the objects detected.
Lovegood-1/OpenMMLab-BoxInst
Lovegood-1/Paddle_Mmdet2pytorch
Lovegood-1/ResNet50vd-pytorch
Lovegood-1/S2FPR
Lovegood-1/segmentation-model-
Some useful segmentation model for TD
Lovegood-1/STDC-Seg
Source Code of our CVPR2021 paper "Rethinking BiSeNet For Real-time Semantic Segmentation"
Lovegood-1/TopFormer
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation, CVPR2022
Lovegood-1/TSS
Lovegood-1/UNO
Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)
Lovegood-1/VINS-Course-new
Lovegood-1/VSLAM-Course
Scaramuzza的VSLAM课程